The clinician-artificial intelligence partnership in early sepsis identification: Leveraging predictive intelligence for enhanced financial outcomes

The clinician-artificial intelligence partnership in early sepsis identification: Leveraging predictive intelligence for enhanced financial outcomes | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article The clinician-artificial intelligence partnership in early sepsis identification: Leveraging predictive intelligence for enhanced financial outcomes Akhil Bhargava, Lee Schmalz, Carlos López-Espina, Gregory Watson, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8483930/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Background Diagnosing sepsis is a critical challenge due to complex clinical and systemic barriers; consequently, delayed and failed diagnoses result in poor patient outcomes, high mortality, and severe financial repercussions for healthcare systems. Inadequate documentation and coding frequently cause sepsis claim denials, leading to reimbursement loss. This analysis evaluates the potential clinical economic impact of using the U.S. Food and Drug Administration-authorized artificial intelligence-based Sepsis ImmunoScore software to achieve accurate severity of illness coding. Methods This retrospective, multisite, observational study included patients with suspected serious infection treated at four U.S. hospitals. Medical Severity Diagnosis Related Group (MS-DRG) assignments were determined following CMS Medicare v39 definitions using each patient’s ICD-10-CM diagnoses, ICD-10-PCS procedures, age, sex, and discharge status. For patients with High/Very High Sepsis ImmunoScore results lacking sufficient sepsis documentation, we compared reimbursement with and without adding a sepsis ICD-10-CM diagnosis. This resulted in two MS-DRG calculations per patient: the current MS-DRG based on existing documentation and the potential MS-DRG with sepsis diagnosis included. When the potential sepsis MS-DRG yielded higher reimbursement than the current MS-DRG, the case represented a revenue recovery opportunity. A subset analysis restricted to patients meeting Sepsis-3 criteria provided a conservative estimate of potential revenue recovery. Results The final analysis cohort included 4419 patients. The Sepsis ImmunoScore identified 745 cases (16.9%) where High/Very High risk results indicated undocumented sepsis with higher reimbursement than current MS-DRG assignments. This represents $ 4 684 373 (95% CI, $ 4 125 378– $ 5 248 933) in potential revenue recovery across all 4419 patients, or $ 1060 ( $ 934– $ 1188) per patient tested. When restricted to cases meeting Sepsis-3 criteria for clinical validation, 516 cases (11.7%) represented $ 3 240 546 ( $ 2 727 080– $ 3 782 855) in potential revenue recovery, or $ 733 ( $ 617– $ 856) per patient tested. Conclusions This analysis demonstrates that implementation of an enhanced diagnostic tool can improve documentation accuracy and ensure it reflects the complexity of care provided, supporting full reimbursement for hospital services. artificial intelligence-based software clinical documentation improvement revenue recovery sepsis denials sepsis documentation sepsis Sepsis ImmunoScore severity of illness Figures Figure 1 Background Annually, over 1.7 million people are diagnosed with sepsis in the U.S. and approximately 350 000 people die [ 1 ]. Sepsis continues to be one of the most challenging syndromes for healthcare professionals to diagnose and document, and is consequently one of the most frequently denied Medicare claims [ 2 ]. Considering the annual healthcare burden of sepsis in the U.S. is estimated at $ 62 billion annually [ 3 ], accurate sepsis identification, documentation, and coding are critical to ensuring adequate payer reimbursement. Sepsis diagnoses are regularly denied by payers, often because of inadequate documentation or a lack of clear clinical indicators [ 4 , 5 ]. Non-specific symptoms and changing clinical definitions make it difficult to establish a clear sepsis diagnosis, underscoring the need for improved diagnostic metrics [ 6 ]. For example, the sepsis diagnostic criteria were updated in 2016. The newer Sepsis-3 definition results in fewer patients meeting the sepsis criteria; however, it is better capable of predicting mortality than Sepsis-2. Recent sepsis indication studies, including those reviewed by the U.S. Food & Drug Administration (FDA), have adopted Sepsis-3 as the primary endpoint, reflecting a broader shift from Sepsis-2 [ 7 – 11 ]. Nevertheless, this update has caused considerable confusion for both sepsis diagnosis and reimbursement and may contribute, in part, to inaccurate coding of sepsis. A systematic review and meta-analysis highlighting the issue of sepsis under coding reported a low sensitivity for sepsis International Classification of Diseases (ICD)-codes [ 12 ], which suggests that many patients who clinically meet the criteria for sepsis are miscoded. Studies have reported that only 17% of clinically evident sepsis cases and 55.4% of patients with clinically evident severe sepsis had sepsis ICD coding at discharge [ 13 , 14 ]. As one of the most expensive medical conditions to treat [ 15 ], sepsis presents significant reimbursement challenges for hospitals. Insufficient documentation to support a sepsis diagnosis can lead to under-coding, resulting in Medicare Severity Diagnosis Related Group (MS-DRG) assignments with reduced reimbursement, as well as claims denials [ 4 ]. Hospital costs for sepsis patients soared from $ 31.2 billion in 2016 to $ 52.1 billion in 2021, accounting for over 14% of all hospital costs. Almost three-quarters of these hospital costs—over $ 37.9 billion—were billed to Medicare and Medicaid for sepsis stays [ 16 ]. Overall claim denial rates reached 15% in 2024, with a higher prevalence of denied claims for higher-cost treatments, such as sepsis [ 17 ]. Although around half of denied claims are eventually overturned, the appeals process is lengthy, costly, and often requires several rounds to resolve the coverage denial [ 17 ]. While hospitals are concerned with potential denial of sepsis claims by payers due to lack of documentation or failure to identify septic patients, payers are concerned about the potential for hospitals to over code sepsis by using sepsis coding for non-septic patients. To address potential sepsis over coding, the 2024 Health and Human Services, Office of Inspector General Work Plan includes the targeting of sepsis billing as an audit priority [ 18 ]. At the same time, the Severe Sepsis and Septic Shock Management Bundle (SEP-1) has been transitioned from a pay-for-reporting measure to a pay-for-performance measure with penalties realized in fiscal year 2026 [ 19 , 20 ]. The combination of these two changes increases the financial risks for hospitals by tying reimbursement not only to accurate billing and coding practices but also on documented adherence to SEP-1 bundle criteria. With the mean SEP-1 compliance currently at 48.9% [ 21 ], hospitals face heightened risk of both claim denials and reduced performance-based payments. Tools that enhance sepsis identification and documentation may therefore help mitigate revenue losses related to both audits and performance shortfalls. Sepsis ImmunoScore, which is based upon a comprehensive assessment of patient biology, is the first FDA-authorized artificial intelligence (AI) / machine learning (ML) sepsis diagnostic tool (De Novo DEN230036, April 2024) [ 10 , 22 ]. It is software as a medical device that integrates with a patient’s electronic medical record to collect measurement metadata for 22 input parameters, providing a comprehensive assessment of a patient’s risk for progression to sepsis within 24 hours when ordered as a diagnostic test. Patients are categorized as Low, Medium, High, or Very High risk. The validation study demonstrated robust performance of Sepsis ImmunoScore across three institutions [ 22 ]. This tool provides objective support for both clinical decision-making and sepsis documentation. Sepsis ImmunoScore risk score can be documented in the patient’s electronic medical record, potentially prompting the assessment of sepsis-related ICD code assignments in the coding process. These codes are then used to determine the most appropriate MS-DRG for the patient encounter, which ultimately yields the reimbursement amount for the visit. This analysis was conducted to address a critical gap in health economics literature by quantifying the administrative value of AI diagnostic tools beyond clinical outcomes, using real-world data across multiple hospital systems. Specifically, we evaluated the potential economic impact of sepsis coding accuracy using Sepsis ImmunoScore. Methods Study objective This retrospective, multisite, observational study evaluated whether retrospectively calculated Sepsis ImmunoScore results could improve documentation gaps for patients with a suspected serious infection, thereby supporting revenue recovery for the treatment of patients meeting Sepsis-3 criteria. Study population The study included patients with a suspected serious infection treated at four hospitals in the U.S. between 2020 and 2023. Hospital A is a comprehensive teaching hospital and level one trauma center that is part of a large non-profit healthcare system; hospitals B and C are large, major non-profit academic medical centers; and hospital D is a large, affiliated community teaching hospital. Adult patients (≥ 18 years) presenting to the Emergency Department or hospital with a suspected infection, defined by a blood culture order, and who had an available lithium-heparin plasma sample drawn within 6 h of the first blood culture order, were included in the study. There were no exclusion criteria. The study population aligns with the intended use population for Sepsis ImmunoScore. The study was approved by the Institutional Review Board of each participating institution under a waiver of informed consent. Study design This study was conducted in three major phases, MS-DRG assignment and Sepsis ImmunoScore risk generation, sepsis documentation simulation, and a gap analysis to identify revenue recovery opportunities (Fig. 1 ). MS-DRG assignment Data collection Clinical and administrative data, including ICD-10-clinical modification (CM) diagnosis codes and ICD-10-procedure coding system (PCS) codes, along with patient demographic variables (age, sex, and discharge status), were extracted from electronic medical records for all study-eligible hospitalized patients. MS-DRG assignment process MS-DRG assignments were determined for each patient following Centers for Medicare & Medicaid Services (CMS) Medicare v39 definitions [ 23 ] using patients’ ICD-10-CM codes, ICD-10-PCS codes, age, sex, and discharge status. Determination of Medicare reimbursement values Medicare reimbursement values (USD) were calculated using the publicly accessible CMS database which provides the average Medicare payment for each MS-DRG by hospital and year [ 23 ]. MS-DRG reimbursement data by site from 2021, the most recent data available at the time of the analysis, were used. To project 2024 values, an annual inflation rate of 3.03% (9.4% cumulative) was applied, derived from historical MS-DRG reimbursement trends in the CMS database (2016–2021). The inflation-adjusted sepsis MS-DRG reimbursement USD values for each of the included hospitals are presented in Table S1 . Sepsis ImmunoScore risk generation Sepsis ImmunoScore was retrospectively calculated for patients with available lithium heparin blood samples using data for the 22 input parameters, and providers were blinded to the results [ 22 ]. Remnant lithium heparin blood samples were used to assess levels of C-reactive protein and procalcitonin for Sepsis ImmunoScore input. Sepsis ImmunoScore risk stratification used FDA-authorized thresholds (Low, Medium, High, Very High), with High and Very High risk categories indicating sufficient evidence for sepsis documentation based on previously reported likelihood ratios for Sepsis-3 (High, 2.1; Very High, 8.3) [ 22 ]. Sepsis documentation simulation To simulate documentation enhancement for patients with a High/Very High Sepsis ImmunoScore results, we added a sepsis ICD-10-CM code to identify their resulting sepsis MS-DRG. Following the CMS Medicare v39 definitions, the simulated sepsis ICD-10-CM code and the remaining clinical criteria determined the appropriate sepsis MS-DRG: septicemia or severe sepsis with mechanical ventilation (MV) > 96 h (870), septicemia or severe sepsis without MV > 96 h with major complication / comorbidity (MCC) (871), or septicemia or severe sepsis without MV > 96 h without MCC (872) ( Fig. S1 ). Overall, there were two MS-DRG calculations per patient: the current MS-DRG based on existing documentation and the potential MS-DRG assigned during the sepsis documentation simulation. Identification of revenue recovery opportunities Potential revenue recovery opportunities were defined as cases where patients classified as High/Very High risk lacked sepsis documentation, yet their potential sepsis-associated MS-DRG reimbursement exceeded their current MS-DRG reimbursement. Endpoints Revenue recovery The study endpoints were Total Revenue Recovery and potential revenue recovery per patient, calculated for two analysis populations: the total study cohort (Total recovery analysis) and cases meeting Sepsis-3 criteria (Sepsis-3 recovery analysis). Revenue Recovery was defined as the dollar amount potentially recoverable if Sepsis ImmunoScore was adopted to support sepsis ICD-10 coding. The Total recovery analysis represents the full potential recovery for all High/Very High risk patients. The Sepsis-3 recovery analysis is limited to cases where both the Sepsis ImmunoScore result and retrospective clinical criteria align, representing the highest-confidence documentation opportunities and a more conservative estimate. Sepsis-3 To identify patients meeting Sepsis-3 criteria, automated retrospective sepsis labels were derived using patients’ electronic medical records [ 24 ]. The label was assigned based on the presence of clinical, laboratory, and treatment information documented over the entire hospital stay, rather than being restricted to data available at the time of initial assessment. This approach ensured that the classification reflected whether the patient developed sepsis during the admission, providing a reliable reference standard for retrospective analyses. Of note, this label is different from what Sepsis ImmunoScore does. Sepsis ImmunoScore is a diagnostic tool, only privy to information up to the time of diagnosis. The Sepsis-3 medical record derived label is a retrospective label used only for analysis purposes. Statistical analysis Continuous and categorical variables were summarized using descriptive statistics. Summary demographics and clinical outcomes were calculated for the total population, and by the presence of sepsis according to the Sepsis-3 criteria (non-septic/septic), current MS-DRGs (MS-DRG 870/MS-DRG 871/MS-DRG 872/Other MS-DRG), and Sepsis ImmunoScore risk category result (Low/Medium/High/Very High). Revenue recovery cases were stratified by hospital and sepsis MS-DRG recovery components (i.e., MV > 96 h, MCC). 95% confidence intervals (CIs) were estimated using Bootstrapping (2000 iterations). All analyses were performed using R version 4.3.2 with specialized packages for sepsis analysis (The R Foundation for Statistical Computing, Vienna, Austria). Potential MS-DRG assignment was conducted using the drgpy Python package ( https://github.com/yubin-park/drgpy ), which processed ICD-10-CM and ICD-10-PCS codes, age, sex, and hospital mortality data according to CMS regulations (CMS Medicare Severity DRG Definitions v39 [ 25 ]). Results Study population Of the 4951 enrolled patients for whom a Sepsis ImmunoScore was attempted, 532 patients were excluded because they lacked at least one of the mandatory features required to obtain a Sepsis ImmunoScore; 4419 were included in the final analysis cohort (Hospital A, n = 1596; Hospital B, n = 1640; Hospital C, n = 716; Hospital D, n = 467). Patient demographic, clinical characteristics, and outcome summary for the total population ( N = 4419) are shown in Table 1 . The median (interquartile range [IQR]) age was 68 (56, 79) years, 51.5% of patients were male, and the two most common race categories were White (66.6%) and Black or African American (25.3%). Nearly all patients were inpatients (95.4%), 28.2% required ICU transfer, and 45.8% met the Sepsis-3 criteria. The median (IQR) retrospectively calculated Sepsis ImmunoScore was 0.29 (0.10, 0.64), and 47.8% of patients fell into the High (41.4%) or Very High (7.3%) risk categories. Table 1 Demographics and outcome summary for the total population Total population ( N = 4419) Study data site, n (%) Hospital A 1596 (36.1) Hospital B 1640 (37.1) Hospital C 716 (16.2) Hospital D 467 (10.6) Age, years, median (IQR) 68 (56, 79) Sex, n (%) Female 2143 (48.5) Male 2275 (51.5) Race, n (%) White 2944 (66.6) Black or African American 1118 (25.3) Asian 92 (2.1) American Indian or Alaska Native 8 (0.2) Native Hawaiian or other Pacific Islander 1 (0.0) Unknown / not recorded 97 (2.2) Other 159 (3.6) Ethnicity, n (%) Not Hispanic or Latino 4145 (93.8) Hispanic or Latino 116 (2.6) Unknown / not recorded 158 (3.6) Inpatients, n (%) 4216 (95.4) Maximum SIRS value, median (IQR) 2 (2, 3) COVID-19, n (%) 536 (12.1) Comorbidities, n (%) Acute myocardial infarction 227 (5.1) AIDS 16 (0.4) Cerebrovascular disease 501 (11.3) Congestive heart failure 1340 (30.3) COPD 1180 (26.7) Dementia 651 (14.7) Diabetes 1081 (24.5) Diabetes with complications 1019 (23.1) History of myocardial infarction 356 (8.1) Mild liver disease 476 (10.8) Moderate or severe liver disease 182 (4.1) Paralysis 194 (4.4) Peptic ulcer disease 94 (2.1) Peripheral vascular disease 549 (12.4) Renal disease 1516 (34.3) Rheumatologic disease 224 (5.1) Hospital length of stay, days, median (IQR) 5.54 (3.29, 9.84) Died in hospital, n (%) 365 (8.3) ICU transfer, n (%) 1248 (28.2) MV > 96 h, n (%) 251 (5.7) MV (any amount of time), n (%) 508 (11.5) Met Sepsis-2 criteria, n (%) 2634 (59.6) Met Sepsis-3 criteria, n (%) 2023 (45.8) Maximum sepsis ICD level, n (%) None 2765 (62.6) Sepsis 840 (19.0) Septic shock 457 (10.3) Severe sepsis 357 (8.1) Current MS-DRG category, n (%) 870 (sepsis with MV > 96 h) 89 (2.0) 871 (sepsis without MV with MCC) 844 (19.1) 872 (sepsis without MV without MCC) 238 (5.4) Other MS-DRGs 3248 (73.5) Average Medicare payment amount received, USD, median (IQR) $ 14 471.04 ( $ 9456.69, $ 19 840.39) Sepsis ImmunoScore, median (IQR) 0.29 (0.10, 0.64) Sepsis ImmunoScore risk category, n (%) Low 1276 (28.9) Medium 989 (22.4) High 1831 (41.4) Very High 323 (7.3) Sepsis eligible by Sepsis ImmunoScore, n (%) 2154 (48.7) AIDS, acquired immunodeficiency syndrome; COPD, Chronic Obstructive Pulmonary Disease; ICD, International Classification of Diseases; ICU, intensive care unit; IQR, interquartile range; MCC, major complication or comorbidity; MS-DRG, Medicare Severity Diagnosis Related Group; MV, mechanical ventilation; SIRS, systemic inflammatory response syndrome; USD, US dollars Subgroup comparisons of demographic and clinical outcome data Patient data were analyzed to determine whether patients met the Sepsis-3 criteria. A summary of patient demographics and clinical outcomes by Sepsis-3 criteria is shown in Table 2 . The Sepsis-3 criteria were met by 2023 patients, of whom 770 (38.1%) had an existing sepsis MS-DRG and 899 (44.4%) met the Sepsis-3 criteria but did not have an existing sepsis ICD code. Among the patients who met the Sepsis-3 criteria, 75.1% (1519/2023) had a High or Very High Sepsis ImmunoScore, supporting a sepsis MS-DRG. The median payment difference between patients who did and did not meet the Sepsis-3 criteria was over $ 4000 per patient. Table 2 Demographics and outcome summary by Sepsis-3 criteria Non-septic ( n = 2396) Septic ( n = 2023) p -value Study data site, n (%) < 0.001 Hospital A 941 (39.3) 655 (32.4) Hospital B 797 (33.3) 843 (41.7) Hospital C 431 (18.0) 285 (14.1) Hospital D 227 (9.5) 240 (11.9) Age, years, median (IQR) 66 (52, 77) 71 (60, 81) < 0.001 Sex, n (%) < 0.001 Female 1232 (51.4) 911 (45.0) Male 1164 (48.6) 1111 (54.9) Unknown / not recorded 0 (0.0) 1 (0.0) Race, n (%) 0.216 White 1581 (66.0) 1363 (67.4) Black or African American 615 (25.7) 503 (24.9) Asian 55 (2.3) 37 (1.8) American Indian or Alaska Native 3 (0.1) 5 (0.2) Native Hawaiian or other Pacific Islander 1 (0.0) 0 (0.0) Unknown / not recorded 45 (1.9) 52 (2.6) Other 96 (4.0) 63 (3.1) Ethnicity, n (%) 0.002 Not Hispanic or Latino 2250 (93.9) 1895 (93.7) Hispanic or Latino 76 (3.2) 40 (2.0) Unknown / not recorded 70 (2.9) 88 (4.3) Inpatients, n (%) 2212 (92.3) 2004 (99.1) < 0.001 Maximum SIRS value, median (IQR) 2 (1, 3) 3 (2, 3) < 0.001 COVID-19, n (%) 214 (8.9) 322 (15.9) < 0.001 Comorbidities, n (%) Acute myocardial infarction 68 (2.8) 159 (7.9) < 0.001 AIDS 7 (0.3) 9 (0.4) 0.555 Cerebrovascular disease 197 (8.2) 304 (15.0) < 0.001 Congestive heart failure 574 (24.0) 766 (37.9) < 0.001 COPD 594 (24.8) 586 (29.0) 0.002 Dementia 256 (10.7) 395 (19.5) < 0.001 Diabetes 558 (23.3) 523 (25.9) 0.052 Diabetes with complications 513 (21.4) 506 (25.0) 0.005 History of myocardial infarction 168 (7.0) 188 (9.3) 0.007 Mild liver disease 231 (9.6) 245 (12.1) 0.01 Moderate or severe liver disease 70 (2.9) 112 (5.5) < 0.001 Paralysis 82 (3.4) 112 (5.5) 0.001 Peptic ulcer disease 34 (1.4) 60 (3.0) 0.001 Peripheral vascular disease 266 (11.1) 283 (14.0) 0.004 Renal disease 677 (28.3) 839 (41.5) < 0.001 Rheumatologic disease 117 (4.9) 107 (5.3) 0.586 Hospital length of stay, days, median (IQR) 3.98 (2.65, 6.59) 8.17 (5.15, 13.91) < 0.001 Died in hospital, n (%) 35 (1.5) 330 (16.3) < 0.001 ICU transfer, n (%) 324 (13.5) 924 (45.7) 96 h, n (%) 26 (1.1) 225 (11.1) < 0.001 MV (any amount of time), n (%) 63 (2.6) 445 (22.0) < 0.001 Met Sepsis-2 criteria, n (%) 783 (32.7) 1851 (91.5) < 0.001 Maximum sepsis ICD level, n (%) < 0.001 None 1866 (77.9) 899 (44.4) Sepsis 399 (16.7) 441 (21.8) Septic shock 28 (1.2) 429 (21.2) Severe sepsis 103 (4.3) 254 (12.6) Current MS-DRG category, n (%) 96 h) 6 (0.3) 83 (4.1) 871 (sepsis without MV with MCC) 237 (9.9) 607 (30.0) 872 (sepsis without MV without MCC) 158 (6.6) 80 (4.0) Other MS-DRGs 1995 (83.3) 1253 (61.9) Average Medicare payment amount received, USD, median (IQR) $ 11 617.72 ( $ 7137.45, $ 16 940.25) $ 15 898.19 ( $ 14 471.04, $ 24 924.37) < 0.001 Sepsis ImmunoScore, median (IQR) 0.14 (0.07, 0.32) 0.59 (0.31, 0.80) < 0.001 Sepsis ImmunoScore risk category, n (%) < 0.001 Low 1108 (46.2) 168 (8.3) Medium 653 (27.3) 336 (16.6) High 608 (25.4) 1223 (60.5) Very High 27 (1.1) 296 (14.6) Sepsis eligible by Sepsis ImmunoScore, n (%) 635 (26.5) 1519 (75.1) < 0.001 AIDS, acquired immunodeficiency syndrome; COPD, Chronic Obstructive Pulmonary Disease; ICD, International Classification of Diseases; ICU, intensive care unit; IQR, interquartile range; MCC, major complication or comorbidity; MS-DRG, Medicare Severity Diagnosis Related Group; MV, mechanical ventilation; SIRS, systemic inflammatory response syndrome; USD, US dollars A summary of patient demographic and clinical outcomes by current MS-DRG is shown in Table S2 . Patients with a current MS-DRG 870 (septicemia or severe sepsis with mechanical ventilation > 96 h) were the sickest and had the highest median Medicare payment. A summary of patient demographic and clinical outcomes by Sepsis ImmunoScore risk category is shown in Table 3 . Only 33.2% of High and 55.1% of Very High risk patients had a sepsis-related current MS-DRG. There was a clear monotonic relationship between Sepsis ImmunoScore and all clinical outcomes, including Medicare payment. Table 3 Demographics and outcome summary by Sepsis ImmunoScore risk category Low ( n = 1276) Medium ( n = 989) High ( n = 1831) Very High ( n = 323) p -value Study data site, n (%) < 0.001 Hospital A 558 (43.7) 338 (34.2) 560 (30.6) 140 (43.3) Hospital B 367 (28.8) 400 (40.4) 769 (42.0) 104 (32.2) Hospital C 217 (17.0) 157 (15.9) 297 (16.2) 45 (13.9) Hospital D 134 (10.5) 94 (9.5) 205 (11.2) 34 (10.5) Age, years, median (IQR) 60 (46, 71) 70 (58, 81) 71 (60, 82) 73 (63, 83) < 0.001 Sex, n (%) < 0.001 Female 716 (56.1) 494 (49.9) 809 (44.2) 124 (38.4) Male 560 (43.9) 495 (50.1) 1021 (55.8) 199 (61.6) Unknown / not recorded 0 (0.0) 0 (0.0) 1 (0.1) 0 (0.0) Race, n (%) 0.351 White 834 (65.4) 665 (67.2) 1222 (66.7) 223 (69.0) Black or African American 340 (26.6) 240 (24.3) 455 (24.8) 83 (25.7) Asian 26 (2.0) 28 (2.8) 36 (2.0) 2 (0.6) American Indian or Alaska Native 4 (0.3) 0 (0.0) 4 (0.2) 0 (0.0) Native Hawaiian or other Pacific Islander 0 (0.0) 1 (0.1) 0 (0.0) 0 (0.0) Unknown / not recorded 26 (2.0) 17 (1.7) 46 (2.5) 8 (2.5) Other 46 (3.6) 38 (3.8) 68 (3.7) 7 (2.2) Ethnicity, n (%) 0.117 Not Hispanic or Latino 1202 (94.2) 931 (94.1) 1711 (93.4) 301 (93.2) Hispanic or Latino 40 (3.1) 26 (2.6) 45 (2.5) 5 (1.5) Unknown / not recorded 34 (2.7) 32 (3.2) 75 (4.1) 17 (5.3) Inpatients, n (%) 1124 (88.1) 960 (97.1) 1811 (98.9) 321 (99.4) < 0.001 Maximum SIRS value, median (IQR) 2 (1, 2) 2 (2, 3) 3 (2, 3) 3 (3, 4) < 0.001 COVID-19, n (%) 147 (11.5) 127 (12.8) 219 (12.0) 43 (13.3) 0.708 Comorbidities, n (%) Acute myocardial infarction 17 (1.3) 36 (3.6) 133 (7.3) 41 (12.7) < 0.001 AIDS 7 (0.5) 1 (0.1) 6 (0.3) 2 (0.6) 0.29 Cerebrovascular disease 115 (9.0) 106 (10.7) 221 (12.1) 59 (18.3) < 0.001 Congestive heart failure 200 (15.7) 290 (29.3) 703 (38.4) 147 (45.5) < 0.001 COPD 308 (24.1) 287 (29.0) 505 (27.6) 80 (24.8) 0. 04 Dementia 119 (9.3) 144 (14.6) 323 (17.6) 65 (20.1) < 0.001 Diabetes 291 (22.8) 241 (24.4) 456 (24.9) 93 (28.8) 0.147 Diabetes with complications 191 (15.0) 245 (24.8) 504 (27.5) 79 (24.5) < 0.001 History of myocardial infarction 62 (4.9) 82 (8.3) 173 (9.4) 39 (12.1) < 0.001 Mild liver disease 74 (5.8) 95 (9.6) 258 (14.1) 49 (15.2) < 0.001 Moderate or severe liver disease 8 (0.6) 19 (1.9) 132 (7.2) 23 (7.1) < 0.001 Paralysis 51 (4.0) 45 (4.6) 86 (4.7) 12 (3.7) 0.731 Peptic ulcer disease 12 (0.9) 15 (1.5) 56 (3.1) 11 (3.4) < 0.001 Peripheral vascular disease 100 (7.8) 130 (13.1) 265 (14.5) 54 (16.7) < 0.001 Renal disease 195 (15.3) 348 (35.2) 816 (44.6) 157 (48.6) < 0.001 Rheumatologic disease 67 (5.3) 50 (5.1) 85 (4.6) 22 (6.8) 0.421 Hospital length of stay, days, median (IQR) 3.87 (2.18, 6.26) 5.26 (3.32, 8.90) 7.09 (4.14, 11.75) 7.84 (4.45, 14.18) < 0.001 Died in hospital, n (%) 12 (0.9) 40 (4.0) 222 (12.1) 91 (28.2) < 0.001 ICU transfer, n (%) 126 (9.9) 189 (19.1) 715 (39.0) 218 (67.5) 96 h, n (%) 17 (1.3) 32 (3.2) 157 (8.6) 45 (13.9) < 0.001 MV (any amount of time), n (%) 37 (2.9) 71 (7.2) 306 (16.7) 94 (29.1) < 0.001 Maximum sepsis ICD level, n (%) < 0.001 None 1039 (81.4) 695 (70.3) 967 (52.8) 64 (19.8) Sepsis 176 (13.8) 210 (21.2) 409 (22.3) 45 (13.9) Septic shock 10 (0.8) 29 (2.9) 260 (14.2) 158 (48.9) Severe sepsis 51 (4.0) 55 (5.6) 195 (10.6) 56 (17.3) Current MS-DRG category, n (%) 96 h) 7 (0.5) 7 (0.7) 53 (2.9) 22 (6.8) 871 (sepsis without MV with MCC) 90 (7.1) 141 (14.3) 462 (25.2) 151 (46.7) 872 (sepsis without MV without MCC) 80 (6.3) 61 (6.2) 92 (5.0) 5 (1.5) Other MS-DRGs 1099 (86.1) 780 (78.9) 1224 (66.8) 145 (44.9) Average Medicare payment amount received, USD, median (IQR) $ 10 444.07 ( $ 6915.04, $ 16 363.99) $ 14 471.04 ( $ 8843.67, $ 17 591.38) $ 15 898.19 ( $ 11 856.51, $ 22 431.56) $ 15 898.19 ( $ 14 471.04, $ 34 935.26) < 0.001 AIDS, acquired immunodeficiency syndrome; COPD, Chronic Obstructive Pulmonary Disease; ICD, International Classification of Diseases; ICU, intensive care unit; IQR, interquartile range; MCC, major complication or comorbidity; MS-DRG, Medicare Severity Diagnosis Related Group; MV, mechanical ventilation; SIRS, systemic inflammatory response syndrome; USD, US dollars Revenue recovery analysis The revenue recovery analyses are shown in Table 4 . Using the Sepsis ImmunoScore result of High or Very High yielded a potential MS-DRG with a reimbursement value that was higher than the current MS-DRG in 745 out of 4419 cases, suggesting that 16.9% of the study population did not have a sepsis ICD code and had a current MS-DRG with a lower reimbursement value than a sepsis-related MS-DRG. This translates to a potential revenue recovery of around $ 4 684 373 for the 4419 patients, or $ 1060 per patient when using Sepsis ImmunoScore to document sepsis. This value represents the upper bound of potential revenue recovery, since not all identified patients will have sepsis. When the analysis was limited to patients who met the Sepsis-3 criteria, the total potential revenue recovery was $ 3 240 546, or $ 733 per patient. Table 4 Potential revenue recovery overall, by institution, and by sepsis MS-DRG recovery components No. pts tested Potential revenue recovery opportunities Total recovery analysis Potential revenue recovery opportunities Sepsis-3 recovery analysis No. oppor-tunities Total revenue recovery Potential revenue recovery per pt No. oppor-tunities Total revenue recovery Potential revenue recovery per pt Overall potential revenue recovery 4419 745 $ 4 684 373 ( $ 4 125 378– $ 5 248 933) $ 1060 ( $ 934– $ 1188) 408 $ 3 240 546 ( $ 2 727 080– $ 3 782 855) $ 733 ( $ 617– $ 856) Potential revenue recovery by institution Hospital A 1596 178 $ 983 294 ( $ 743 573– $ 1 244 347) $ 616 ( $ 466– $ 780) 96 $ 735 280 ( $ 502 044– $ 998 104) $ 461 ( $ 315– $ 625) Hospital B 1640 344 $ 1 493 684 ( $ 1 257 436– $ 1 769 265) $ 911 ( $ 767– $ 1079) 184 $ 852 582 ( $ 665 486– $ 1 078 162) $ 520 ( $ 406– $ 657) Hospital C 716 138 $ 1 135 369 ( $ 794 002– $ 1 512 447) $ 1586 ( $ 1109– $ 2112) 73 $ 868 828 ( $ 550 899– $ 1 245 779) $ 1213 ( $ 769– $ 1740) Hospital D 467 85 $ 1 072 027 ( $ 898 126– $ 1 255 593) $ 2296 ( $ 1923– $ 2689) 55 $ 783 856 ( $ 581 392– $ 988 775) $ 1678 ( $ 1245– $ 2117) Potential revenue recovery by clinical group MV > 96 h 251 70 $ 2 002 369 ( $ 1 647 712– $ 2 348 057) $ 7978 ( $ 6565– $ 9355) 64 $ 1 716 040 ( $ 1 389 919– $ 2 061 750) $ 6837 ( $ 5538– $ 8214) MCC only 2629 521 $ 2 505 057 ( $ 2 344 743– $ 2 676 167) $ 953 ( $ 892– $ 1018) 304 $ 1 486 271 ( $ 1 316 946– $ 1 660 746) $ 565 ( $ 501– $ 632) Neither MV > 96 h nor MCC 1539 154 $ 176 947 ( $ 158 332– $ 194 952) $ 115 ( $ 103– $ 127) 40 $ 38 234 ( $ 25 675– $ 52 615) $ 25 ( $ 17– $ 34) USD values are shown as mean (95% confidence interval). MCC, major complication or comorbidity; MS-DRG, Medicare Severity Diagnosis Related Group; MV, mechanical ventilation; pt(s), patient(s) Revenue recovery by hospital showed an approximately 4-fold variation among sites, with Hospital D having the highest per-patient revenue recovery opportunity at $ 2296 and Hospital A having the lowest per-patient revenue recovery opportunity at $ 616. Academic centers (Hospitals C and D) had higher per-patient revenue recovery opportunities while larger community hospitals (Hospitals A and B) had more total opportunities. This is consistent with the literature, which suggests a large variation of coding practices across hospitals [ 26 ]. Considering the effects of MV and MCC, MV > 96 h (with or without MCC) had the highest per-patient revenue recovery opportunity ( $ 7978) followed by MCC only ( $ 953), and neither MV > 96 h nor MCC ( $ 115). 91.4% of identified potential revenue recovery opportunities among patients with MV > 96 h (with or without MCC) were patients who meet the Sepsis-3 criteria. Discussion This multisite analysis demonstrates the substantial potential economic impact of AI-enhanced sepsis documentation using the FDA-authorized Sepsis ImmunoScore. The technology supports more accurate diagnosis and documentation, with potential revenue recovery averaging upwards of one thousand dollars per patient tested. Hospitals absorbed $ 130 billion in Medicare and Medicaid underpayments in 2023, and these shortfalls are predicted to continue [ 27 – 29 ]. At the same time, cumulative hospital expense growth is more than twice the cumulative increase in Medicare reimbursement [ 28 ]. These data highlight the need for improved documentation to minimize inaccurate coding and claims denials. For patient charts lacking sufficient evidence to confirm a sepsis diagnosis, an objective diagnostic tool can help bridge this gap by providing measurable data to support the diagnosis. The study findings demonstrate that integration of Sepsis ImmunoScore has the potential to mitigate potential lost revenue by improving sepsis coding and documentation to support sepsis claims. Indeed, our analysis showed that the use of Sepsis ImmunoScore to support the documentation of sepsis would have resulted in an increase in recovered revenue of approximately $ 4.68M for the hospitals in the dataset, with an average of $ 1060 potential revenue recovery per patient, and an average of $ 733 potential revenue recovery per patient who met the Sepsis-3 criteria. CMS issued a new ICD-10-PCS code, XXEZXCB: Measurement of Infection, Computer-aided Triage and Notification, New Technology Group 11, that is applicable to Sepsis ImmunoScore and available as of October 1, 2025, providing a pathway for documenting Sepsis ImmunoScore for claims submissions. Successful implementation of Sepsis ImmunoScore has the potential to improve both workflow and documentation and billing accuracy. Providers can integrate Sepsis ImmunoScore when ordering diagnostic testing for patients who are suspected of having sepsis. The full diagnostic results, including Sepsis ImmunoScore, can then inform clinical decisions and be used as documentation to support whether a sepsis ICD-10 code is assigned by coding specialists and whether CMS finds sufficient documentation to support a sepsis MS-DRG. Hospitals can facilitate the incorporation of Sepsis ImmunoScore into their current workflow by developing protocols to integrate Sepsis ImmunoScore into electronic medical records and educating providers on the clinical decision support provided by Sepsis ImmunoScore. The availability of Sepsis ImmunoScore coincides well with the increased regulatory focus on SEP-1 Bundle Compliance documentation in fiscal year 2026. With the SEP-1 Bundle Compliance measure transitioning to pay-for-performance in 2026 [ 19 , 20 ] and the ongoing Office of the Inspector General scrutiny [ 18 ], the support of diagnostic tools rooted in comprehensive biological assessment becomes increasingly valuable. The objective evidence provided by Sepsis ImmunoScore strengthens documentation, directly supporting more accurate sepsis coding and reducing the risk of audit exposure. Further, Sepsis ImmunoScore aligns with the documentation requirements for reimbursement by CMS and provides support for legitimate sepsis cases. This study had a few limitations that should be considered when interpreting the results. First, this was a retrospective data review and as such could not capture real-world workflow integration effects. Second, the data for this study were collected during the COVID-19 pandemic (2020–2023); therefore, the results may not fully represent conditions outside the pandemic period. Third, the analysis utilized Medicare reimbursement data; impacts from private payers may be different. Additionally, average Medicare reimbursement data were used rather than individual patient payment data. Fourth, coding accuracy varies among institutions [ 30 ]. While the analysis included data from multiple hospitals, the potential for institution-to-institution variability may affect the generalizability of these findings across hospitals. Fifth, the Sepsis-3 analysis did not utilize adjudicators to confirm whether Sepsis-3 criteria were met. Sixth, the analysis did not consider how a Low or Medium Sepsis ImmunoScore would impact potential revenue recovery. Finally, it is important to highlight the use of the Sepsis-3 criteria in our analysis and to note that the Sepsis ImmunoScore was designed to predict Sepsis-3, not Sepsis-2 [ 10 , 22 ]. The Sepsis-2 criteria define three levels of sepsis based on systemic inflammatory response syndrome (SIRS): sepsis, ≥ 2 SIRS criteria (fever/hypothermia, tachycardia, tachypnea, leukocytosis/leukopenia); severe sepsis, sepsis with organ failure, hypotension, or hypoperfusion; and septic shock, refractory hypotension [ 31 ]. Sepsis-3 criteria define two levels of sepsis based on sequential organ failure assessment: sepsis, defined as infection and organ failure (may include hypotension, hyperlactatemia, or hypotension requiring vasopressors) and septic shock, defined as hypotension, hyperlactatemia, and hypotension requiring vasopressors. Because these are distinct clinical definitions rather than interchangeable labels, patients meeting one set of criteria may not meet the other. In our study, 32% of patients meeting Sepsis-2 criteria did not meet Sepsis-3 criteria, while 91.5% of patients meeting Sepsis-3 criteria also met Sepsis-2 (Table 2 ). Current MS-DRGs are rooted in the Sepsis-2 criteria; however, the clinical and payer landscape is shifting towards Sepsis-3. Sepsis-3 offers a definition correlated with mortality, that aligns with recent FDA preference for medical devices with a sepsis endpoint, and several major private payers—including United Healthcare (2019) [ 32 ], Cigna (2020) [ 33 ], and Blue Cross Blue Shield (2024) [ 34 ]—have adopted Sepsis-3 criteria for claims validation. The Sepsis ImmunoScore was designed to predict Sepsis-3 [ 10 , 23 ], positioning it for this evolving landscape. Future studies with prospective implementation of Sepsis ImmunoScore to assess workflow, studies investigating the long-term impact of Sepsis ImmunoScore implementation on denial rates and audit outcomes, and studies investigating the integration of Sepsis ImmunoScore with other quality initiatives (e.g., rapid intervention with integration) are warranted. Conclusions Sepsis ImmunoScore represents a significant advancement in addressing the ongoing sepsis documentation crisis. By providing objective, FDA-authorized diagnostic support, it enables more accurate documentation while supporting both clinical care and financial sustainability. The demonstrated revenue recovery potential supports implementation across diverse hospital settings. As healthcare systems face increasing pressure to balance quality care with financial viability, tools that enhance both clinical and administrative accuracy become increasingly valuable. Sepsis ImmunoScore offers a pathway to achieve these dual goals while maintaining the highest standards of documentation integrity. Abbreviations AI Artificial intelligence AIDS Acquired immunodeficiency syndrome CI Confidence interval CM Clinical modification CMS Centers for Medicare & Medicaid Services COPD Chronic obstructive pulmonary disease CRP C-reactive protein EMR Electronic medical record FDA U.S. Food & Drug Administration ICD International Classification of Diseases ICU Intensive care unit IQR Interquartile range MCC Major complication / comorbidity ML Machine learning MS-DRG Medicare Severity Diagnosis Related Group MV Mechanical ventilation PCS Procedure Coding System PCT Procalcitonin SEP-1 Septic Shock Management Bundle SIRS Systemic inflammatory response syndrome USD US dollars Declarations Ethics approval and consent to participate This study was approved by the Institutional Review Boards (IRBs) of all participating institutions, including the Institutional Review Board of Mercy Hospital, St. Louis (Protocol #1597481-1; approved April 28, 2020), the Institutional Review Board of Corewell Health William Beaumont University Hospital, Royal Oak (Protocol #2018-459; approved January 15, 2019), the LifeBridge Health Institutional Review Board, Sinai Hospital of Baltimore (Protocol #2023P005665; approved July 14, 2023), and the Institutional Review Board of Beth Israel Deaconess Medical Center, Boston (Protocol #1858614-1; approved February 8, 2022). All procedures were conducted in accordance with the ethical standards of the respective institutional research committees and with the 1964 Declaration of Helsinki and its later amendments. Consent for publication Not applicable. Availability of data and materials The data that support the findings of this study are available from Prenosis, Inc. However, restrictions apply to the availability of these data, which were used under license for the current study, and so are not publicly available. The data are available from the authors upon reasonable request and with the permission of Prenosis, Inc. Competing interests RB is a consultant for Prenosis, Inc. AB, LAS, CL-E, GLW, LU, DU, SK, and BR are employees of Prenosis, Inc. Funding This study was funded in part by the Defense Threat Reduction Agency, National Institutes of Health, Centers for Disease Control and Prevention, National Science Foundation, Biomedical Advanced Research and Development Authority, and Prenosis, Inc. Prenosis, Inc. was overall responsible for the design and conduct of the study, collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication. The other funding agencies had no role. Authors’ contributions AB, LAS, and CL-E conceptualized the study. AB, CL-E, LAS, SK, DU, and LU were involved in data curation. AB performed the formal analysis and validation of the findings. LAS was involved in the study investigation. AB and LAS were responsible for the methodology, software used, and supervision of the study. BR, GLW, CL-E, and RB contributed to funding acquisition. BR was responsible for project administration and managing resources. AB, LAS, and CL-E wrote the first draft. All authors reviewed, edited, and approved the final manuscript before submission. Acknowledgements We are indebted to the study coordinators, research staff, and lab technicians who participated in the study. These contributions were part of these individuals’ jobs, and they did not receive additional compensation. The authors thank Sarah Bubeck, PhD, for providing medical writing support, which was funded by Prenosis, Inc., in accordance with Good Publication Practice (GPP3) guidelines (http://www.ismpp.org/gpp3). References Rhee C, Dantes R, Epstein L, Murphy DJ, Seymour CW, Iwashyna TJ, Kadri SS, Angus DC, Danner RL, Fiore AE, Jernigan JA, Martin GS, Septimus E, Warren DK, Karcz A, Chan C, Menchaca JT, Wang R, Gruber S, Klompas M, Program CDCPE. Incidence and trends of sepsis in US hospitals using clinical vs claims data, 2009–2014. JAMA. 2017;318(13):1241–9. Payer denial hit. sepsis amid conflicting clinical protocols; diagnosis is doubted. Report on Medicare Compliance. Volume 26. Health Care Compliance Association; 2017. Buchman TG, Simpson SQ, Sciarretta KL, Finne KP, Sowers N, Collier M, Chavan S, Oke I, Pennini ME, Santhosh A, Wax M, Woodbury R, Chu S, Merkeley TG, Disbrow GL, Bright RA, MaCurdy TE, Kelman JA. Sepsis among Medicare beneficiaries: 3. The methods, models, and forecasts of sepsis, 2012–2018. Crit Care Med. 2020;48(3):302–18. Sand J, Kuqi A. Current challenges in sepsis documentation and coding: A review of the literature. Perspect Health Inf Manag. 2023;20(3):1g. Rhee C, Gohil S, Klompas M. Regulatory mandates for sepsis care–reasons for caution. N Engl J Med. 2014;370(18):1673–6. Rhee C, Dantes RB, Epstein L, Klompas M. Using objective clinical data to track progress on preventing and treating sepsis: CDC's new 'Adult Sepsis Event' surveillance strategy. BMJ Qual Saf. 2019;28(4):305–9. Levy MM, Fink MP, Marshall JC, Abraham E, Angus D, Cook D, Cohen J, Opal SM, Vincent JL, Ramsay G, International Sepsis Definitions C. 2001 SCCM/ESICM/ACCP/ATS/SIS International Sepsis Definitions Conference. Intensive Care Med. 2003;29(4):530–538. Singer M, Deutschman CS, Seymour CW, Shankar-Hari M, Annane D, Bauer M, Bellomo R, Bernard GR, Chiche JD, Coopersmith CM, Hotchkiss RS, Levy MM, Marshall JC, Martin GS, Opal SM, Rubenfeld GD, van der Poll T, Vincent JL, Angus DC. The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). JAMA. 2016;315(8):801–10. Poutsiaka DD, Porto MC, Perry WA, Hudcova J, Tybor DJ, Hadley S, Doron S, Reich JA, Snydman DR, Nasraway SA. Prospective observational study comparing Sepsis-2 and Sepsis-3 definitions in predicting mortality in critically ill patients. Open Forum Infect Dis. 2019;6(7):ofz271. De novo classification request for Sepsis ImmunoScore. https://www.accessdata.fda.gov/cdrh_docs/reviews/DEN230036.pdf . Accessed 17 December 2025. 510(k.) Substantial equivalence determination decision summary: Assay and instrument. https://www.accessdata.fda.gov/cdrh_docs/reviews/K220991.pdf . Accessed 22 December 2025. Liu B, Hadzi-Tosev M, Liu Y, Lucier KJ, Garg A, Li S, Heddle NM, Rochwerg B, Ning S. Accuracy of International Classification of Diseases, 10th revision codes for identifying sepsis: A systematic review and meta-analysis. Crit Care Explor. 2022;4(11):e0788. Arberry J, Henry Z, Corrah T. A simple measure to improve sepsis documentation and coding. Clin Med (Lond). 2021;21(3):222–5. Wilhelms SB, Walther SM, Huss F, Sjoberg F. Severe sepsis in the ICU is often missing in hospital discharge codes. Acta Anaesthesiol Scand. 2017;61(2):186–93. National inpatient hospital costs: The most expensive conditions by payer. 2011. https://hcup-us.ahrq.gov/reports/statbriefs/sb160.jsp . Accessed 27 September 2025. AHRQ's portrait of. sepsis reveals its alarming human toll. https://www.ahrq.gov/news/blog/ahrqviews/portrait-of-sepsis.html . Accessed 27 September 2025. Trend alert. Private payers retain profits by refusing or delaying legitimate medical claims. https://premierinc.com/newsroom/blog/trend-alert-private-payers-retain-profits-by-refusing-or-delaying-legitimate-medical-claims . Accessed 27 September 2025. Medicare inpatient hospital billing for sepsis. https://oig.hhs.gov/reports-and-publications/workplan/summary/wp-summary-0000841.asp#:~:text=Office%20of%20Inspector%20General%20%7C%20U.S.%20Department%20of%20Health%20and%20Human%20Services . Accessed 27 September 2025. Centers for Medicare & Medicaid Services. Medicare program: proposed hospital inpatient prospective payment systems for acute care hospitals and the long-term care hospital prospective payment system and policy changes and fiscal year 2024 rates. Fed Regist. 2023;88:27193. FY 2026 Hospital Inpatient Prospective Payment System (IPPS). and Long-Term Care Hospital Prospective Payment System (LTCH PPS) proposed rule — CMS-1833-P Fact Sheet. https://www.cms.gov/newsroom/fact-sheets/fy-2026-hospital-inpatient-prospective-payment-system-ipps-and-long-term-care-hospital-prospective . Accessed 27 September 2025. Barbash IJ, Davis B, Kahn JM. National performance on the Medicare SEP-1 sepsis quality measure. Crit Care Med. 2019;47(8):1026–32. Bhargava A, López-Espina C, Schmalz L, Khan S, Watson GL, Urdiales D, Updike L, Kurtzman N, Dagan A, Doodlesack A, Stenson BA, Sarma D, Reseland E, Lee JH, Kravitz MS, Antkowiak PS, Shvilkina T, Espinosa A, Halalau A, Demarco C, Davila F, Davila H, Sims M, Maddens N, Berghea R, Smith S, Palagiri AV, Ezekiel C, Sadaka F, Iyer K, Crisp M, Azad S, Oke V, Friederich A, Syed A, Gosai F, Chawla L, Evans N, Thomas K, Malkani R, Patel R, Mayer S, Ali F, Raghavakurup L, Tafa M, Singh S, Raouf S, Zhao SD, Zhu R, Bashir R, Reddy B, Shapiro NI. FDA-authorized AI/ML tool for sepsis prediction: Development and validation. NEJM AI. 2024;1(12):AIoa2400867. CMS Data. https://data.cms.gov. Accessed 27 September 2025. Hospital toolkit for adult sepsis surveillance. https://www.cdc.gov/sepsis/media/pdfs/sepsis-surveillance-toolkit-aug-2018-508.pdf?CDC_AAref_Val=https://www.cdc.gov/sepsis/pdfs/Sepsis-Surveillance-Toolkit-Aug-2018_508.pdf . Accessed 27 September 2025. ICD-10-CM/PCS MS-DRG v39.0 Definitions Manual. https://www.cms.gov/icd10m/version39-fullcode-cms/fullcode_cms/P0001.html . Accessed 27 September 2025. Rhee C, Jentzsch MS, Kadri SS, Seymour CW, Angus DC, Murphy DJ, Martin GS, Dantes RB, Epstein L, Fiore AE, Jernigan JA, Danner RL, Warren DK, Septimus EJ, Hickok J, Poland RE, Jin R, Fram D, Schaaf R, Wang R, Klompas M. Centers for Disease C, Prevention Prevention Epicenters P. Variation in identifying sepsis and organ dysfunction using administrative versus electronic clinical data and impact on hospital outcome comparisons. Crit Care Med. 2019;47(4):493–500. report New AHA. Hospitals and health systems squeezed by persistent economic challenges. https://www.aha.org/press-releases/2025-04-30-new-aha-report-hospitals-and-health-systems-squeezed-persistent-economic-challenges . Accessed 27 September 2025. The financial stability. of America’s hospitals and health systems is at risk as the costs of caring continue to rise. https://www.aha.org/system/files/media/file/2023/04/Cost-of-Caring-2023-The-Financial-Stability-of-Americas-Hospitals-and-Health-Systems-Is-at-Risk.pdf . Accessed 27 September 2025. The cost of caring. Challenges facing America’s hospitals in 2025. https://www.aha.org/system/files/media/file/2025/04/The-Cost-of-Caring-April-2025.pdf . Accessed 27 September 2025. Schwarzkopf D, Rose N, Fleischmann-Struzek C, Boden B, Dorow H, Edel A, Friedrich M, Gonnert FA, Gotz J, Grundling M, Heim M, Holbeck K, Jaschinski U, Koch C, Kunzer C, Le Ngoc K, Lindau S, Mehlmann NB, Meschede J, Meybohm P, Ouart D, Putensen C, Sander M, Schewe JC, Schlattmann P, Schmidt G, Schneider G, Spies C, Steinsberger F, Zacharowski K, Zinn S, Reinhart K. Understanding the biases to sepsis surveillance and quality assurance caused by inaccurate coding in administrative health data. Infection. 2024;52(2):413–27. Carneiro AH, Povoa P, Gomes JA. Dear Sepsis-3, we are sorry to say that we don't like you. Rev Bras Ter Intensiva. 2017;29(1):4–8. Clinical guidelines. Sepsis. https://www.uhcprovider.com/content/dam/provider/docs/public/policies/clinical-guidelines/sepsis.pdf . Accessed 22 December 2025. Healthcare giant adopts Sepsis-3. https://icd10monitor.medlearn.com/healthcare-giant-adopts-sepsis-3/ . Accessed 22 December 2025. Sepsis policy. https://www.bcbsil.com/docs/provider/il/standards/cpcp/2024/cpcp041-07012024.pdf . Accessed 22 December 2025. Additional Declarations Competing interest reported. RB is a consultant for Prenosis, Inc. AB, LAS, CL-E, GLW, LU, DU, SK, and BR are employees of Prenosis, Inc. Supplementary Files CodingmanuscriptThirdDraftSupplement18Dec2025clean.docx Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 19 Feb, 2026 Reviewers agreed at journal 10 Feb, 2026 Reviewers invited by journal 30 Jan, 2026 Editor assigned by journal 14 Jan, 2026 Editor invited by journal 05 Jan, 2026 Submission checks completed at journal 05 Jan, 2026 First submitted to journal 05 Jan, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8483930","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":569744724,"identity":"f73057a6-9a2b-4f85-97f3-6347a91e4308","order_by":0,"name":"Akhil Bhargava","email":"data:image/png;base64,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","orcid":"","institution":"Prenosis (United States)","correspondingAuthor":true,"prefix":"","firstName":"Akhil","middleName":"","lastName":"Bhargava","suffix":""},{"id":569744728,"identity":"49ac6505-892b-4a7e-ad88-d286556b9449","order_by":1,"name":"Lee Schmalz","email":"","orcid":"","institution":"Prenosis (United States)","correspondingAuthor":false,"prefix":"","firstName":"Lee","middleName":"","lastName":"Schmalz","suffix":""},{"id":569744738,"identity":"ad0b606d-f91d-474f-bab2-de9f5fd6c935","order_by":2,"name":"Carlos López-Espina","email":"","orcid":"","institution":"Prenosis (United States)","correspondingAuthor":false,"prefix":"","firstName":"Carlos","middleName":"","lastName":"López-Espina","suffix":""},{"id":569744744,"identity":"cda9cebb-c3b9-45a3-8234-03348d94f6e6","order_by":3,"name":"Gregory Watson","email":"","orcid":"","institution":"Prenosis (United States)","correspondingAuthor":false,"prefix":"","firstName":"Gregory","middleName":"","lastName":"Watson","suffix":""},{"id":569744747,"identity":"8b1335a7-92a9-43f0-84b5-884db7a564c2","order_by":4,"name":"Lincoln Updike","email":"","orcid":"","institution":"Prenosis (United States)","correspondingAuthor":false,"prefix":"","firstName":"Lincoln","middleName":"","lastName":"Updike","suffix":""},{"id":569744750,"identity":"540c6ea6-250d-4d19-86b5-e06201c9637c","order_by":5,"name":"Dennys Urdiales","email":"","orcid":"","institution":"Prenosis (United States)","correspondingAuthor":false,"prefix":"","firstName":"Dennys","middleName":"","lastName":"Urdiales","suffix":""},{"id":569744752,"identity":"0276427b-00d6-445c-a103-59cb6bbb944b","order_by":6,"name":"Shah Khan","email":"","orcid":"","institution":"Prenosis (United States)","correspondingAuthor":false,"prefix":"","firstName":"Shah","middleName":"","lastName":"Khan","suffix":""},{"id":569744753,"identity":"88b900e9-a0c2-40ed-a46a-eef85601b322","order_by":7,"name":"Rashid Bashir","email":"","orcid":"","institution":"University of Illinois Urbana-Champaign","correspondingAuthor":false,"prefix":"","firstName":"Rashid","middleName":"","lastName":"Bashir","suffix":""},{"id":569744755,"identity":"e36755e0-c3da-4053-aaa3-99c7d4613dd1","order_by":8,"name":"Bobby Reddy","email":"","orcid":"","institution":"Prenosis (United States)","correspondingAuthor":false,"prefix":"","firstName":"Bobby","middleName":"","lastName":"Reddy","suffix":""}],"badges":[],"createdAt":"2025-12-30 19:38:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8483930/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8483930/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99602764,"identity":"d3b9e718-5286-4083-a8da-cd0bd27d2a25","added_by":"auto","created_at":"2026-01-06 10:54:53","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":349683,"visible":true,"origin":"","legend":"","description":"","filename":"CodingmanuscriptThirdDraft05Jan2026cleanwithEndNotecoding.docx","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/36826529ac537a2ae8490026.docx"},{"id":99602774,"identity":"6a605a24-7c74-43b1-b35c-c31db4a1ac83","added_by":"auto","created_at":"2026-01-06 10:54:58","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11762,"visible":true,"origin":"","legend":"","description":"","filename":"3fe0d937088e48ffbf75d25634fc6233.json","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/8e3961b09edd6e27c96b7624.json"},{"id":99602769,"identity":"98971e34-c807-4043-be2d-bc82ea31d53f","added_by":"auto","created_at":"2026-01-06 10:54:56","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":332463,"visible":true,"origin":"","legend":"","description":"","filename":"CodingmanuscriptThirdDraftSupplement18Dec2025clean.docx","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/a3d40de5f2687edc2b4b2e42.docx"},{"id":99602777,"identity":"a3b1bfe4-2fb3-4715-ac94-319ac9cdeac9","added_by":"auto","created_at":"2026-01-06 10:54:58","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":177257,"visible":true,"origin":"","legend":"","description":"","filename":"3fe0d937088e48ffbf75d25634fc62331enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/d4356c8b84673340b4bc7992.xml"},{"id":99602838,"identity":"a7ba04b5-9287-44e0-8d52-4a8a9aae394b","added_by":"auto","created_at":"2026-01-06 10:55:04","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":268289,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/cd624ec5b1249ba02a8bc93f.jpeg"},{"id":99602837,"identity":"0d138b12-407c-4e66-8c3b-8177c37511a0","added_by":"auto","created_at":"2026-01-06 10:55:03","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":75732,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/0127812b2bf9287d619b323c.png"},{"id":99602767,"identity":"340a3e8d-4961-454d-98e2-81543dc7b398","added_by":"auto","created_at":"2026-01-06 10:54:55","extension":"xml","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":173910,"visible":true,"origin":"","legend":"","description":"","filename":"3fe0d937088e48ffbf75d25634fc62331structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/fb0304502cc60313786aaa54.xml"},{"id":99602772,"identity":"a613c328-d017-4168-a0fd-4f02c65f60e6","added_by":"auto","created_at":"2026-01-06 10:54:57","extension":"html","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":189642,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/0f72037777c94b3e73aeba35.html"},{"id":99602763,"identity":"54e49f56-4220-4c80-9315-3b30d4b9134b","added_by":"auto","created_at":"2026-01-06 10:54:53","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":328464,"visible":true,"origin":"","legend":"\u003cp\u003eSepsis coding workflow using Sepsis ImmunoScore\u003c/p\u003e\n\u003cp\u003eAssignment of MS-DRGs was based on the presence/absence of mechanical ventilation and the presence/absence of major complication/comorbidity. MS-DRG 870, septicemia or severe sepsis with mechanical ventilation \u0026gt;96 h; MS-DRG 870, septicemia or severe sepsis without mechanical ventilation \u0026gt;96 h with major complication/comorbidity; MS-DRG 872, septicemia or severe sepsis without mechanical ventilation \u0026gt;96 h without major complication/comorbidity.\u003c/p\u003e\n\u003cp\u003eCM, Clinical Modification; CRP, C-reactive protein; MS-DRG, Medicare SeverityDiagnosis Related Group; EMR, electronic medical record; ICD-10, International Classification of Diseases; PCS, procedure coding system; PCT, procalcitonin\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/3747da9727f6b2a19461b35c.png"},{"id":100356381,"identity":"24da295f-fe90-44ec-a205-2b849d6e4f7b","added_by":"auto","created_at":"2026-01-16 07:06:24","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1805260,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/d738ba3d-b626-482e-bc61-0426f1cb8ca3.pdf"},{"id":99602827,"identity":"7615dcb0-5ec9-4059-b8ed-0e12429bb8a1","added_by":"auto","created_at":"2026-01-06 10:55:02","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":332463,"visible":true,"origin":"","legend":"","description":"","filename":"CodingmanuscriptThirdDraftSupplement18Dec2025clean.docx","url":"https://assets-eu.researchsquare.com/files/rs-8483930/v1/3ebb648922dcb0b9b1c38481.docx"}],"financialInterests":"Competing interest reported. RB is a consultant for Prenosis, Inc. AB, LAS, CL-E, GLW, LU, DU, SK, and BR are employees of Prenosis, Inc.","formattedTitle":"The clinician-artificial intelligence partnership in early sepsis identification: Leveraging predictive intelligence for enhanced financial outcomes","fulltext":[{"header":"Background","content":"\u003cp\u003eAnnually, over 1.7\u0026nbsp;million people are diagnosed with sepsis in the U.S. and approximately 350 000 people die [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Sepsis continues to be one of the most challenging syndromes for healthcare professionals to diagnose and document, and is consequently one of the most frequently denied Medicare claims [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Considering the annual healthcare burden of sepsis in the U.S. is estimated at \u003cspan\u003e$\u003c/span\u003e62\u0026nbsp;billion annually [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e], accurate sepsis identification, documentation, and coding are critical to ensuring adequate payer reimbursement.\u003c/p\u003e \u003cp\u003eSepsis diagnoses are regularly denied by payers, often because of inadequate documentation or a lack of clear clinical indicators [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Non-specific symptoms and changing clinical definitions make it difficult to establish a clear sepsis diagnosis, underscoring the need for improved diagnostic metrics [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. For example, the sepsis diagnostic criteria were updated in 2016. The newer Sepsis-3 definition results in fewer patients meeting the sepsis criteria; however, it is better capable of predicting mortality than Sepsis-2. Recent sepsis indication studies, including those reviewed by the U.S. Food \u0026amp; Drug Administration (FDA), have adopted Sepsis-3 as the primary endpoint, reflecting a broader shift from Sepsis-2 [\u003cspan additionalcitationids=\"CR8 CR9 CR10\" citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. Nevertheless, this update has caused considerable confusion for both sepsis diagnosis and reimbursement and may contribute, in part, to inaccurate coding of sepsis. A systematic review and meta-analysis highlighting the issue of sepsis under coding reported a low sensitivity for sepsis International Classification of Diseases (ICD)-codes [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e], which suggests that many patients who clinically meet the criteria for sepsis are miscoded. Studies have reported that only 17% of clinically evident sepsis cases and 55.4% of patients with clinically evident severe sepsis had sepsis ICD coding at discharge [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eAs one of the most expensive medical conditions to treat [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e], sepsis presents significant reimbursement challenges for hospitals. Insufficient documentation to support a sepsis diagnosis can lead to under-coding, resulting in Medicare Severity Diagnosis Related Group (MS-DRG) assignments with reduced reimbursement, as well as claims denials [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Hospital costs for sepsis patients soared from \u003cspan\u003e$\u003c/span\u003e31.2\u0026nbsp;billion in 2016 to \u003cspan\u003e$\u003c/span\u003e52.1\u0026nbsp;billion in 2021, accounting for over 14% of all hospital costs. Almost three-quarters of these hospital costs\u0026mdash;over \u003cspan\u003e$\u003c/span\u003e37.9 billion\u0026mdash;were billed to Medicare and Medicaid for sepsis stays [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Overall claim denial rates reached 15% in 2024, with a higher prevalence of denied claims for higher-cost treatments, such as sepsis [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. Although around half of denied claims are eventually overturned, the appeals process is lengthy, costly, and often requires several rounds to resolve the coverage denial [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWhile hospitals are concerned with potential denial of sepsis claims by payers due to lack of documentation or failure to identify septic patients, payers are concerned about the potential for hospitals to over code sepsis by using sepsis coding for non-septic patients. To address potential sepsis over coding, the 2024 Health and Human Services, Office of Inspector General Work Plan includes the targeting of sepsis billing as an audit priority [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. At the same time, the Severe Sepsis and Septic Shock Management Bundle (SEP-1) has been transitioned from a pay-for-reporting measure to a pay-for-performance measure with penalties realized in fiscal year 2026 [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. The combination of these two changes increases the financial risks for hospitals by tying reimbursement not only to accurate billing and coding practices but also on documented adherence to SEP-1 bundle criteria. With the mean SEP-1 compliance currently at 48.9% [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e], hospitals face heightened risk of both claim denials and reduced performance-based payments. Tools that enhance sepsis identification and documentation may therefore help mitigate revenue losses related to both audits and performance shortfalls.\u003c/p\u003e \u003cp\u003eSepsis ImmunoScore, which is based upon a comprehensive assessment of patient biology, is the first FDA-authorized artificial intelligence (AI) / machine learning (ML) sepsis diagnostic tool (De Novo DEN230036, April 2024) [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. It is software as a medical device that integrates with a patient\u0026rsquo;s electronic medical record to collect measurement metadata for 22 input parameters, providing a comprehensive assessment of a patient\u0026rsquo;s risk for progression to sepsis within 24 hours when ordered as a diagnostic test. Patients are categorized as Low, Medium, High, or Very High risk. The validation study demonstrated robust performance of Sepsis ImmunoScore across three institutions [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. This tool provides objective support for both clinical decision-making and sepsis documentation. Sepsis ImmunoScore risk score can be documented in the patient\u0026rsquo;s electronic medical record, potentially prompting the assessment of sepsis-related ICD code assignments in the coding process. These codes are then used to determine the most appropriate MS-DRG for the patient encounter, which ultimately yields the reimbursement amount for the visit.\u003c/p\u003e \u003cp\u003eThis analysis was conducted to address a critical gap in health economics literature by quantifying the administrative value of AI diagnostic tools beyond clinical outcomes, using real-world data across multiple hospital systems. Specifically, we evaluated the potential economic impact of sepsis coding accuracy using Sepsis ImmunoScore.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eStudy objective\u003c/h2\u003e \u003cp\u003eThis retrospective, multisite, observational study evaluated whether retrospectively calculated Sepsis ImmunoScore results could improve documentation gaps for patients with a suspected serious infection, thereby supporting revenue recovery for the treatment of patients meeting Sepsis-3 criteria.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eStudy population\u003c/h3\u003e\n\u003cp\u003eThe study included patients with a suspected serious infection treated at four hospitals in the U.S. between 2020 and 2023. Hospital A is a comprehensive teaching hospital and level one trauma center that is part of a large non-profit healthcare system; hospitals B and C are large, major non-profit academic medical centers; and hospital D is a large, affiliated community teaching hospital.\u003c/p\u003e \u003cp\u003eAdult patients (\u0026ge;\u0026thinsp;18 years) presenting to the Emergency Department or hospital with a suspected infection, defined by a blood culture order, and who had an available lithium-heparin plasma sample drawn within 6 h of the first blood culture order, were included in the study. There were no exclusion criteria. The study population aligns with the intended use population for Sepsis ImmunoScore. The study was approved by the Institutional Review Board of each participating institution under a waiver of informed consent.\u003c/p\u003e\n\u003ch3\u003eStudy design\u003c/h3\u003e\n\u003cp\u003eThis study was conducted in three major phases, MS-DRG assignment and Sepsis ImmunoScore risk generation, sepsis documentation simulation, and a gap analysis to identify revenue recovery opportunities (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e\n\u003ch3\u003eMS-DRG assignment\u003c/h3\u003e\n\u003cp\u003eData collection\u003c/p\u003e \u003cp\u003eClinical and administrative data, including ICD-10-clinical modification (CM) diagnosis codes and ICD-10-procedure coding system (PCS) codes, along with patient demographic variables (age, sex, and discharge status), were extracted from electronic medical records for all study-eligible hospitalized patients.\u003c/p\u003e \u003cp\u003eMS-DRG assignment process\u003c/p\u003e \u003cp\u003eMS-DRG assignments were determined for each patient following Centers for Medicare \u0026amp; Medicaid Services (CMS) Medicare v39 definitions [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e] using patients\u0026rsquo; ICD-10-CM codes, ICD-10-PCS codes, age, sex, and discharge status.\u003c/p\u003e \u003cp\u003eDetermination of Medicare reimbursement values\u003c/p\u003e \u003cp\u003eMedicare reimbursement values (USD) were calculated using the publicly accessible CMS database which provides the average Medicare payment for each MS-DRG by hospital and year [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. MS-DRG reimbursement data by site from 2021, the most recent data available at the time of the analysis, were used. To project 2024 values, an annual inflation rate of 3.03% (9.4% cumulative) was applied, derived from historical MS-DRG reimbursement trends in the CMS database (2016\u0026ndash;2021). The inflation-adjusted sepsis MS-DRG reimbursement USD values for each of the included hospitals are presented in \u003cb\u003eTable \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e\u003c/b\u003e.\u003c/p\u003e\n\u003ch3\u003eSepsis ImmunoScore risk generation\u003c/h3\u003e\n\u003cp\u003eSepsis ImmunoScore was retrospectively calculated for patients with available lithium heparin blood samples using data for the 22 input parameters, and providers were blinded to the results [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Remnant lithium heparin blood samples were used to assess levels of C-reactive protein and procalcitonin for Sepsis ImmunoScore input. Sepsis ImmunoScore risk stratification used FDA-authorized thresholds (Low, Medium, High, Very High), with High and Very High risk categories indicating sufficient evidence for sepsis documentation based on previously reported likelihood ratios for Sepsis-3 (High, 2.1; Very High, 8.3) [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e].\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eSepsis documentation simulation\u003c/h2\u003e \u003cp\u003eTo simulate documentation enhancement for patients with a High/Very High Sepsis ImmunoScore results, we added a sepsis ICD-10-CM code to identify their resulting sepsis MS-DRG. Following the CMS Medicare v39 definitions, the simulated sepsis ICD-10-CM code and the remaining clinical criteria determined the appropriate sepsis MS-DRG: septicemia or severe sepsis with mechanical ventilation (MV)\u0026thinsp;\u0026gt;\u0026thinsp;96 h (870), septicemia or severe sepsis without MV\u0026thinsp;\u0026gt;\u0026thinsp;96 h with major complication / comorbidity (MCC) (871), or septicemia or severe sepsis without MV\u0026thinsp;\u0026gt;\u0026thinsp;96 h without MCC (872) (\u003cb\u003eFig. \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e\u003c/b\u003e). Overall, there were two MS-DRG calculations per patient: the current MS-DRG based on existing documentation and the potential MS-DRG assigned during the sepsis documentation simulation.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eIdentification of revenue recovery opportunities\u003c/h3\u003e\n\u003cp\u003ePotential revenue recovery opportunities were defined as cases where patients classified as High/Very High risk lacked sepsis documentation, yet their potential sepsis-associated MS-DRG reimbursement exceeded their current MS-DRG reimbursement.\u003c/p\u003e\n\u003ch3\u003eEndpoints\u003c/h3\u003e\n\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003eRevenue recovery\u003c/h2\u003e \u003cp\u003eThe study endpoints were Total Revenue Recovery and potential revenue recovery per patient, calculated for two analysis populations: the total study cohort (Total recovery analysis) and cases meeting Sepsis-3 criteria (Sepsis-3 recovery analysis). Revenue Recovery was defined as the dollar amount potentially recoverable if Sepsis ImmunoScore was adopted to support sepsis ICD-10 coding. The Total recovery analysis represents the full potential recovery for all High/Very High risk patients. The Sepsis-3 recovery analysis is limited to cases where both the Sepsis ImmunoScore result and retrospective clinical criteria align, representing the highest-confidence documentation opportunities and a more conservative estimate.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003eSepsis-3\u003c/h2\u003e \u003cp\u003eTo identify patients meeting Sepsis-3 criteria, automated retrospective sepsis labels were derived using patients\u0026rsquo; electronic medical records [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. The label was assigned based on the presence of clinical, laboratory, and treatment information documented over the entire hospital stay, rather than being restricted to data available at the time of initial assessment. This approach ensured that the classification reflected whether the patient developed sepsis during the admission, providing a reliable reference standard for retrospective analyses. Of note, this label is different from what Sepsis ImmunoScore does. Sepsis ImmunoScore is a diagnostic tool, only privy to information up to the time of diagnosis. The Sepsis-3 medical record derived label is a retrospective label used only for analysis purposes.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eContinuous and categorical variables were summarized using descriptive statistics. Summary demographics and clinical outcomes were calculated for the total population, and by the presence of sepsis according to the Sepsis-3 criteria (non-septic/septic), current MS-DRGs (MS-DRG 870/MS-DRG 871/MS-DRG 872/Other MS-DRG), and Sepsis ImmunoScore risk category result (Low/Medium/High/Very High). Revenue recovery cases were stratified by hospital and sepsis MS-DRG recovery components (i.e., MV\u0026thinsp;\u0026gt;\u0026thinsp;96 h, MCC). 95% confidence intervals (CIs) were estimated using Bootstrapping (2000 iterations).\u003c/p\u003e \u003cp\u003eAll analyses were performed using R version 4.3.2 with specialized packages for sepsis analysis (The R Foundation for Statistical Computing, Vienna, Austria). Potential MS-DRG assignment was conducted using the drgpy Python package (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/yubin-park/drgpy\u003c/span\u003e\u003cspan address=\"https://github.com/yubin-park/drgpy\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e), which processed ICD-10-CM and ICD-10-PCS codes, age, sex, and hospital mortality data according to CMS regulations (CMS Medicare Severity DRG Definitions v39 [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]).\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003eStudy population\u003c/h2\u003e \u003cp\u003eOf the 4951 enrolled patients for whom a Sepsis ImmunoScore was attempted, 532 patients were excluded because they lacked at least one of the mandatory features required to obtain a Sepsis ImmunoScore; 4419 were included in the final analysis cohort (Hospital A, \u003cem\u003en\u0026thinsp;=\u003c/em\u003e\u0026thinsp;1596; Hospital B, \u003cem\u003en\u0026thinsp;=\u003c/em\u003e\u0026thinsp;1640; Hospital C, \u003cem\u003en\u0026thinsp;=\u003c/em\u003e\u0026thinsp;716; Hospital D, \u003cem\u003en\u0026thinsp;=\u003c/em\u003e\u0026thinsp;467).\u003c/p\u003e \u003cp\u003ePatient demographic, clinical characteristics, and outcome summary for the total population (\u003cem\u003eN\u0026thinsp;=\u003c/em\u003e\u0026thinsp;4419) are shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. The median (interquartile range [IQR]) age was 68 (56, 79) years, 51.5% of patients were male, and the two most common race categories were White (66.6%) and Black or African American (25.3%). Nearly all patients were inpatients (95.4%), 28.2% required ICU transfer, and 45.8% met the Sepsis-3 criteria. The median (IQR) retrospectively calculated Sepsis ImmunoScore was 0.29 (0.10, 0.64), and 47.8% of patients fell into the High (41.4%) or Very High (7.3%) risk categories.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDemographics and outcome summary for the total population\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTotal population\u003c/p\u003e \u003cp\u003e(\u003cem\u003eN\u003c/em\u003e\u0026thinsp;=\u0026thinsp;4419)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStudy data site, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital A\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1596 (36.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital B\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1640 (37.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital C\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e716 (16.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital D\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e467 (10.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge, years, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e68 (56, 79)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSex, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2143 (48.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2275 (51.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRace, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWhite\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2944 (66.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBlack or African American\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1118 (25.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAsian\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e92 (2.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAmerican Indian or Alaska Native\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (0.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNative Hawaiian or other Pacific Islander\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (0.0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnknown / not recorded\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e97 (2.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOther\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e159 (3.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEthnicity, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNot Hispanic or Latino\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4145 (93.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHispanic or Latino\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e116 (2.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnknown / not recorded\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e158 (3.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInpatients, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4216 (95.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMaximum SIRS value, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (2, 3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCOVID-19, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e536 (12.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eComorbidities, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute myocardial infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e227 (5.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAIDS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (0.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCerebrovascular disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e501 (11.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCongestive heart failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1340 (30.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCOPD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1180 (26.7)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDementia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e651 (14.7)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1081 (24.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes with complications\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1019 (23.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHistory of myocardial infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e356 (8.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMild liver disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e476 (10.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModerate or severe liver disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e182 (4.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParalysis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e194 (4.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeptic ulcer disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e94 (2.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeripheral vascular disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e549 (12.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRenal disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1516 (34.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRheumatologic disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e224 (5.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital length of stay, days, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5.54 (3.29, 9.84)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDied in hospital, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e365 (8.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICU transfer, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1248 (28.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMV\u0026thinsp;\u0026gt;\u0026thinsp;96 h, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e251 (5.7)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMV (any amount of time), n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e508 (11.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMet Sepsis-2 criteria, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2634 (59.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMet Sepsis-3 criteria, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2023 (45.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMaximum sepsis ICD level, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2765 (62.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSepsis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e840 (19.0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSeptic shock\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e457 (10.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSevere sepsis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e357 (8.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCurrent MS-DRG category, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e870 (sepsis with MV\u0026thinsp;\u0026gt;\u0026thinsp;96 h)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e89 (2.0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e871 (sepsis without MV with MCC)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e844 (19.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e872 (sepsis without MV without MCC)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e238 (5.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOther MS-DRGs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3248 (73.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAverage Medicare payment amount received, USD, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e14\u0026thinsp;471.04\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e9456.69, \u003cspan\u003e$\u003c/span\u003e19\u0026thinsp;840.39)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSepsis ImmunoScore, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.29 (0.10, 0.64)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSepsis ImmunoScore risk category, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLow\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1276 (28.9)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMedium\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e989 (22.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHigh\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1831 (41.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVery High\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e323 (7.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSepsis eligible by Sepsis ImmunoScore, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2154 (48.7)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"2\"\u003eAIDS, acquired immunodeficiency syndrome; COPD, Chronic Obstructive Pulmonary Disease; ICD, International Classification of Diseases; ICU, intensive care unit; IQR, interquartile range; MCC, major complication or comorbidity; MS-DRG, Medicare Severity Diagnosis Related Group; MV, mechanical ventilation; SIRS, systemic inflammatory response syndrome; USD, US dollars\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003eSubgroup comparisons of demographic and clinical outcome data\u003c/h2\u003e \u003cp\u003ePatient data were analyzed to determine whether patients met the Sepsis-3 criteria. A summary of patient demographics and clinical outcomes by Sepsis-3 criteria is shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The Sepsis-3 criteria were met by 2023 patients, of whom 770 (38.1%) had an existing sepsis MS-DRG and 899 (44.4%) met the Sepsis-3 criteria but did not have an existing sepsis ICD code. Among the patients who met the Sepsis-3 criteria, 75.1% (1519/2023) had a High or Very High Sepsis ImmunoScore, supporting a sepsis MS-DRG. The median payment difference between patients who did and did not meet the Sepsis-3 criteria was over \u003cspan\u003e$\u003c/span\u003e4000 per patient.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDemographics and outcome summary by Sepsis-3 criteria\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNon-septic\u003c/p\u003e \u003cp\u003e(\u003cem\u003en\u0026thinsp;=\u003c/em\u003e\u0026thinsp;2396)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSeptic\u003c/p\u003e \u003cp\u003e(\u003cem\u003en\u0026thinsp;=\u003c/em\u003e\u0026thinsp;2023)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStudy data site, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital A\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e941 (39.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e655 (32.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital B\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e797 (33.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e843 (41.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital C\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e431 (18.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e285 (14.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital D\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e227 (9.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e240 (11.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge, years, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e66 (52, 77)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e71 (60, 81)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSex, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1232 (51.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e911 (45.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1164 (48.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1111 (54.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnknown / not recorded\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRace, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.216\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWhite\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1581 (66.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1363 (67.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBlack or African American\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e615 (25.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e503 (24.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAsian\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e55 (2.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e37 (1.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAmerican Indian or Alaska Native\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (0.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5 (0.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNative Hawaiian or other Pacific Islander\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnknown / not recorded\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e45 (1.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e52 (2.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOther\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e96 (4.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e63 (3.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEthnicity, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNot Hispanic or Latino\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2250 (93.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1895 (93.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHispanic or Latino\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e76 (3.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e40 (2.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnknown / not recorded\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e70 (2.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e88 (4.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInpatients, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2212 (92.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2004 (99.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMaximum SIRS value, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (1, 3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (2, 3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCOVID-19, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e214 (8.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e322 (15.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eComorbidities, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute myocardial infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e68 (2.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e159 (7.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAIDS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (0.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (0.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.555\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCerebrovascular disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e197 (8.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e304 (15.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCongestive heart failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e574 (24.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e766 (37.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCOPD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e594 (24.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e586 (29.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDementia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e256 (10.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e395 (19.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e558 (23.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e523 (25.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.052\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes with complications\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e513 (21.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e506 (25.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.005\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHistory of myocardial infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e168 (7.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e188 (9.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.007\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMild liver disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e231 (9.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e245 (12.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.01\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModerate or severe liver disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e70 (2.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e112 (5.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParalysis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e82 (3.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e112 (5.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeptic ulcer disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e34 (1.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e60 (3.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeripheral vascular disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e266 (11.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e283 (14.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.004\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRenal disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e677 (28.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e839 (41.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRheumatologic disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e117 (4.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e107 (5.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.586\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital length of stay, days, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3.98\u003c/p\u003e \u003cp\u003e(2.65, 6.59)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8.17\u003c/p\u003e \u003cp\u003e(5.15, 13.91)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDied in hospital, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e35 (1.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e330 (16.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICU transfer, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e324 (13.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e924 (45.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMV\u0026thinsp;\u0026gt;\u0026thinsp;96 h, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e26 (1.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e225 (11.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMV (any amount of time), n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e63 (2.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e445 (22.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMet Sepsis-2 criteria, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e783 (32.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1851 (91.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMaximum sepsis ICD level, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1866 (77.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e899 (44.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSepsis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e399 (16.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e441 (21.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSeptic shock\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e28 (1.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e429 (21.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSevere sepsis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e103 (4.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e254 (12.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCurrent MS-DRG category, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e870 (sepsis with MV\u0026thinsp;\u0026gt;\u0026thinsp;96 h)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (0.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e83 (4.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e871 (sepsis without MV with MCC)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e237 (9.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e607 (30.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e872 (sepsis without MV without MCC)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e158 (6.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e80 (4.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOther MS-DRGs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1995 (83.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1253 (61.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAverage Medicare payment amount received, USD, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e11\u0026thinsp;617.72 (\u003cspan\u003e$\u003c/span\u003e7137.45, \u003cspan\u003e$\u003c/span\u003e16\u0026thinsp;940.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e15\u0026thinsp;898.19 (\u003cspan\u003e$\u003c/span\u003e14\u0026thinsp;471.04, \u003cspan\u003e$\u003c/span\u003e24\u0026thinsp;924.37)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSepsis ImmunoScore, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.14\u003c/p\u003e \u003cp\u003e(0.07, 0.32)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.59\u003c/p\u003e \u003cp\u003e(0.31, 0.80)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSepsis ImmunoScore risk category, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLow\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1108 (46.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e168 (8.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMedium\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e653 (27.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e336 (16.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHigh\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e608 (25.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1223 (60.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVery High\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e27 (1.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e296 (14.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSepsis eligible by Sepsis ImmunoScore, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e635 (26.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1519 (75.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"4\"\u003eAIDS, acquired immunodeficiency syndrome; COPD, Chronic Obstructive Pulmonary Disease; ICD, International Classification of Diseases; ICU, intensive care unit; IQR, interquartile range; MCC, major complication or comorbidity; MS-DRG, Medicare Severity Diagnosis Related Group; MV, mechanical ventilation; SIRS, systemic inflammatory response syndrome; USD, US dollars\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eA summary of patient demographic and clinical outcomes by current MS-DRG is shown in \u003cb\u003eTable S2\u003c/b\u003e. Patients with a current MS-DRG 870 (septicemia or severe sepsis with mechanical ventilation\u0026thinsp;\u0026gt;\u0026thinsp;96 h) were the sickest and had the highest median Medicare payment.\u003c/p\u003e \u003cp\u003eA summary of patient demographic and clinical outcomes by Sepsis ImmunoScore risk category is shown in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. Only 33.2% of High and 55.1% of Very High risk patients had a sepsis-related current MS-DRG. There was a clear monotonic relationship between Sepsis ImmunoScore and all clinical outcomes, including Medicare payment.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDemographics and outcome summary by Sepsis ImmunoScore risk category\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLow\u003c/p\u003e \u003cp\u003e(\u003cem\u003en\u0026thinsp;=\u003c/em\u003e\u0026thinsp;1276)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMedium\u003c/p\u003e \u003cp\u003e(\u003cem\u003en\u0026thinsp;=\u003c/em\u003e\u0026thinsp;989)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eHigh\u003c/p\u003e \u003cp\u003e(\u003cem\u003en\u0026thinsp;=\u003c/em\u003e\u0026thinsp;1831)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eVery High\u003c/p\u003e \u003cp\u003e(\u003cem\u003en\u0026thinsp;=\u003c/em\u003e\u0026thinsp;323)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStudy data site, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital A\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e558 (43.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e338 (34.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e560 (30.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e140 (43.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital B\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e367 (28.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e400 (40.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e769 (42.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e104 (32.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital C\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e217 (17.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e157 (15.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e297 (16.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e45 (13.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital D\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e134 (10.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94 (9.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e205 (11.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e34 (10.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge, years, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e60 (46, 71)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e70 (58, 81)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e71 (60, 82)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e73 (63, 83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSex, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e716 (56.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e494 (49.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e809 (44.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e124 (38.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e560 (43.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e495 (50.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1021 (55.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e199 (61.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnknown / not recorded\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1 (0.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRace, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.351\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWhite\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e834 (65.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e665 (67.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1222 (66.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e223 (69.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBlack or African American\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e340 (26.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e240 (24.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e455 (24.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e83 (25.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAsian\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e26 (2.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e28 (2.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e36 (2.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e2 (0.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAmerican Indian or Alaska Native\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (0.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4 (0.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNative Hawaiian or other Pacific Islander\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (0.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnknown / not recorded\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e26 (2.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e17 (1.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e46 (2.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e8 (2.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOther\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e46 (3.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e38 (3.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e68 (3.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e7 (2.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEthnicity, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.117\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNot Hispanic or Latino\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1202 (94.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e931 (94.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1711 (93.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e301 (93.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHispanic or Latino\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e40 (3.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e26 (2.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e45 (2.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e5 (1.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnknown / not recorded\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e34 (2.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32 (3.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e75 (4.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e17 (5.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInpatients, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1124 (88.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e960 (97.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1811 (98.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e321 (99.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMaximum SIRS value, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (1, 2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (2, 3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3 (2, 3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e3 (3, 4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCOVID-19, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e147 (11.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e127 (12.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e219 (12.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e43 (13.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.708\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eComorbidities, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute myocardial infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e17 (1.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36 (3.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e133 (7.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e41 (12.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAIDS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (0.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (0.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6 (0.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e2 (0.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.29\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCerebrovascular disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e115 (9.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e106 (10.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e221 (12.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e59 (18.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCongestive heart failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200 (15.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e290 (29.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e703 (38.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e147 (45.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCOPD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e308 (24.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e287 (29.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e505 (27.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e80 (24.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0. 04\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDementia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e119 (9.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e144 (14.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e323 (17.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e65 (20.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e291 (22.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e241 (24.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e456 (24.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e93 (28.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.147\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes with complications\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e191 (15.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e245 (24.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e504 (27.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e79 (24.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHistory of myocardial infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e62 (4.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e82 (8.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e173 (9.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e39 (12.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMild liver disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e74 (5.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95 (9.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e258 (14.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e49 (15.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModerate or severe liver disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (0.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e19 (1.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e132 (7.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e23 (7.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParalysis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e51 (4.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e45 (4.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e86 (4.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e12 (3.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.731\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeptic ulcer disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (0.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e15 (1.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e56 (3.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e11 (3.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeripheral vascular disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e100 (7.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e130 (13.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e265 (14.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e54 (16.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRenal disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e195 (15.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e348 (35.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e816 (44.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e157 (48.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRheumatologic disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e67 (5.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e50 (5.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e85 (4.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e22 (6.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.421\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital length of stay, days, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3.87 (2.18, 6.26)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5.26 (3.32, 8.90)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7.09 (4.14, 11.75)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e7.84 (4.45, 14.18)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDied in hospital, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (0.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e40 (4.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e222 (12.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e91 (28.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICU transfer, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e126 (9.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e189 (19.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e715 (39.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e218 (67.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMV\u0026thinsp;\u0026gt;\u0026thinsp;96 h, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e17 (1.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32 (3.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e157 (8.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e45 (13.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMV (any amount of time), n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e37 (2.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e71 (7.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e306 (16.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e94 (29.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMaximum sepsis ICD level, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1039 (81.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e695 (70.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e967 (52.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e64 (19.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSepsis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e176 (13.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e210 (21.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e409 (22.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e45 (13.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSeptic shock\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (0.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e29 (2.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e260 (14.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e158 (48.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSevere sepsis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e51 (4.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e55 (5.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e195 (10.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e56 (17.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCurrent MS-DRG category, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e870 (sepsis with MV\u0026thinsp;\u0026gt;\u0026thinsp;96 h)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (0.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (0.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e53 (2.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e22 (6.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e871 (sepsis without MV with MCC)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e90 (7.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e141 (14.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e462 (25.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e151 (46.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e872 (sepsis without MV without MCC)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e80 (6.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e61 (6.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e92 (5.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e5 (1.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOther MS-DRGs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1099 (86.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e780 (78.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1224 (66.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e145 (44.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAverage Medicare payment amount received, USD, median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e10\u0026thinsp;444.07 (\u003cspan\u003e$\u003c/span\u003e6915.04, \u003cspan\u003e$\u003c/span\u003e16\u0026thinsp;363.99)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e14\u0026thinsp;471.04 (\u003cspan\u003e$\u003c/span\u003e8843.67, \u003cspan\u003e$\u003c/span\u003e17\u0026thinsp;591.38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e15\u0026thinsp;898.19 (\u003cspan\u003e$\u003c/span\u003e11\u0026thinsp;856.51, \u003cspan\u003e$\u003c/span\u003e22\u0026thinsp;431.56)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e15\u0026thinsp;898.19 (\u003cspan\u003e$\u003c/span\u003e14\u0026thinsp;471.04, \u003cspan\u003e$\u003c/span\u003e34\u0026thinsp;935.26)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"6\"\u003eAIDS, acquired immunodeficiency syndrome; COPD, Chronic Obstructive Pulmonary Disease; ICD, International Classification of Diseases; ICU, intensive care unit; IQR, interquartile range; MCC, major complication or comorbidity; MS-DRG, Medicare Severity Diagnosis Related Group; MV, mechanical ventilation; SIRS, systemic inflammatory response syndrome; USD, US dollars\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec17\" class=\"Section2\"\u003e \u003ch2\u003eRevenue recovery analysis\u003c/h2\u003e \u003cp\u003eThe revenue recovery analyses are shown in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. Using the Sepsis ImmunoScore result of High or Very High yielded a potential MS-DRG with a reimbursement value that was higher than the current MS-DRG in 745 out of 4419 cases, suggesting that 16.9% of the study population did not have a sepsis ICD code and had a current MS-DRG with a lower reimbursement value than a sepsis-related MS-DRG. This translates to a potential revenue recovery of around \u003cspan\u003e$\u003c/span\u003e4 684 373 for the 4419 patients, or \u003cspan\u003e$\u003c/span\u003e1060 per patient when using Sepsis ImmunoScore to document sepsis. This value represents the upper bound of potential revenue recovery, since not all identified patients will have sepsis. When the analysis was limited to patients who met the Sepsis-3 criteria, the total potential revenue recovery was \u003cspan\u003e$\u003c/span\u003e3 240 546, or \u003cspan\u003e$\u003c/span\u003e733 per patient.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePotential revenue recovery overall, by institution, and by sepsis MS-DRG recovery components\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"8\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eNo. pts tested\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"3\" nameend=\"c5\" namest=\"c3\"\u003e \u003cp\u003ePotential revenue recovery opportunities\u003c/p\u003e \u003cp\u003eTotal recovery analysis\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"3\" nameend=\"c8\" namest=\"c6\"\u003e \u003cp\u003ePotential revenue recovery opportunities\u003c/p\u003e \u003cp\u003eSepsis-3 recovery analysis\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNo. oppor-tunities\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTotal revenue recovery\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003ePotential revenue recovery per pt\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNo. oppor-tunities\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eTotal revenue recovery\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003ePotential revenue recovery per pt\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOverall potential revenue recovery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4419\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e745\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e4\u0026thinsp;684\u0026thinsp;373\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e4\u0026thinsp;125\u0026thinsp;378\u0026ndash;\u003cspan\u003e$\u003c/span\u003e5\u0026thinsp;248\u0026thinsp;933)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e1060\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e934\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1188)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e408\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e3\u0026thinsp;240\u0026thinsp;546\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e2\u0026thinsp;727\u0026thinsp;080\u0026ndash;\u003cspan\u003e$\u003c/span\u003e3\u0026thinsp;782\u0026thinsp;855)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e733\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e617\u0026ndash;\u003cspan\u003e$\u003c/span\u003e856)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePotential revenue recovery by institution\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital A\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1596\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e178\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e983 294\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e743 573\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;244\u0026thinsp;347)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e616\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e466\u0026ndash;\u003cspan\u003e$\u003c/span\u003e780)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e735 280\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e502\u0026thinsp;044\u0026ndash;\u003cspan\u003e$\u003c/span\u003e998\u0026thinsp;104)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e461\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e315\u0026ndash;\u003cspan\u003e$\u003c/span\u003e625)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital B\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1640\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e344\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;493\u0026thinsp;684\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;257\u0026thinsp;436\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;769\u0026thinsp;265)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e911\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e767\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1079)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e184\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e852\u0026thinsp;582\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e665\u0026thinsp;486\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;078\u0026thinsp;162)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e520\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e406\u0026ndash;\u003cspan\u003e$\u003c/span\u003e657)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital C\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e716\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e138\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;135\u0026thinsp;369\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e794\u0026thinsp;002\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;512\u0026thinsp;447)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e1586\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e1109\u0026ndash;\u003cspan\u003e$\u003c/span\u003e2112)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e868\u0026thinsp;828\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e550\u0026thinsp;899\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;245\u0026thinsp;779)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e1213\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e769\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1740)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospital D\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e467\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;072\u0026thinsp;027\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e898\u0026thinsp;126\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;255\u0026thinsp;593)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e2296\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e1923\u0026ndash;\u003cspan\u003e$\u003c/span\u003e2689)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e783\u0026thinsp;856\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e581\u0026thinsp;392\u0026ndash;\u003cspan\u003e$\u003c/span\u003e988\u0026thinsp;775)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e1678\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e1245\u0026ndash;\u003cspan\u003e$\u003c/span\u003e2117)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePotential revenue recovery by clinical group\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMV\u0026thinsp;\u0026gt;\u0026thinsp;96 h\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e251\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e2\u0026thinsp;002\u0026thinsp;369\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;647\u0026thinsp;712\u0026ndash;\u003cspan\u003e$\u003c/span\u003e2\u0026thinsp;348\u0026thinsp;057)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e7978\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e6565\u0026ndash;\u003cspan\u003e$\u003c/span\u003e9355)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e64\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;716\u0026thinsp;040\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;389\u0026thinsp;919\u0026ndash;\u003cspan\u003e$\u003c/span\u003e2\u0026thinsp;061\u0026thinsp;750)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e6837\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e5538\u0026ndash;\u003cspan\u003e$\u003c/span\u003e8214)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMCC only\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2629\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e521\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e2\u0026thinsp;505\u0026thinsp;057\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e2\u0026thinsp;344\u0026thinsp;743\u0026ndash;\u003cspan\u003e$\u003c/span\u003e2\u0026thinsp;676\u0026thinsp;167)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e953\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e892\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1018)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e304\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;486\u0026thinsp;271\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;316\u0026thinsp;946\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1\u0026thinsp;660\u0026thinsp;746)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e565\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e501\u0026ndash;\u003cspan\u003e$\u003c/span\u003e632)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeither MV\u0026thinsp;\u0026gt;\u0026thinsp;96 h nor MCC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1539\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e154\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e176\u0026thinsp;947\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e158\u0026thinsp;332\u0026ndash;\u003cspan\u003e$\u003c/span\u003e194\u0026thinsp;952)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e115\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e103\u0026ndash;\u003cspan\u003e$\u003c/span\u003e127)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e38\u0026thinsp;234\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e25\u0026thinsp;675\u0026ndash;\u003cspan\u003e$\u003c/span\u003e52\u0026thinsp;615)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u003cspan\u003e$\u003c/span\u003e25\u003c/p\u003e \u003cp\u003e(\u003cspan\u003e$\u003c/span\u003e17\u0026ndash;\u003cspan\u003e$\u003c/span\u003e34)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"8\"\u003eUSD values are shown as mean (95% confidence interval).\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"8\"\u003eMCC, major complication or comorbidity; MS-DRG, Medicare Severity Diagnosis Related Group; MV, mechanical ventilation; pt(s), patient(s)\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eRevenue recovery by hospital showed an approximately 4-fold variation among sites, with Hospital D having the highest per-patient revenue recovery opportunity at \u003cspan\u003e$\u003c/span\u003e2296 and Hospital A having the lowest per-patient revenue recovery opportunity at \u003cspan\u003e$\u003c/span\u003e616. Academic centers (Hospitals C and D) had higher per-patient revenue recovery opportunities while larger community hospitals (Hospitals A and B) had more total opportunities. This is consistent with the literature, which suggests a large variation of coding practices across hospitals [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eConsidering the effects of MV and MCC, MV\u0026thinsp;\u0026gt;\u0026thinsp;96 h (with or without MCC) had the highest per-patient revenue recovery opportunity (\u003cspan\u003e$\u003c/span\u003e7978) followed by MCC only (\u003cspan\u003e$\u003c/span\u003e953), and neither MV\u0026thinsp;\u0026gt;\u0026thinsp;96 h nor MCC (\u003cspan\u003e$\u003c/span\u003e115). 91.4% of identified potential revenue recovery opportunities among patients with MV\u0026thinsp;\u0026gt;\u0026thinsp;96 h (with or without MCC) were patients who meet the Sepsis-3 criteria.\u003c/p\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eThis multisite analysis demonstrates the substantial potential economic impact of AI-enhanced sepsis documentation using the FDA-authorized Sepsis ImmunoScore. The technology supports more accurate diagnosis and documentation, with potential revenue recovery averaging upwards of one thousand dollars per patient tested.\u003c/p\u003e \u003cp\u003eHospitals absorbed \u003cspan\u003e$\u003c/span\u003e130\u0026nbsp;billion in Medicare and Medicaid underpayments in 2023, and these shortfalls are predicted to continue [\u003cspan additionalcitationids=\"CR28\" citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. At the same time, cumulative hospital expense growth is more than twice the cumulative increase in Medicare reimbursement [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]. These data highlight the need for improved documentation to minimize inaccurate coding and claims denials. For patient charts lacking sufficient evidence to confirm a sepsis diagnosis, an objective diagnostic tool can help bridge this gap by providing measurable data to support the diagnosis.\u003c/p\u003e \u003cp\u003eThe study findings demonstrate that integration of Sepsis ImmunoScore has the potential to mitigate potential lost revenue by improving sepsis coding and documentation to support sepsis claims. Indeed, our analysis showed that the use of Sepsis ImmunoScore to support the documentation of sepsis would have resulted in an increase in recovered revenue of approximately \u003cspan\u003e$\u003c/span\u003e4.68M for the hospitals in the dataset, with an average of \u003cspan\u003e$\u003c/span\u003e1060 potential revenue recovery per patient, and an average of \u003cspan\u003e$\u003c/span\u003e733 potential revenue recovery per patient who met the Sepsis-3 criteria.\u003c/p\u003e \u003cp\u003e CMS issued a new ICD-10-PCS code, XXEZXCB: Measurement of Infection, Computer-aided Triage and Notification, New Technology Group 11, that is applicable to Sepsis ImmunoScore and available as of October 1, 2025, providing a pathway for documenting Sepsis ImmunoScore for claims submissions. Successful implementation of Sepsis ImmunoScore has the potential to improve both workflow and documentation and billing accuracy. Providers can integrate Sepsis ImmunoScore when ordering diagnostic testing for patients who are suspected of having sepsis. The full diagnostic results, including Sepsis ImmunoScore, can then inform clinical decisions and be used as documentation to support whether a sepsis ICD-10 code is assigned by coding specialists and whether CMS finds sufficient documentation to support a sepsis MS-DRG. Hospitals can facilitate the incorporation of Sepsis ImmunoScore into their current workflow by developing protocols to integrate Sepsis ImmunoScore into electronic medical records and educating providers on the clinical decision support provided by Sepsis ImmunoScore.\u003c/p\u003e \u003cp\u003eThe availability of Sepsis ImmunoScore coincides well with the increased regulatory focus on SEP-1 Bundle Compliance documentation in fiscal year 2026. With the SEP-1 Bundle Compliance measure transitioning to pay-for-performance in 2026 [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e] and the ongoing Office of the Inspector General scrutiny [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e], the support of diagnostic tools rooted in comprehensive biological assessment becomes increasingly valuable. The objective evidence provided by Sepsis ImmunoScore strengthens documentation, directly supporting more accurate sepsis coding and reducing the risk of audit exposure. Further, Sepsis ImmunoScore aligns with the documentation requirements for reimbursement by CMS and provides support for legitimate sepsis cases.\u003c/p\u003e \u003cp\u003eThis study had a few limitations that should be considered when interpreting the results. First, this was a retrospective data review and as such could not capture real-world workflow integration effects. Second, the data for this study were collected during the COVID-19 pandemic (2020\u0026ndash;2023); therefore, the results may not fully represent conditions outside the pandemic period. Third, the analysis utilized Medicare reimbursement data; impacts from private payers may be different. Additionally, average Medicare reimbursement data were used rather than individual patient payment data. Fourth, coding accuracy varies among institutions [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. While the analysis included data from multiple hospitals, the potential for institution-to-institution variability may affect the generalizability of these findings across hospitals. Fifth, the Sepsis-3 analysis did not utilize adjudicators to confirm whether Sepsis-3 criteria were met. Sixth, the analysis did not consider how a Low or Medium Sepsis ImmunoScore would impact potential revenue recovery. Finally, it is important to highlight the use of the Sepsis-3 criteria in our analysis and to note that the Sepsis ImmunoScore was designed to predict Sepsis-3, not Sepsis-2 [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. The Sepsis-2 criteria define three levels of sepsis based on systemic inflammatory response syndrome (SIRS): sepsis, \u0026ge;\u0026thinsp;2 SIRS criteria (fever/hypothermia, tachycardia, tachypnea, leukocytosis/leukopenia); severe sepsis, sepsis with organ failure, hypotension, or hypoperfusion; and septic shock, refractory hypotension [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. Sepsis-3 criteria define two levels of sepsis based on sequential organ failure assessment: sepsis, defined as infection and organ failure (may include hypotension, hyperlactatemia, or hypotension requiring vasopressors) and septic shock, defined as hypotension, hyperlactatemia, and hypotension requiring vasopressors. Because these are distinct clinical definitions rather than interchangeable labels, patients meeting one set of criteria may not meet the other. In our study, 32% of patients meeting Sepsis-2 criteria did not meet Sepsis-3 criteria, while 91.5% of patients meeting Sepsis-3 criteria also met Sepsis-2 (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eCurrent MS-DRGs are rooted in the Sepsis-2 criteria; however, the clinical and payer landscape is shifting towards Sepsis-3. Sepsis-3 offers a definition correlated with mortality, that aligns with recent FDA preference for medical devices with a sepsis endpoint, and several major private payers\u0026mdash;including United Healthcare (2019) [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e], Cigna (2020) [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e], and Blue Cross Blue Shield (2024) [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]\u0026mdash;have adopted Sepsis-3 criteria for claims validation. The Sepsis ImmunoScore was designed to predict Sepsis-3 [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e], positioning it for this evolving landscape.\u003c/p\u003e \u003cp\u003eFuture studies with prospective implementation of Sepsis ImmunoScore to assess workflow, studies investigating the long-term impact of Sepsis ImmunoScore implementation on denial rates and audit outcomes, and studies investigating the integration of Sepsis ImmunoScore with other quality initiatives (e.g., rapid intervention with integration) are warranted.\u003c/p\u003e"},{"header":"Conclusions","content":"\u003cp\u003eSepsis ImmunoScore represents a significant advancement in addressing the ongoing sepsis documentation crisis. By providing objective, FDA-authorized diagnostic support, it enables more accurate documentation while supporting both clinical care and financial sustainability. The demonstrated revenue recovery potential supports implementation across diverse hospital settings. As healthcare systems face increasing pressure to balance quality care with financial viability, tools that enhance both clinical and administrative accuracy become increasingly valuable. Sepsis ImmunoScore offers a pathway to achieve these dual goals while maintaining the highest standards of documentation integrity.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eAI\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eArtificial intelligence\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eAIDS\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eAcquired immunodeficiency syndrome\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCI\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eConfidence interval\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCM\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eClinical modification\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCMS\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eCenters for Medicare \u0026amp; Medicaid Services\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCOPD\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eChronic obstructive pulmonary disease\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCRP\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eC-reactive protein\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eEMR\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eElectronic medical record\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eFDA\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eU.S. Food \u0026amp; Drug Administration\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eICD\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eInternational Classification of Diseases\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eICU\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eIntensive care unit\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eIQR\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eInterquartile range\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eMCC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eMajor complication / comorbidity\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eML\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eMachine learning\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eMS-DRG\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eMedicare Severity Diagnosis Related Group\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eMV\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eMechanical ventilation\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003ePCS\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eProcedure Coding System\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003ePCT\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eProcalcitonin\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eSEP-1\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eSeptic Shock Management Bundle\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eSIRS\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eSystemic inflammatory response syndrome\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eUSD\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eUS dollars\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003eEthics approval and consent to participate\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was approved by the Institutional Review Boards (IRBs) of all participating institutions, including the Institutional Review Board of Mercy Hospital, St. Louis (Protocol #1597481-1; approved April 28, 2020), the Institutional Review Board of Corewell Health William Beaumont University Hospital, Royal Oak (Protocol #2018-459; approved January 15, 2019), the LifeBridge Health Institutional Review Board, Sinai Hospital of Baltimore (Protocol #2023P005665; approved July 14, 2023), and the Institutional Review Board of Beth Israel Deaconess Medical Center, Boston (Protocol #1858614-1; approved February 8, 2022). All procedures were conducted in accordance with the ethical standards of the respective institutional research committees and with the 1964 Declaration of Helsinki and its later amendments.\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eConsent for publication\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eAvailability of data and materials\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data that support the findings of this study are available from Prenosis, Inc. However, restrictions apply to the availability of these data, which were used under license for the current study, and so are not publicly available. The data are available from the authors upon reasonable request and with the permission of Prenosis, Inc.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eCompeting interests\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eRB is a consultant for Prenosis, Inc. AB, LAS, CL-E, GLW, LU, DU, SK, and BR are employees of Prenosis, Inc.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eFunding\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was funded in part by the Defense Threat Reduction Agency, National Institutes of Health, Centers for Disease Control and Prevention, National Science Foundation, Biomedical Advanced Research and Development Authority, and Prenosis, Inc. Prenosis, Inc. was overall responsible for the design and conduct of the study, collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication. The other funding agencies had no role.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eAuthors\u0026rsquo; contributions\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAB, LAS, and CL-E conceptualized the study. AB, CL-E, LAS, SK, DU, and LU were involved in data curation. AB performed the formal analysis and validation of the findings. LAS was involved in the study investigation. AB and LAS were responsible for the methodology, software used, and supervision of the study. BR, GLW, CL-E, and RB contributed to funding acquisition. BR was responsible for project administration and managing resources. AB, LAS, and CL-E wrote the first draft. All authors reviewed, edited, and approved the final manuscript before submission.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eAcknowledgements\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe are indebted to the study coordinators, research staff, and lab technicians who participated in the study. These contributions were part of these individuals\u0026rsquo; jobs, and they did not receive additional compensation. The authors thank Sarah Bubeck, PhD, for providing medical writing support, which was funded by Prenosis, Inc., in accordance with Good Publication Practice (GPP3) guidelines (http://www.ismpp.org/gpp3).\u0026nbsp;\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eRhee C, Dantes R, Epstein L, Murphy DJ, Seymour CW, Iwashyna TJ, Kadri SS, Angus DC, Danner RL, Fiore AE, Jernigan JA, Martin GS, Septimus E, Warren DK, Karcz A, Chan C, Menchaca JT, Wang R, Gruber S, Klompas M, Program CDCPE. Incidence and trends of sepsis in US hospitals using clinical vs claims data, 2009\u0026ndash;2014. JAMA. 2017;318(13):1241\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePayer denial hit. sepsis amid conflicting clinical protocols; diagnosis is doubted. Report on Medicare Compliance. Volume 26. Health Care Compliance Association; 2017.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBuchman TG, Simpson SQ, Sciarretta KL, Finne KP, Sowers N, Collier M, Chavan S, Oke I, Pennini ME, Santhosh A, Wax M, Woodbury R, Chu S, Merkeley TG, Disbrow GL, Bright RA, MaCurdy TE, Kelman JA. Sepsis among Medicare beneficiaries: 3. The methods, models, and forecasts of sepsis, 2012\u0026ndash;2018. Crit Care Med. 2020;48(3):302\u0026ndash;18.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSand J, Kuqi A. Current challenges in sepsis documentation and coding: A review of the literature. Perspect Health Inf Manag. 2023;20(3):1g.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRhee C, Gohil S, Klompas M. Regulatory mandates for sepsis care\u0026ndash;reasons for caution. N Engl J Med. 2014;370(18):1673\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRhee C, Dantes RB, Epstein L, Klompas M. Using objective clinical data to track progress on preventing and treating sepsis: CDC's new 'Adult Sepsis Event' surveillance strategy. BMJ Qual Saf. 2019;28(4):305\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLevy MM, Fink MP, Marshall JC, Abraham E, Angus D, Cook D, Cohen J, Opal SM, Vincent JL, Ramsay G, International Sepsis Definitions C. 2001 SCCM/ESICM/ACCP/ATS/SIS International Sepsis Definitions Conference. Intensive Care Med. 2003;29(4):530\u0026ndash;538.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSinger M, Deutschman CS, Seymour CW, Shankar-Hari M, Annane D, Bauer M, Bellomo R, Bernard GR, Chiche JD, Coopersmith CM, Hotchkiss RS, Levy MM, Marshall JC, Martin GS, Opal SM, Rubenfeld GD, van der Poll T, Vincent JL, Angus DC. The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). JAMA. 2016;315(8):801\u0026ndash;10.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePoutsiaka DD, Porto MC, Perry WA, Hudcova J, Tybor DJ, Hadley S, Doron S, Reich JA, Snydman DR, Nasraway SA. Prospective observational study comparing Sepsis-2 and Sepsis-3 definitions in predicting mortality in critically ill patients. Open Forum Infect Dis. 2019;6(7):ofz271.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDe novo classification request for Sepsis ImmunoScore. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.accessdata.fda.gov/cdrh_docs/reviews/DEN230036.pdf\u003c/span\u003e\u003cspan address=\"https://www.accessdata.fda.gov/cdrh_docs/reviews/DEN230036.pdf\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 17 December 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003e510(k.) Substantial equivalence determination decision summary: Assay and instrument. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.accessdata.fda.gov/cdrh_docs/reviews/K220991.pdf\u003c/span\u003e\u003cspan address=\"https://www.accessdata.fda.gov/cdrh_docs/reviews/K220991.pdf\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 22 December 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu B, Hadzi-Tosev M, Liu Y, Lucier KJ, Garg A, Li S, Heddle NM, Rochwerg B, Ning S. Accuracy of International Classification of Diseases, 10th revision codes for identifying sepsis: A systematic review and meta-analysis. Crit Care Explor. 2022;4(11):e0788.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eArberry J, Henry Z, Corrah T. A simple measure to improve sepsis documentation and coding. Clin Med (Lond). 2021;21(3):222\u0026ndash;5.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWilhelms SB, Walther SM, Huss F, Sjoberg F. Severe sepsis in the ICU is often missing in hospital discharge codes. Acta Anaesthesiol Scand. 2017;61(2):186\u0026ndash;93.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNational inpatient hospital costs: The most expensive conditions by payer. 2011. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://hcup-us.ahrq.gov/reports/statbriefs/sb160.jsp\u003c/span\u003e\u003cspan address=\"https://hcup-us.ahrq.gov/reports/statbriefs/sb160.jsp\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAHRQ's portrait of. sepsis reveals its alarming human toll. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.ahrq.gov/news/blog/ahrqviews/portrait-of-sepsis.html\u003c/span\u003e\u003cspan address=\"https://www.ahrq.gov/news/blog/ahrqviews/portrait-of-sepsis.html\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTrend alert. Private payers retain profits by refusing or delaying legitimate medical claims. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://premierinc.com/newsroom/blog/trend-alert-private-payers-retain-profits-by-refusing-or-delaying-legitimate-medical-claims\u003c/span\u003e\u003cspan address=\"https://premierinc.com/newsroom/blog/trend-alert-private-payers-retain-profits-by-refusing-or-delaying-legitimate-medical-claims\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMedicare inpatient hospital billing for sepsis. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://oig.hhs.gov/reports-and-publications/workplan/summary/wp-summary-0000841.asp#:~:text=Office%20of%20Inspector%20General%20%7C%20U.S.%20Department%20of%20Health%20and%20Human%20Services\u003c/span\u003e\u003cspan address=\"https://oig.hhs.gov/reports-and-publications/workplan/summary/wp-summary-0000841.asp#:~:text=Office%20of%20Inspector%20General%20%7C%20U.S.%20Department%20of%20Health%20and%20Human%20Services\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCenters for Medicare \u0026amp; Medicaid Services. Medicare program: proposed hospital inpatient prospective payment systems for acute care hospitals and the long-term care hospital prospective payment system and policy changes and fiscal year 2024 rates. Fed Regist. 2023;88:27193.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFY 2026 Hospital Inpatient Prospective Payment System (IPPS). and Long-Term Care Hospital Prospective Payment System (LTCH PPS) proposed rule \u0026mdash; CMS-1833-P Fact Sheet. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.cms.gov/newsroom/fact-sheets/fy-2026-hospital-inpatient-prospective-payment-system-ipps-and-long-term-care-hospital-prospective\u003c/span\u003e\u003cspan address=\"https://www.cms.gov/newsroom/fact-sheets/fy-2026-hospital-inpatient-prospective-payment-system-ipps-and-long-term-care-hospital-prospective\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBarbash IJ, Davis B, Kahn JM. National performance on the Medicare SEP-1 sepsis quality measure. Crit Care Med. 2019;47(8):1026\u0026ndash;32.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhargava A, L\u0026oacute;pez-Espina C, Schmalz L, Khan S, Watson GL, Urdiales D, Updike L, Kurtzman N, Dagan A, Doodlesack A, Stenson BA, Sarma D, Reseland E, Lee JH, Kravitz MS, Antkowiak PS, Shvilkina T, Espinosa A, Halalau A, Demarco C, Davila F, Davila H, Sims M, Maddens N, Berghea R, Smith S, Palagiri AV, Ezekiel C, Sadaka F, Iyer K, Crisp M, Azad S, Oke V, Friederich A, Syed A, Gosai F, Chawla L, Evans N, Thomas K, Malkani R, Patel R, Mayer S, Ali F, Raghavakurup L, Tafa M, Singh S, Raouf S, Zhao SD, Zhu R, Bashir R, Reddy B, Shapiro NI. FDA-authorized AI/ML tool for sepsis prediction: Development and validation. NEJM AI. 2024;1(12):AIoa2400867.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCMS Data. https://data.cms.gov. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHospital toolkit for adult sepsis surveillance. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.cdc.gov/sepsis/media/pdfs/sepsis-surveillance-toolkit-aug-2018-508.pdf?CDC_AAref_Val=https://www.cdc.gov/sepsis/pdfs/Sepsis-Surveillance-Toolkit-Aug-2018_508.pdf\u003c/span\u003e\u003cspan address=\"https://www.cdc.gov/sepsis/media/pdfs/sepsis-surveillance-toolkit-aug-2018-508.pdf?CDC_AAref_Val=https://www.cdc.gov/sepsis/pdfs/Sepsis-Surveillance-Toolkit-Aug-2018_508.pdf\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eICD-10-CM/PCS MS-DRG v39.0 Definitions Manual. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.cms.gov/icd10m/version39-fullcode-cms/fullcode_cms/P0001.html\u003c/span\u003e\u003cspan address=\"https://www.cms.gov/icd10m/version39-fullcode-cms/fullcode_cms/P0001.html\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRhee C, Jentzsch MS, Kadri SS, Seymour CW, Angus DC, Murphy DJ, Martin GS, Dantes RB, Epstein L, Fiore AE, Jernigan JA, Danner RL, Warren DK, Septimus EJ, Hickok J, Poland RE, Jin R, Fram D, Schaaf R, Wang R, Klompas M. Centers for Disease C, Prevention Prevention Epicenters P. Variation in identifying sepsis and organ dysfunction using administrative versus electronic clinical data and impact on hospital outcome comparisons. Crit Care Med. 2019;47(4):493\u0026ndash;500.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ereport New AHA. Hospitals and health systems squeezed by persistent economic challenges. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.aha.org/press-releases/2025-04-30-new-aha-report-hospitals-and-health-systems-squeezed-persistent-economic-challenges\u003c/span\u003e\u003cspan address=\"https://www.aha.org/press-releases/2025-04-30-new-aha-report-hospitals-and-health-systems-squeezed-persistent-economic-challenges\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThe financial stability. of America\u0026rsquo;s hospitals and health systems is at risk as the costs of caring continue to rise. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.aha.org/system/files/media/file/2023/04/Cost-of-Caring-2023-The-Financial-Stability-of-Americas-Hospitals-and-Health-Systems-Is-at-Risk.pdf\u003c/span\u003e\u003cspan address=\"https://www.aha.org/system/files/media/file/2023/04/Cost-of-Caring-2023-The-Financial-Stability-of-Americas-Hospitals-and-Health-Systems-Is-at-Risk.pdf\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThe cost of caring. Challenges facing America\u0026rsquo;s hospitals in 2025. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.aha.org/system/files/media/file/2025/04/The-Cost-of-Caring-April-2025.pdf\u003c/span\u003e\u003cspan address=\"https://www.aha.org/system/files/media/file/2025/04/The-Cost-of-Caring-April-2025.pdf\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 27 September 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSchwarzkopf D, Rose N, Fleischmann-Struzek C, Boden B, Dorow H, Edel A, Friedrich M, Gonnert FA, Gotz J, Grundling M, Heim M, Holbeck K, Jaschinski U, Koch C, Kunzer C, Le Ngoc K, Lindau S, Mehlmann NB, Meschede J, Meybohm P, Ouart D, Putensen C, Sander M, Schewe JC, Schlattmann P, Schmidt G, Schneider G, Spies C, Steinsberger F, Zacharowski K, Zinn S, Reinhart K. Understanding the biases to sepsis surveillance and quality assurance caused by inaccurate coding in administrative health data. Infection. 2024;52(2):413\u0026ndash;27.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCarneiro AH, Povoa P, Gomes JA. Dear Sepsis-3, we are sorry to say that we don't like you. Rev Bras Ter Intensiva. 2017;29(1):4\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eClinical guidelines. Sepsis. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.uhcprovider.com/content/dam/provider/docs/public/policies/clinical-guidelines/sepsis.pdf\u003c/span\u003e\u003cspan address=\"https://www.uhcprovider.com/content/dam/provider/docs/public/policies/clinical-guidelines/sepsis.pdf\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 22 December 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHealthcare giant adopts Sepsis-3. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://icd10monitor.medlearn.com/healthcare-giant-adopts-sepsis-3/\u003c/span\u003e\u003cspan address=\"https://icd10monitor.medlearn.com/healthcare-giant-adopts-sepsis-3/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 22 December 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSepsis policy. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.bcbsil.com/docs/provider/il/standards/cpcp/2024/cpcp041-07012024.pdf\u003c/span\u003e\u003cspan address=\"https://www.bcbsil.com/docs/provider/il/standards/cpcp/2024/cpcp041-07012024.pdf\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 22 December 2025.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"artificial intelligence-based software, clinical documentation improvement, revenue recovery, sepsis denials, sepsis documentation, sepsis, Sepsis ImmunoScore, severity of illness","lastPublishedDoi":"10.21203/rs.3.rs-8483930/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8483930/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eDiagnosing sepsis is a critical challenge due to complex clinical and systemic barriers; consequently, delayed and failed diagnoses result in poor patient outcomes, high mortality, and severe financial repercussions for healthcare systems. Inadequate documentation and coding frequently cause sepsis claim denials, leading to reimbursement loss. This analysis evaluates the potential clinical economic impact of using the U.S. Food and Drug Administration-authorized artificial intelligence-based Sepsis ImmunoScore software to achieve accurate severity of illness coding.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThis retrospective, multisite, observational study included patients with suspected serious infection treated at four U.S. hospitals. Medical Severity Diagnosis Related Group (MS-DRG) assignments were determined following CMS Medicare v39 definitions using each patient\u0026rsquo;s ICD-10-CM diagnoses, ICD-10-PCS procedures, age, sex, and discharge status. For patients with High/Very High Sepsis ImmunoScore results lacking sufficient sepsis documentation, we compared reimbursement with and without adding a sepsis ICD-10-CM diagnosis. This resulted in two MS-DRG calculations per patient: the current MS-DRG based on existing documentation and the potential MS-DRG with sepsis diagnosis included. When the potential sepsis MS-DRG yielded higher reimbursement than the current MS-DRG, the case represented a revenue recovery opportunity. A subset analysis restricted to patients meeting Sepsis-3 criteria provided a conservative estimate of potential revenue recovery.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe final analysis cohort included 4419 patients. The Sepsis ImmunoScore identified 745 cases (16.9%) where High/Very High risk results indicated undocumented sepsis with higher reimbursement than current MS-DRG assignments. This represents \u003cspan\u003e$\u003c/span\u003e4 684 373 (95% CI, \u003cspan\u003e$\u003c/span\u003e4 125 378\u0026ndash;\u003cspan\u003e$\u003c/span\u003e5 248 933) in potential revenue recovery across all 4419 patients, or \u003cspan\u003e$\u003c/span\u003e1060 (\u003cspan\u003e$\u003c/span\u003e934\u0026ndash;\u003cspan\u003e$\u003c/span\u003e1188) per patient tested. When restricted to cases meeting Sepsis-3 criteria for clinical validation, 516 cases (11.7%) represented \u003cspan\u003e$\u003c/span\u003e3 240 546 (\u003cspan\u003e$\u003c/span\u003e2 727 080\u0026ndash;\u003cspan\u003e$\u003c/span\u003e3 782 855) in potential revenue recovery, or \u003cspan\u003e$\u003c/span\u003e733 (\u003cspan\u003e$\u003c/span\u003e617\u0026ndash;\u003cspan\u003e$\u003c/span\u003e856) per patient tested.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003e This analysis demonstrates that implementation of an enhanced diagnostic tool can improve documentation accuracy and ensure it reflects the complexity of care provided, supporting full reimbursement for hospital services.\u003c/p\u003e","manuscriptTitle":"The clinician-artificial intelligence partnership in early sepsis identification: Leveraging predictive intelligence for enhanced financial outcomes","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-06 10:54:35","doi":"10.21203/rs.3.rs-8483930/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-02-20T02:43:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"12180275055508170535372382001477838208","date":"2026-02-10T07:10:07+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-30T13:13:37+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-15T01:56:40+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-06T04:37:39+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-05T17:28:26+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2026-01-05T17:21:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d205d2ea-ebcf-4fac-9629-8532b414f839","owner":[],"postedDate":"January 6th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-01-30T13:23:16+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-06 10:54:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8483930","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8483930","identity":"rs-8483930","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}