Establishment of seven lung ultrasound phenotypes: a retrospective observational study

Establishment of seven lung ultrasound phenotypes: a retrospective observational study | 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 Establishment of seven lung ultrasound phenotypes: a retrospective observational study Qian Wang, Tongjuan Zou, Xueying Zeng, Ting Bao, Wanhong Yin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3946340/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background Lung phenotypes have been extensively utilized to assess lung injury and guide precise treatment. However, current phenotypic evaluation methods rely on CT scans and other techniques. Although lung ultrasound (LUS) is widely employed in critically ill patients, there is a lack of comprehensive and systematic identification of LUS phenotypes based on clinical data and assessment of their clinical value. Methods Our study was based on a retrospective database. A total of 821 patients were included from September 2019 to October 2020. 1902 LUS examinations were performed in this period. Using a dataset of 55 LUS examinations focused on lung injuries, a group of experts developed an algorithm for classifying LUS phenotypes based on clinical practice, expert experience, and lecture review. This algorithm was subsequently validated and refined using images from an additional 140 LUS examinations. Finally, machine learning was used to apply the validated algorithm to 1902 LUS phenotypes. After sampling 30% of LUS phenotypes, experts substantiated the efficacy of the machine learning algorithm through meticulous manual verification. By utilizing K-means cluster analysis and expert selection of images from a total of 1902 LUS examinations, we established seven distinct LUS phenotypes. To further explore the diagnostic value of these phenotypes for clinical diagnosis, we investigated their auxiliary diagnostic capabilities. Results A total of 1902 LUS phenotypes were tested by randomly selecting 30% to verify the phenotypic accuracy. With the 1902 LUS phenotypes, seven lung ultrasound phenotypes were established through statistical K-means cluster analysis and expert screening. The acute respiratory distress syndrome (ARDS) exhibited gravity-dependent phenotypes, while the cardiogenic pulmonary edema exhibited nongravity phenotypes. The baseline characteristics of the 821 patients included age (66.14 ± 11.76), sex (560/321), heart rate (96.99 ± 23.75), mean arterial pressure (86.5 ± 13.57), Acute Physiology and Chronic Health Evaluation II( APACHE II )score (20.49 ± 8.60), and duration of ICU stay (24.50 ± 26.22); among the 821 patients, 78.8% were cured. In severe pneumonia patients, the gravity-dependent phenotype accounted for 42% of the cases, whereas the nongravity-dependent phenotype constituted 58%. These findings highlight the value of applying different LUS phenotypes in various diagnoses. Conclusions Seven sets of LUS phenotypes were established through machine learning analysis of retrospective data; these phenotypes could represent the typical characteristics of patients with different types of critical illness. Critical care ultrasound Lung ultrasound Phenotype ICU Diagnosis Figures Figure 1 Figure 2 Figure 3 Introduction Lung phenotypes have been extensively utilized to assess lung injury and guide precise treatment 1–3 . Previous studies have reported that significant lung injury is associated with clinical disorders, physiological data, and radiographic images. Others studies have illustrated biological phenotypes, including plasma protein biomarkers, gene expression, and common causative microbiological pathogens 3–7 . These findings could lead to the identification of pathways for defining phenotypes and testing therapeutics that could lead to a more personalized approach for precise therapies for patients with lung injury 8, 9 . Gattinoni and colleagues demonstrated that COVID-19-related ARDS can be divided into type H (type high) and type L (type low) 5 ARDS according to chest CT images. The patients with these two types exhibited different therapeutic responses. Patients with type H ARDS benefited from low tidal volume and high PEEP, the opposite effect is obtained with the type L, and the classified treatment has great medicinal value. lung ultrasound (LUS), a noninvasive imaging technique, is crucial for assessing various pulmonary conditions 10 . Although LUS is widely employed in critically ill patients 1, 11 , several studies have reported that by monitoring different lung ultrasonographic signs 12–16 , there are diagnostic differences between cardiogenic and noncardiogenic lung edema, particularly regarding subpleural consolidations 17–19 . Some related research has focused on diagnosing the primary disease 20, 21 ; other studies have reported the clinical diagnostic value of lung ultrasonography for pneumonia and solitary obstructive atelectasis when combined with relevant clinical indicators to construct a diagnostic decision tree 22, 23 .There is a lack of comprehensive and systematic studies of LUS phenotypes based on real clinical data and assessments of their clinical value. For these reasons, the objective of our study was to establish additional LUS phenotypes by combining patterns of different LUS presentations in various regions 10 . This goal was achieved through lecture review 1, 11, 24 , expert discussions and experience 25, 26 , and the fundamental principles of LUS 27 . We aimed to devise basic rules and create a foundational database of LUS phenotypes using machine learning 28 . To further explore the diagnostic value of these phenotypes for clinical diagnosis, we investigated their auxiliary diagnostic capabilities. Methods Database extraction and sample establishment A retrospective study of 1902 LUS examinations of 821 patients in the LUS database was conducted from September 2019 to October 2020. Each LUS examination included twelve LUS images. We used a twelve-zone LUS examination protocol according to the technical specifications for the clinical application of critical ultrasonography. Five certified experts with ten years of experience in critical ultrasound and in the CCUSG (Critical Care Ultrasound Study Group) developed an algorithm for classifying LUS phenotypes based on clinical practice, expert knowledge, and lecture review. The major LUS patterns are shown below (Table 1 , Fig. 1 ). This algorithm was subsequently validated and refined using images from more than 140 LUS examinations. Finally, the validated algorithm was applied to analyse 1902 LUS phenotypes. After sampling 30% of the LUS phenotypes, the experts evaluated the accuracy of machine learning in classifying images from 571 LUS examinations. By utilizing K-means cluster analysis and expert selection on images from a total of 1902 LUS examinations, we established seven distinct LUS phenotypes. To further explore the diagnostic value of these phenotypes for clinical diagnosis, we investigated their auxiliary diagnostic capabilities. The underlying principles are shown in Table 2 . Table 1 Lung ultrasound patterns Lung ultrasound pattern Definition Pathophysiological significance A Presence of lung sliding with A-lines or fewer than two isolated B-lines Normal lung A' Presence of lung sliding disappearance with A-lines Pneumothorax and pleural adhesion A'' Lung sliding reduced with line A-lines Local hyperinflation, decreased lung compliance, or airway spasm B1 Moderate loss of lung aeration with multiple, well-defined B-lines Interlobular septal thickening, lung interstitial or alveolar edema B2 Severe loss of lung aeration with multiple coalescent B-lines Interlobular septal thickening, lung interstitial or alveolar edema C1 The presence of a tissue pattern characterized by dynamic air bronchograms, subpleural changes, small fragments, and heterogeneous changes, with lesions ranging from 0.5 cm to 1 cm in diameter Lobular consolidation of the lung C2 Presence of a tissue pattern characterized by a large volume of consolidation, dynamic bronchial meteorology, and less pleural fluid (liquid dark area less than 3 cm) The air in the lung is replaced by fluid, and the injured area reaches the diaphragm or chest wall. The consolidation is larger and is mostly caused by infection or mass inhalation and the deposit C3 A relatively uniform parenchymal echo, significantly reduced lung tissue volume, a large amount of compressed pleural fluid, and smooth outer pleura. Bronchial meteorology is obviously in the early stage, mainly concentrated in the central area, and distributed like branches. The dynamic bronchial meteorology is apparent but not obvious in the later stage. External pressure atelectasis, pleural effusion C4 A uniform parenchymal echo, similar to the liver echo (hepatoid). A significantly reduced lung tissue volume, less chest water volume, a static bronchial gas sign shown in the early stage, and a reduced or no bronchial sign in the later stage. Large lung consolidation with a longer duration. Eventually, severe atelectasis occurs. Table 2 Algorithm rules for determining the composition of the LUS phenotype Composition of lung ultrasound phenotype Algorithm rules Gravity dependence Zone 6 presents the real variation C, the gravity-dependence zone, B2 or higher, which appears in zone 6 on both sides. Diffuse Two or more of the same regions appear symmetric B or C on both sides (the non-gravity dependent region is zone 1/2/3/4) Bilateral/unilateral B/C appears in two or more regions Focal zone 1, 2, 3, 4, 5, 6, any single area Interstitial deaeration patterns with B1, B2 transform Consolidation deaeration patterns with C1, C2, C3 transform Atelectasis deaeration patterns with C4 transform Statistical analysis The data were analyzed using SPSS 25.0 statistical software. The values are expressed as the means ± standard deviations or medians and quartiles (first-third quartile) according to the distribution for continuous variables or as counts and percentages for categorical variables. The Wilson score and confidence interval of the single sample rate determined the accuracy of the LUS phenotypes. Finally, K-means cluster analysis and expert selection were used to establish distinct LUS phenotypes. The diagnostic value of the LUS phenotypes for clinical diagnosis was further explored. Results A total of 1902 LUS phenotypes were generated from the LUS database via machine learning (Fig. 2 ). We sampled and validated the accuracy of machine learning-based LUS phenotypes. A total of 30% of the 1902 LUS phenotypes were randomly selected for 517 LUSs examinations to verify the phenotypic accuracy. Since there were 1902 sets of LUS phenotypes, 7 LUS phenotypes were identified through statistical K-means cluster analysis and expert screening. The accuracy of gravity-dependent interstitial deaeration (G-I) was 100% (95% CI 0.92, 1), that of gravity-dependent consolidation deaeration (G-C) was 95.8% (95% CI 0.88 0.98), and that of gravity-dependent atelectasis deaeration (G-A) was 97% (95% CI 0.94, 0.98). The accuracy of diffuse non-gravity-dependent interstitial deaeration (D-NG-I) was 100% (95% CI 0.93, 1), that of bilateral/unilateral non-gravity-dependent interstitial deaeration (B/U-NG-I) was 93.4% (95% CI 0.84, 0.96), and that of non-gravity-dependent real deaeration (NG-C) was 88% (95% CI 0.76, 0.95). The accuracy of gravity-independent atelectasis deaeration (NG-A) was 96.3% (95% CI 0.94, 0.98) (Table 3 ). Table 3 Validation of the accuracy of lung ultrasound phenotyping lung ultrasound phenotypes enrollment sample correct Correct percentage(%) Confidence interval G-I 170 51 51 100 (0.92,1) G-C 243 73 70 95.8 (0.88,10.98) G-A 786 236 229 97 (0.94,0.98) D-NG-I 183 55 55 100 (0.93,1) B/U-NG-I 257 77 71 93.4 (0.84,0.96) NG-C 116 35 35 100 (0.90,1) NG-A 147 44 39 88 (0.76,0.95) in total 1902 571 550 96.3 (0.94,0.98) G-I: Gravity-dependent interstitial deaeration, G-C: Gravity-dependent consolidation deaeration, G-A: Gravity-dependent atelectasis deaeration, D-NG-I: Nongravity-dependent interstitial deaeration, B/U-NG-I: Bilateral/unilateral nongravity-dependent interstitial deaeration, NG-C: Nongravity-dependent deaeration, NG-A: Nongravity-independent atelectasis deaeration. Moreover, the phenotype and diagnostic correlation of the first lung examination of 821 patients were analyzed for different phenotypes. The baseline characteristics of the 821 patients included age (66.14 ± 11.76), sex (560/321), heart rate (96.99 ± 23.75), mean arterial pressure (86.5 ± 13.57), APACHE II score (20.49 ± 8.60), and duration of ICU stay (24.50 ± 26.22); among the 821 patients, among the 821 patients, 78.8% were cured. The date were shown in Table 4 . As presented in Table 5 , the diagnosis on the admission of the study group is listed. We also analyzed the distribution of lung ultrasound phenotypes involving lung-related diseases in Fig. 3 . The acute respiratory distress syndrome (ARDS) exhibited gravity-dependent phenotypes, while the cardiogenic pulmonary edema exhibited nongravity phenotypes. In severe pneumonia patients, the gravity-dependent phenotype accounted for 42% of the cases, whereas the nongravity-dependent phenotype constituted 58%. Table 4 Demographic and clinical characteristics at admission and outcomes of the studied subjects Measure Range no 821 sex(M/F), 560/321 Not available year 66.14 ± 11.76 44–85 Heart Rate, 96.99 ± 23.75 74–180 MAP, mmHg 86.5 ± 13.57 42–127 APACHE II 20.49 ± 8.60 5–37 Urine output per hour 82.24 ± 73.95 5-600 PaO2/ FiO2 221.7 ± 103.8 28.3-474.25 Lac 1.75(1–15) 1–16 EF 60.28 ± 8.69 20–76 WBC 10.59 ± 5.64 0.42–30.3 IL-6 68.20 (181.53-661.33) 2.77–664.1 PCT 2(6.34–95.83) 0.13–95.96 BNP 1029(1629–15224) 138-15362 endotracheal intubation (Y/N) 760/61 mechanical ventilation(h) 433.53 ± 469.40 10-2832 in hospital day 34.76 ± 35.50 1-381 in ICU day 24.50 ± 26.22 1-377 cured (%) 78.8% not available Death (%) 29.2% not available MAP, mean arterial pressure; APACHE II, Acute Physiology and Chronic Health Evaluation II; ICU, Intensive care units; EF left ventricular systolic function; WBC, white blood cell count; IL-6, Interleukin-6; PCT, procalcitonin; BNP, Brain Natriuretic Peptide; Lac, lactic acid. Normal range of test results: WBC ×10 9 /L (3.5–9.5), IL-6 pg/ml (0.00–7.00); PCT ng/ml (<0.046); Lac mmol/L (0.70–2.10). Table 5 Admission diagnosis and the proportions Diagnosis n = 821 % Respiratory disease severe pneumonia 95 11.5% COPD 5 0.61% thymoma 12 1.46% Pulmonary embolism 1 0.12% Lung cancer 15 1.83% Tracheoesophageal fistula 1 0.12% Heart disease valvular heart disease 2 0.24% cardiac arrest 2 0.24% Abdominal diseases esophagus cancer 26 3.17% other tumors 61 7.43% gastric-intestinal perforation 15 1.83% gastrointestinal hemorrhage 27 3.29% abdominal infection 12 1.46% acute suppurative cholangitis 6 0.73% intestinal necrosis /obstruction 45 5.48% abdominal aortic aneurysm 5 0.61% severe acute pancreatitis 76 9.26% Neurological disease encephalitis 13 1.58% cerebral hemorrhage 28 3.41% arterial aneurysm 20 2.44% cerebral infarction 11 1.34% infection-related skin infection 5 0.61% Hepatic abscess 10 1.22% intracranial infection 4 0.49% infective endocarditis 4 0.49% Abdominal infection 38 4.63% hepatic failure 35 4.26% chronic renal failure 15 1.83% Thrombotic Thrombocytopenic Purpura 2 0.24% trauma 86 10.48% Liver transplantation 12 1.46% Immune-related disease 12 1.46% High paraplegia 10 1.22% others diseases 110 13.3% Discussion We established the underlying rules through clinical practice and lecture learning 1, 10, 11, 17, 29–32 and generated seven valuable LUS phenotypes through statistical cluster analysis and expert screening. The application of LUS phenotypes can aid in progressive stratification of lung pathophysiology diagnosis and the implementation of precise treatment 3, 5, 33 . Through multiple iterations of machine learning 16, 34 , we generated meaningful and valuable typical LUS phenotypes, consisting of three gravitational distribution phenotypes and four nongravitational distribution phenotypes 4 . Different LUS phenotypes can indicate distinct primary aetiologies in lung 31, 35 . Severe pneumonia is more frequently observed in individuals with gravity-dependent deaeration, and the distribution of pneumonia is often one-sided 13, 20, 23, 36–39 ; moreover, ARDS is more commonly associated with gravity-dependent consolidation deaeration 7, 20, 40–42 . The cardiogenic pulmonary edema is primarily observed in patients with non-gravity-dependent interstitial deaeration 14, 43 . Different LUS phenotypes can be used to diagnose and evaluate disease conditions 29, 44, 45 and to guide precise treatment in the future 33 . Lichtenstein promoted LUS in 1995 17, 30, 46–52 . Over the period from 1995 to 2005, Lichtenstein established the theoretical foundation and research significance of ten major LUS signs, proposing a systematic evaluation process for LUS encompassing the BLUE protocol and FALL protocol 17 . In 2012, guidelines for LUS were published 11 , which were followed by the release of the second edition in 2023 1 . The clinical application framework of LUS has been continuously enhanced. The understanding of this technique has increased, leading to its widespread utilization in severe cases due to its remarkable value. Implementing twelve-zone assessment and LUS scores aids clinical diagnosis and facilitates treatment decisions, particularly for patients requiring comprehensive postural and prognostic evaluations 36 . However, an all-encompassing assessment evaluation of overall lung ultrasonography is necessary to accurately determine changes related to air and fluid within the lungs. Several studies have used regional ultrasonic scoring systems to evaluate LUS phenotypes; LUS is a reliable bedside tool able to distinguish focal from nonfocal morphologies, and an LUS score ≥ 3 in the ventral lung regions accurately excludes focal ARDS morphology 3 . Nevertheless, establishing these phenotypes relies on expert experience rather than extensive case data support. Therefore, based on large-scale clinical sample data analysis using objective clustering techniques, LUS phenotypes that possess high scientific validity and practicality when applied to the assessment of lung injury conditions can be generated. Furthermore, it has been confirmed that different phenotypes correspond to distinct diagnoses and various lung injuries, highlighting their crucial value. By association analysis with diagnosis, gravity-dependent classification can reflect the lung’s characteristics and potentially guide the treatment of patients in the prone position 42, 53 . However, our research has certain limitations. Our results are based on data from a single centre, which may have introduced certain biases. Our data came from the largest hospitals in western China that receive critical patients from multiple district and county hospitals. Our samples were diverse and representative with large amounts of valuable phenotypic data. Stratification can help compensate for the limitations of a single center study. Additionally, this retrospective study serves as a foundation for future multicenter studies to verify and optimize our research. The LUS phenotypes we included may not pertain to patients hospitalized during the same period and could represent phenotypes obtained at different stages of the disease; however, these are indeed clinically objective phenotypes. In further studies, we will further investigate how LUS phenotypes evolve across different disease periods. The issue of focusing clinical trials on the stage of lung injury, including prevention, administration of therapy during early acute lung injury, and treatment of established ARDS, should be discussed. Conclusions In conclusion, based on our study, we established seven sets of LUS phenotypes through machine learning analysis of retrospective data; these phenotypes could represent the typical characteristics of patients with different types of critical illness. Abbreviations LUS Lung ultrasound ARDS Acute respiratory distress syndrome CCUSG Critical Care Ultrasound Study Group G-I Gravity-dependent interstitial deaeration G-C Gravity-dependent consolidation deaeration G-A gravity-dependent atelectasis deaeration D-NG-I Nongravity-dependent interstitial deaeration B/U-NG-I Bilateral/unilateral nongravity-dependent interstitial deaeration NG-C Nongravity-dependent deaeration NG-A Nongravity-independent atelectasis deaeration APACHE II Acute Physiology and Chronic Health Evaluation Declarations Ethics approval and consent to participate This study was approved by the medical ethics committee of West China Hospital of Sichuan University (No.2022-990). Written informed consent was obtained from the participant. Consent for publication Written informed consent was obtained from the participant for publication and any accompanying images. A copy of the written consent is available for review by the Editor of this journal. Availability of data and materials Summarized data have been presented in this manuscript. The raw data for this study are located and protected at West China Hospital of Sichuan University. Sharing of the raw data is not suggested, because a secondary analysis is planned. Competing interests The authors declare that they have no competing interests. Funding This study was supported by the National Key Research and Development Program of China (No. 2022YFC2504504). The funder contributed to the study design, study carry out and research expenditure. Authors’ contributions Concept and design: Wanhong Yin. Methodology: Wanhong Yin, Tongjuan Zou and Xueying Zeng. Acquisition, analysis, or interpretation of data: all authors. Drafting of the manuscript: Wanhong Yin and Qian Wang. Statistical analysis: Ting Bao. Supervision: Wanhong Yin. Critical revision of the manuscript for important intellectual content: all authors read and approved the final manuscript. Acknowledgements Not applicable. References Demi L, Wolfram F, Klersy C, et al. New International Guidelines and Consensus on the Use of Lung Ultrasound. J Ultrasound Med. 2023;42(2):309–44. Buda N, Mendrala K, Skoczynski S, et al. Basics of Point-of-Care Lung Ultrasonography. N Engl J Med. 2023;389(21):e44. Zochios V, Yusuff H, Schmidt M, et al. Acute right ventricular injury phenotyping in ARDS. Intensive Care Med. 2023;49(1):99–102. Matthay MA, Arabi YM, Siegel ER, et al. Phenotypes and personalized medicine in the acute respiratory distress syndrome. Intensive Care Med. 2020;46(12):2136–52. Mousavizadeh L, Ghasemi S. Genotype and phenotype of COVID-19: Their roles in pathogenesis. J Microbiol Immunol Infect. 2021;54(2):159–63. Ware LB, Matthay MA, Mebazaa A. Designing an ARDS trial for 2020 and beyond: focus on enrichment strategies. Intensive Care Med. 2020;46(12):2153–6. Chotalia M, Patel J, Bangash M, et al. Cardiovascular Subphenotypes in ARDS: Diagnostic and Therapeutic Implications and Overlap with Other ARDS Subphenotypes. J Clin Med. 2023;12(11):3695. Pelosi P, Ball L, Barbas CSV et al. Personalized mechanical ventilation in acute respiratory distress syndrome. Crit Care 2021; 25 (1). Vignon P, Evrard B, Asfar P, et al. Fluid administration and monitoring in ARDS: which management? Intensive Care Med. 2020;46(12):2252–64. Bouhemad B, Mongodi S, Via G, et al. Ultrasound for lung monitoring of ventilated patients. Anesthesiology. 2015;122(2):437–47. Volpicelli G, Elbarbary M, Blaivas M, et al. International evidence-based recommendations for point-of-care lung ultrasound. Intensive Care Med. 2012;38(4):577–91. Heldeweg MLA, Smit MR, Kramer-Elliott SR, et al. Lung Ultrasound Signs to Diagnose and Discriminate Interstitial Syndromes in ICU Patients: A Diagnostic Accuracy Study in Two Cohorts. Crit Care Med. 2022;50(11):1607–17. Sultan SR. Association Between Lung Ultrasound Patterns and Pneumonia. Ultrasound Q. 2022;38(3):246–9. Heldeweg MLA, Haaksma ME, Smit JM, et al. Lung ultrasound to discriminate non-cardiogenic interstitial syndrome from cardiogenic pulmonary edema: Is gestalt as good as it gets? J Crit Care. 2022;73:154180. Zanforlin A, Smargiassi A, Perrone T, et al. Artifacts and Signs in Lung Ultrasound: The Need for a Revised Classification: Part 1: An Accademia di Ecografia Toracica (AdET) Survey: Part 1: An Accademia di Ecografia Toracica (AdET) Survey. J Ultrasound Med. 2022;41(11):2907–9. Haaksma ME, Smit JM, Heldeweg MLA, et al. Extended Lung Ultrasound to Differentiate Between Pneumonia and Atelectasis in Critically Ill Patients: A Diagnostic Accuracy Study. Crit Care Med. 2022;50(5):750–9. Lichtenstein DA. BLUE-protocol and FALLS-protocol: two applications of lung ultrasound in the critically ill. Chest. 2015;147(6):1659–70. Martindale JL, Wakai A, Collins SP, et al. Diagnosing Acute Heart Failure in the Emergency Department: A Systematic Review and Meta-analysis. Acad Emerg Med. 2016;23(3):223–42. Llamas-Álvarez AM, Tenza-Lozano EM, Latour-Pérez J. Diaphragm and Lung Ultrasound to Predict Weaning Outcome: Systematic Review and Meta-Analysis. Chest. 2017;152(6):1140–50. Dargent A, Chatelain E, Kreitmann L, et al. Lung ultrasound score to monitor COVID-19 pneumonia progression in patients with ARDS. PLoS ONE. 2020;15(7):e0236312. Juárez-Villa JD, Vargas-Rojas JA, Amores-Tamay CA, et al. Lung ultrasound: clinical applications and its teaching in medical education. Rev Med Inst Mex Seguro Soc. 2020;58(6):709–18. Lichtenstein DA. Lung ultrasound for the cardiologist-a basic application: The B-profile of the Bedside Lung Ultrasound in Emergencies protocol for diagnosing haemodynamic pulmonary oedema. Arch Cardiovasc Dis. 2020;113(8–9):489–91. Wang G, Ji X, Xu Y, et al. Lung ultrasound: a promising tool to monitor ventilator-associated pneumonia in critically ill patients. Crit Care. 2016;20(1):320. Frankel HL, Kirkpatrick AW, Elbarbary M, et al. Guidelines for the Appropriate Use of Bedside General and Cardiac Ultrasonography in the Evaluation of Critically Ill Patients-Part I: General Ultrasonography. Crit Care Med. 2015;43(11):2479–502. Zou T, Yin W, Kang Y. Application of Critical Care Ultrasound in Patients With COVID-19: Our Experience and Perspective. IEEE Trans Ultrason Ferroelectr Freq Control. 2020;67(11):2197–206. Yin W, Zou T, Qin Y, et al. Poor lung ultrasound score in shock patients admitted to the ICU is associated with worse outcome. BMC Pulm Med. 2019;19(1):1. Rocca E, Zanza C, Longhitano Y, et al. Lung Ultrasound in Critical Care and Emergency Medicine: Clinical Review. Adv Respir Med. 2023;91(3):203–23. Kim K, Macruz F, Wu D et al. Point-of-care AI-assisted stepwise ultrasound pneumothorax diagnosis. Phys Med Biol 2023; 68 (20). Xirouchaki N, Kondili E, Prinianakis G, et al. Impact of lung ultrasound on clinical decision making in critically ill patients. Intensive Care Med. 2014;40(1):57–65. Lichtenstein D. Lung ultrasound in the critically ill. Curr Opin Crit Care. 2014;20(3):315–22. Zou T, Yin W, Diddams M, et al. The Global and Regional Lung Ultrasound Score Can Accurately Evaluate the Severity of Lung Disease in Critically Ill Patients. J Ultrasound Med. 2020;39(9):1879–80. Shrestha GS, Weeratunga D, Baker K. Point-of-Care Lung Ultrasound in Critically ill Patients. Rev Recent Clin Trials. 2018;13(1):15–26. Smit MR, Hagens LA, Heijnen NFL, et al. Lung Ultrasound Prediction Model for Acute Respiratory Distress Syndrome: A Multicenter Prospective Observational Study. Am J Respir Crit Care Med. 2023;207(12):1591–601. Nhat PTH, Van Hao N, Tho PV, et al. Clinical benefit of AI-assisted lung ultrasound in a resource-limited intensive care unit. Crit Care. 2023;27(1):257. Secco G, Delorenzo M, Salinaro F, et al. Lung ultrasound presentation of COVID-19 patients: phenotypes and correlations. Intern Emerg Med. 2021;16(5):1317–27. Dargent A, Chatelain E, Si-Mohamed S, et al. Lung ultrasound score as a tool to monitor disease progression and detect ventilator-associated pneumonia during COVID-19-associated ARDS. Heart Lung. 2021;50(5):700–5. Reissig A, Copetti R, Mathis G, et al. Lung ultrasound in the diagnosis and follow-up of community-acquired pneumonia: a prospective, multicenter, diagnostic accuracy study. Chest. 2012;142(4):965–72. Chavez MA, Shams N, Ellington LE, et al. Lung ultrasound for the diagnosis of pneumonia in adults: a systematic review and meta-analysis. Respir Res. 2014;15(1):50. Staub LJ, Biscaro RRM, Maurici R. Accuracy and Applications of Lung Ultrasound to Diagnose Ventilator-Associated Pneumonia: A Systematic Review. J Intensive Care Med. 2018;33(8):447–55. Garcia-de-Acilu M, Santafe M, Roca O. Use of thoracic ultrasound in acute respiratory distress syndrome. Ann Transl Med. 2023;11(9):320. Caltabeloti F, Monsel A, Arbelot C, et al. Early fluid loading in acute respiratory distress syndrome with septic shock deteriorates lung aeration without impairing arterial oxygenation: a lung ultrasound observational study. Crit Care. 2014;18(3):R91. Wang XT, Ding X, Zhang HM, et al. Lung ultrasound can be used to predict the potential of prone positioning and assess prognosis in patients with acute respiratory distress syndrome. Crit Care. 2016;20(1):385. Gargani L. Ultrasound of the Lungs: More than a Room with a View. Heart Fail Clin. 2019;15(2):297–303. Gutierrez M, Tardella M, Rodriguez L, et al. Ultrasound as a potential tool for the assessment of interstitial lung disease in rheumatic patients. Where are we now? Radiol Med. 2019;124(10):989–99. Huang Y, Liu T, Huang S, et al. Screening value of lung ultrasound in connective tissue disease related interstitial lung disease. Heart Lung. 2023;57:110–6. Lichtenstein DA, Menu Y. A bedside ultrasound sign ruling out pneumothorax in the critically ill. Lung sliding Chest. 1995;108(5):1345–8. Lichtenstein D, Mézière G, Biderman P, et al. The comet-tail artifact. An ultrasound sign of alveolar-interstitial syndrome. Am J Respir Crit Care Med. 1997;156(5):1640–6. Lichtenstein D, Meziere G, Biderman P, et al. The lung point: an ultrasound sign specific to pneumothorax. Intensive Care Med. 2000;26(10):1434–40. Lichtenstein DA, Lascols N, Prin S, et al. The lung pulse: an early ultrasound sign of complete atelectasis. Intensive Care Med. 2003;29(12):2187–92. Lichtenstein DA, Lascols N, Meziere G, et al. Ultrasound diagnosis of alveolar consolidation in the critically ill. Intensive Care Med. 2004;30(2):276–81. Lichtenstein DA. Ultrasound in the management of thoracic disease. Crit Care Med. 2007;35(5 Suppl):250–61. Lichtenstein DA. Ultrasound examination of the lungs in the intensive care unit. Pediatr Crit Care Med. 2009;10(6):693–8. Rousset D, Sarton B, Riu B, et al. Bedside ultrasound monitoring of prone position induced lung inflation. Intensive Care Med. 2021;47(5):626–8. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-3946340","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":272705514,"identity":"e36f6e34-cdf7-4016-9054-0023f0302b33","order_by":0,"name":"Qian Wang","email":"","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Qian","middleName":"","lastName":"Wang","suffix":""},{"id":272705515,"identity":"60740aca-5c43-4fe0-a954-ce8d8e6f2a0b","order_by":1,"name":"Tongjuan Zou","email":"","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Tongjuan","middleName":"","lastName":"Zou","suffix":""},{"id":272705516,"identity":"510bf263-b255-47fc-ae7d-796bff373c63","order_by":2,"name":"Xueying Zeng","email":"","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Xueying","middleName":"","lastName":"Zeng","suffix":""},{"id":272705517,"identity":"8ebd3886-5a03-4e66-8048-199c67159191","order_by":3,"name":"Ting Bao","email":"","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Ting","middleName":"","lastName":"Bao","suffix":""},{"id":272705518,"identity":"3d7190ba-6558-4e08-b90e-3fbdfeb755c1","order_by":4,"name":"Wanhong Yin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIie3NsQqCQBzHcUW4yXTVoewRTgSP3saWHkOC4Kbc6x0anKTx4A+5GK6GDUHg5hpIBF2SbV22Bd13OH7D/8Mpikz2i2ntyx6LKer8O4KCnkR5ER33Izgd7KxmexwRc3PhI3Qw06qTkIAxs6Os8iarOuED3JghgsVE94sBhWlc7JNSpSzATEfWJ3K4tSSrOAn7kbL9JV8iTrTPxAadXIcUPFwg0kQU3DUgX0iMPPPcmsII53DGDQ0dI11UQjJm3bKC59BE9zxn3i2Tvb+SyWSy/+4OpE5R8IlyC74AAAAASUVORK5CYII=","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":true,"prefix":"","firstName":"Wanhong","middleName":"","lastName":"Yin","suffix":""}],"badges":[],"createdAt":"2024-02-10 16:44:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3946340/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3946340/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":51136892,"identity":"be89f1d6-21b6-4d46-b22e-af2167ff001e","added_by":"auto","created_at":"2024-02-14 18:37:05","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":5023030,"visible":true,"origin":"","legend":"\u003cp\u003eLung ultrasound patterns\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-3946340/v1/56fe32f6afe2f7d3feda91c5.png"},{"id":51136891,"identity":"23e18361-ea92-4a4c-afe2-68e3583003b9","added_by":"auto","created_at":"2024-02-14 18:37:05","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":9243275,"visible":true,"origin":"","legend":"\u003cp\u003eSeven typical lung ultrasound phenotypes\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-3946340/v1/46b7f484a4be575e38961564.png"},{"id":51136890,"identity":"38de3dd8-008e-4705-8b6c-f7c2284b6a77","added_by":"auto","created_at":"2024-02-14 18:37:05","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":75939,"visible":true,"origin":"","legend":"\u003cp\u003eDiagnosis of hospitality-related lung disease and lung ultrasound phenotypes\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-3946340/v1/adb6711088f1902e39a0f08b.png"},{"id":51423045,"identity":"d11cf3e5-dd46-4b81-b58f-f4002547237d","added_by":"auto","created_at":"2024-02-21 10:09:55","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1291508,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3946340/v1/6c91ba94-1ae4-4a8c-a40d-a3d0c2b754b2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Establishment of seven lung ultrasound phenotypes: a retrospective observational study","fulltext":[{"header":"Introduction","content":"\u003cp\u003eLung phenotypes have been extensively utilized to assess lung injury and guide precise treatment \u003csup\u003e1\u0026ndash;3\u003c/sup\u003e. Previous studies have reported that significant lung injury is associated with clinical disorders, physiological data, and radiographic images. Others studies have illustrated biological phenotypes, including plasma protein biomarkers, gene expression, and common causative microbiological pathogens\u003csup\u003e3\u0026ndash;7\u003c/sup\u003e. These findings could lead to the identification of pathways for defining phenotypes and testing therapeutics that could lead to a more personalized approach for precise therapies for patients with lung injury\u003csup\u003e8, 9\u003c/sup\u003e. Gattinoni and colleagues demonstrated that COVID-19-related ARDS can be divided into type H (type high) and type L (type low)\u003csup\u003e5\u003c/sup\u003e ARDS according to chest CT images. The patients with these two types exhibited different therapeutic responses. Patients with type H ARDS benefited from low tidal volume and high PEEP, the opposite effect is obtained with the type L, and the classified treatment has great medicinal value. lung ultrasound (LUS), a noninvasive imaging technique, is crucial for assessing various pulmonary conditions\u003csup\u003e10\u003c/sup\u003e. Although LUS is widely employed in critically ill patients\u003csup\u003e1, 11\u003c/sup\u003e, several studies have reported that by monitoring different lung ultrasonographic signs\u003csup\u003e12\u0026ndash;16\u003c/sup\u003e, there are diagnostic differences between cardiogenic and noncardiogenic lung edema, particularly regarding subpleural consolidations\u003csup\u003e17\u0026ndash;19\u003c/sup\u003e. Some related research has focused on diagnosing the primary disease\u003csup\u003e20, 21\u003c/sup\u003e; other studies have reported the clinical diagnostic value of lung ultrasonography for pneumonia and solitary obstructive atelectasis when combined with relevant clinical indicators to construct a diagnostic decision tree\u003csup\u003e22, 23\u003c/sup\u003e.There is a lack of comprehensive and systematic studies of LUS phenotypes based on real clinical data and assessments of their clinical value. For these reasons, the objective of our study was to establish additional LUS phenotypes by combining patterns of different LUS presentations in various regions\u003csup\u003e10\u003c/sup\u003e. This goal was achieved through lecture review\u003csup\u003e1, 11, 24\u003c/sup\u003e, expert discussions and experience\u003csup\u003e25, 26\u003c/sup\u003e, and the fundamental principles of LUS\u003csup\u003e27\u003c/sup\u003e. We aimed to devise basic rules and create a foundational database of LUS phenotypes using machine learning\u003csup\u003e28\u003c/sup\u003e. To further explore the diagnostic value of these phenotypes for clinical diagnosis, we investigated their auxiliary diagnostic capabilities.\u003c/p\u003e"},{"header":"Methods","content":"\u003cp\u003eDatabase extraction and sample establishment\u003c/p\u003e \u003cp\u003eA retrospective study of 1902 LUS examinations of 821 patients in the LUS database was conducted from September 2019 to October 2020. Each LUS examination included twelve LUS images. We used a twelve-zone LUS examination protocol according to the technical specifications for the clinical application of critical ultrasonography. Five certified experts with ten years of experience in critical ultrasound and in the CCUSG (Critical Care Ultrasound Study Group) developed an algorithm for classifying LUS phenotypes based on clinical practice, expert knowledge, and lecture review. The major LUS patterns are shown below (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). This algorithm was subsequently validated and refined using images from more than 140 LUS examinations. Finally, the validated algorithm was applied to analyse 1902 LUS phenotypes. After sampling 30% of the LUS phenotypes, the experts evaluated the accuracy of machine learning in classifying images from 571 LUS examinations. By utilizing K-means cluster analysis and expert selection on images from a total of 1902 LUS examinations, we established seven distinct LUS phenotypes. To further explore the diagnostic value of these phenotypes for clinical diagnosis, we investigated their auxiliary diagnostic capabilities. The underlying principles are shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\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\u003eLung ultrasound patterns\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLung ultrasound pattern\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDefinition\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePathophysiological significance\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eA\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePresence of lung sliding with A-lines or fewer than two isolated B-lines\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNormal lung\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eA'\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePresence of lung sliding disappearance with A-lines\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePneumothorax and pleural adhesion\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eA''\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLung sliding reduced with line A-lines\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eLocal hyperinflation, decreased lung compliance, or airway spasm\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eB1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eModerate loss of lung aeration with multiple, well-defined B-lines\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eInterlobular septal thickening, lung interstitial or alveolar edema\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eB2\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSevere loss of lung aeration with multiple coalescent B-lines\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eInterlobular septal thickening, lung interstitial or alveolar edema\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eC1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eThe presence of a tissue pattern characterized by dynamic air bronchograms, subpleural changes, small fragments, and heterogeneous changes, with lesions ranging from 0.5 cm to 1 cm in diameter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eLobular consolidation of the lung\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eC2\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePresence of a tissue pattern characterized by a large volume of consolidation, dynamic bronchial meteorology, and less pleural fluid (liquid dark area less than 3 cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eThe air in the lung is replaced by fluid, and the injured area reaches the diaphragm or chest wall. The consolidation is larger and is mostly caused by infection or mass inhalation and the deposit\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eC3\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eA relatively uniform parenchymal echo, significantly reduced lung tissue volume, a large amount of compressed pleural fluid, and smooth outer pleura. Bronchial meteorology is obviously in the early stage, mainly concentrated in the central area, and distributed like branches. The dynamic bronchial meteorology is apparent but not obvious in the later stage.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eExternal pressure atelectasis, pleural effusion\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eC4\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eA uniform parenchymal echo, similar to the liver echo (hepatoid). A significantly reduced lung tissue volume, less chest water volume, a static bronchial gas sign shown in the early stage, and a reduced or no bronchial sign in the later stage.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eLarge lung consolidation with a longer duration. Eventually, severe atelectasis occurs.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \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\u003eAlgorithm rules for determining the composition of the LUS phenotype\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 \u003cp\u003eComposition of lung ultrasound phenotype\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAlgorithm rules\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGravity dependence\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eZone 6 presents the real variation C, the gravity-dependence zone, B2 or higher, which appears in zone 6 on both sides.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiffuse\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTwo or more of the same regions appear symmetric B or C on both sides (the non-gravity dependent region is zone 1/2/3/4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBilateral/unilateral\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eB/C appears in two or more regions\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFocal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ezone 1, 2, 3, 4, 5, 6, any single area\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInterstitial deaeration\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003epatterns with B1, B2 transform\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eConsolidation deaeration\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003epatterns with C1, C2, C3 transform\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAtelectasis deaeration\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003epatterns with C4 transform\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eThe data were analyzed using SPSS 25.0 statistical software. The values are expressed as the means\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviations or medians and quartiles (first-third quartile) according to the distribution for continuous variables or as counts and percentages for categorical variables. The Wilson score and confidence interval of the single sample rate determined the accuracy of the LUS phenotypes. Finally, K-means cluster analysis and expert selection were used to establish distinct LUS phenotypes. The diagnostic value of the LUS phenotypes for clinical diagnosis was further explored.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003eA total of 1902 LUS phenotypes were generated from the LUS database via machine learning (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). We sampled and validated the accuracy of machine learning-based LUS phenotypes. A total of 30% of the 1902 LUS phenotypes were randomly selected for 517 LUSs examinations to verify the phenotypic accuracy. Since there were 1902 sets of LUS phenotypes, 7 LUS phenotypes were identified through statistical K-means cluster analysis and expert screening. The accuracy of gravity-dependent interstitial deaeration (G-I) was 100% (95% CI 0.92, 1), that of gravity-dependent consolidation deaeration (G-C) was 95.8% (95% CI 0.88 0.98), and that of gravity-dependent atelectasis deaeration (G-A) was 97% (95% CI 0.94, 0.98). The accuracy of diffuse non-gravity-dependent interstitial deaeration (D-NG-I) was 100% (95% CI 0.93, 1), that of bilateral/unilateral non-gravity-dependent interstitial deaeration (B/U-NG-I) was 93.4% (95% CI 0.84, 0.96), and that of non-gravity-dependent real deaeration (NG-C) was 88% (95% CI 0.76, 0.95). The accuracy of gravity-independent atelectasis deaeration (NG-A) was 96.3% (95% CI 0.94, 0.98) (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \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\u003eValidation of the accuracy of lung ultrasound phenotyping\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=\"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=\"char\" char=\".\" 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 \u003cp\u003elung ultrasound phenotypes\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eenrollment\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003esample\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003ecorrect\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCorrect percentage(%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eConfidence interval\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eG-I\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e170\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e(0.92,1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eG-C\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e243\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e95.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e(0.88,10.98)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eG-A\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e786\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e236\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e229\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e(0.94,0.98)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eD-NG-I\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e183\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e(0.93,1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eB/U-NG-I\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e257\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e77\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e71\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e93.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e(0.84,0.96)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNG-C\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e116\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e(0.90,1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNG-A\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e147\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e39\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e(0.76,0.95)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ein total\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1902\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e571\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e550\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e96.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e(0.94,0.98)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"6\"\u003eG-I: Gravity-dependent interstitial deaeration, G-C: Gravity-dependent consolidation deaeration, G-A: Gravity-dependent atelectasis deaeration, D-NG-I: Nongravity-dependent interstitial deaeration, B/U-NG-I: Bilateral/unilateral nongravity-dependent interstitial deaeration, NG-C: Nongravity-dependent deaeration, NG-A: Nongravity-independent atelectasis deaeration.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eMoreover, the phenotype and diagnostic correlation of the first lung examination of 821 patients were analyzed for different phenotypes. The baseline characteristics of the 821 patients included age (66.14\u0026thinsp;\u0026plusmn;\u0026thinsp;11.76), sex (560/321), heart rate (96.99\u0026thinsp;\u0026plusmn;\u0026thinsp;23.75), mean arterial pressure (86.5\u0026thinsp;\u0026plusmn;\u0026thinsp;13.57), APACHE II score (20.49\u0026thinsp;\u0026plusmn;\u0026thinsp;8.60), and duration of ICU stay (24.50\u0026thinsp;\u0026plusmn;\u0026thinsp;26.22); among the 821 patients, among the 821 patients, 78.8% were cured. The date were shown in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. As presented in Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e, the diagnosis on the admission of the study group is listed. We also analyzed the distribution of lung ultrasound phenotypes involving lung-related diseases in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. The acute respiratory distress syndrome (ARDS) exhibited gravity-dependent phenotypes, while the cardiogenic pulmonary edema exhibited nongravity phenotypes. In severe pneumonia patients, the gravity-dependent phenotype accounted for 42% of the cases, whereas the nongravity-dependent phenotype constituted 58%.\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\u003eDemographic and clinical characteristics at admission and outcomes of the studied subjects\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMeasure\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRange\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eno\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e821\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003esex(M/F),\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e560/321\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNot available\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eyear\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e66.14\u0026thinsp;\u0026plusmn;\u0026thinsp;11.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e44\u0026ndash;85\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHeart Rate,\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e96.99\u0026thinsp;\u0026plusmn;\u0026thinsp;23.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e74\u0026ndash;180\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMAP, mmHg\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e86.5\u0026thinsp;\u0026plusmn;\u0026thinsp;13.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e42\u0026ndash;127\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAPACHE II\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e20.49\u0026thinsp;\u0026plusmn;\u0026thinsp;8.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5\u0026ndash;37\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUrine output per hour\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e82.24\u0026thinsp;\u0026plusmn;\u0026thinsp;73.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5-600\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePaO2/ FiO2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e221.7\u0026thinsp;\u0026plusmn;\u0026thinsp;103.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e28.3-474.25\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLac\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.75(1\u0026ndash;15)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1\u0026ndash;16\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e60.28\u0026thinsp;\u0026plusmn;\u0026thinsp;8.69\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e20\u0026ndash;76\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWBC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10.59\u0026thinsp;\u0026plusmn;\u0026thinsp;5.64\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.42\u0026ndash;30.3\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIL-6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e68.20 (181.53-661.33)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.77\u0026ndash;664.1\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePCT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2(6.34\u0026ndash;95.83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.13\u0026ndash;95.96\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBNP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1029(1629\u0026ndash;15224)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e138-15362\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eendotracheal intubation (Y/N)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e760/61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003emechanical ventilation(h)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e433.53\u0026thinsp;\u0026plusmn;\u0026thinsp;469.40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10-2832\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ein hospital day\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e34.76\u0026thinsp;\u0026plusmn;\u0026thinsp;35.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1-381\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ein ICU day\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e24.50\u0026thinsp;\u0026plusmn;\u0026thinsp;26.22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1-377\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ecured (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e78.8%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003enot available\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeath (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e29.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003enot available\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"3\"\u003eMAP, mean arterial pressure; APACHE II, Acute Physiology and Chronic Health Evaluation II; ICU, Intensive care units; EF left ventricular systolic function; WBC, white blood cell count; IL-6, Interleukin-6; PCT, procalcitonin; BNP, Brain Natriuretic Peptide; Lac, lactic acid.\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"3\"\u003eNormal range of test results: WBC \u0026times;10\u003csup\u003e9\u003c/sup\u003e/L (3.5\u0026ndash;9.5), IL-6 pg/ml (0.00\u0026ndash;7.00); PCT ng/ml (\u0026lt;0.046); Lac mmol/L (0.70\u0026ndash;2.10).\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eAdmission diagnosis and the proportions\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=\"char\" char=\".\" 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\u003eDiagnosis\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003en\u0026thinsp;=\u0026thinsp;821\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e%\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRespiratory disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003esevere pneumonia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e11.5%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCOPD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.61%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ethymoma\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.46%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePulmonary embolism\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.12%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLung cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.83%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTracheoesophageal fistula\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.12%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHeart disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003evalvular heart disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.24%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ecardiac arrest\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.24%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAbdominal diseases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eesophagus cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3.17%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eother tumors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e7.43%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003egastric-intestinal perforation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.83%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003egastrointestinal hemorrhage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3.29%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eabdominal infection\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.46%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eacute suppurative cholangitis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.73%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eintestinal necrosis /obstruction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5.48%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eabdominal aortic aneurysm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.61%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003esevere acute pancreatitis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e9.26%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeurological disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eencephalitis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.58%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ecerebral hemorrhage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3.41%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003earterial aneurysm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.44%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ecerebral infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.34%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003einfection-related\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eskin infection\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.61%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHepatic abscess\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.22%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eintracranial infection\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.49%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003einfective endocarditis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.49%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAbdominal infection\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e38\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e4.63%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ehepatic failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e4.26%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003echronic renal failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.83%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eThrombotic Thrombocytopenic Purpura\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.24%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003etrauma\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e10.48%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLiver transplantation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.46%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eImmune-related disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.46%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHigh paraplegia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.22%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eothers diseases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e110\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e13.3%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eWe established the underlying rules through clinical practice and lecture learning\u003csup\u003e1, 10, 11, 17, 29\u0026ndash;32\u003c/sup\u003e and generated seven valuable LUS phenotypes through statistical cluster analysis and expert screening. The application of LUS phenotypes can aid in progressive stratification of lung pathophysiology diagnosis and the implementation of precise treatment\u003csup\u003e3, 5, 33\u003c/sup\u003e. Through multiple iterations of machine learning\u003csup\u003e16, 34\u003c/sup\u003e, we generated meaningful and valuable typical LUS phenotypes, consisting of three gravitational distribution phenotypes and four nongravitational distribution phenotypes\u003csup\u003e4\u003c/sup\u003e. Different LUS phenotypes can indicate distinct primary aetiologies in lung\u003csup\u003e31, 35\u003c/sup\u003e. Severe pneumonia is more frequently observed in individuals with gravity-dependent deaeration, and the distribution of pneumonia is often one-sided\u003csup\u003e13, 20, 23, 36\u0026ndash;39\u003c/sup\u003e; moreover, ARDS is more commonly associated with gravity-dependent consolidation deaeration \u003csup\u003e7, 20, 40\u0026ndash;42\u003c/sup\u003e. The cardiogenic pulmonary edema is primarily observed in patients with non-gravity-dependent interstitial deaeration\u003csup\u003e14, 43\u003c/sup\u003e. Different LUS phenotypes can be used to diagnose and evaluate disease conditions\u003csup\u003e29, 44, 45\u003c/sup\u003e and to guide precise treatment in the future\u003csup\u003e33\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eLichtenstein promoted LUS in 1995\u003csup\u003e17, 30, 46\u0026ndash;52\u003c/sup\u003e. Over the period from 1995 to 2005, Lichtenstein established the theoretical foundation and research significance of ten major LUS signs, proposing a systematic evaluation process for LUS encompassing the BLUE protocol and FALL protocol \u003csup\u003e17\u003c/sup\u003e. In 2012, guidelines for LUS were published\u003csup\u003e11\u003c/sup\u003e, which were followed by the release of the second edition in 2023\u003csup\u003e1\u003c/sup\u003e. The clinical application framework of LUS has been continuously enhanced. The understanding of this technique has increased, leading to its widespread utilization in severe cases due to its remarkable value. Implementing twelve-zone assessment and LUS scores aids clinical diagnosis and facilitates treatment decisions, particularly for patients requiring comprehensive postural and prognostic evaluations\u003csup\u003e36\u003c/sup\u003e. However, an all-encompassing assessment evaluation of overall lung ultrasonography is necessary to accurately determine changes related to air and fluid within the lungs. Several studies have used regional ultrasonic scoring systems to evaluate LUS phenotypes; LUS is a reliable bedside tool able to distinguish focal from nonfocal morphologies, and an LUS score\u0026thinsp;\u0026ge;\u0026thinsp;3 in the ventral lung regions accurately excludes focal ARDS morphology\u003csup\u003e3\u003c/sup\u003e. Nevertheless, establishing these phenotypes relies on expert experience rather than extensive case data support. Therefore, based on large-scale clinical sample data analysis using objective clustering techniques, LUS phenotypes that possess high scientific validity and practicality when applied to the assessment of lung injury conditions can be generated. Furthermore, it has been confirmed that different phenotypes correspond to distinct diagnoses and various lung injuries, highlighting their crucial value. By association analysis with diagnosis, gravity-dependent classification can reflect the lung\u0026rsquo;s characteristics and potentially guide the treatment of patients in the prone position \u003csup\u003e42, 53\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eHowever, our research has certain limitations. Our results are based on data from a single centre, which may have introduced certain biases. Our data came from the largest hospitals in western China that receive critical patients from multiple district and county hospitals. Our samples were diverse and representative with large amounts of valuable phenotypic data. Stratification can help compensate for the limitations of a single center study. Additionally, this retrospective study serves as a foundation for future multicenter studies to verify and optimize our research. The LUS phenotypes we included may not pertain to patients hospitalized during the same period and could represent phenotypes obtained at different stages of the disease; however, these are indeed clinically objective phenotypes. In further studies, we will further investigate how LUS phenotypes evolve across different disease periods. The issue of focusing clinical trials on the stage of lung injury, including prevention, administration of therapy during early acute lung injury, and treatment of established ARDS, should be discussed.\u003c/p\u003e"},{"header":"Conclusions","content":"\u003cp\u003eIn conclusion, based on our study, we established seven sets of LUS phenotypes through machine learning analysis of retrospective data; these phenotypes could represent the typical characteristics of patients with different types of critical illness.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eLUS Lung ultrasound\u003c/p\u003e\n\u003cp\u003eARDS Acute respiratory distress syndrome\u003c/p\u003e\n\u003cp\u003eCCUSG Critical Care Ultrasound Study Group\u003c/p\u003e\n\u003cp\u003eG-I Gravity-dependent interstitial deaeration\u003c/p\u003e\n\u003cp\u003eG-C Gravity-dependent consolidation deaeration\u003c/p\u003e\n\u003cp\u003eG-A gravity-dependent atelectasis deaeration\u003c/p\u003e\n\u003cp\u003eD-NG-I Nongravity-dependent interstitial deaeration\u003c/p\u003e\n\u003cp\u003eB/U-NG-I Bilateral/unilateral nongravity-dependent interstitial deaeration\u003c/p\u003e\n\u003cp\u003eNG-C Nongravity-dependent deaeration\u003c/p\u003e\n\u003cp\u003eNG-A Nongravity-independent atelectasis deaeration\u003c/p\u003e\n\u003cp\u003eAPACHE II Acute Physiology and Chronic Health Evaluation\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003eEthics approval and consent to participate\u003c/p\u003e\n\u003cp\u003eThis study was approved by the medical ethics committee of West China Hospital of Sichuan University (No.2022-990). Written informed consent was obtained from the participant.\u003c/p\u003e\n\u003cp\u003eConsent for publication\u003c/p\u003e\n\u003cp\u003eWritten informed consent was obtained from the participant for publication and any accompanying images. A copy of the written consent is available for review by the Editor of this journal.\u003c/p\u003e\n\u003cp\u003eAvailability of data and materials\u003c/p\u003e\n\u003cp\u003eSummarized data have been presented in this manuscript. The raw data for this study are located and protected at West China Hospital of Sichuan University. Sharing of the raw data is not suggested, because a secondary analysis is planned.\u003c/p\u003e\n\u003cp\u003eCompeting interests\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003eFunding\u003c/p\u003e\n\u003cp\u003eThis study was supported by the\u0026nbsp;National Key Research and Development Program of China (No. 2022YFC2504504). The funder contributed to the study design, study carry out and research expenditure.\u003c/p\u003e\n\u003cp\u003eAuthors\u0026rsquo; contributions\u003c/p\u003e\n\u003cp\u003eConcept and design: Wanhong Yin.\u003c/p\u003e\n\u003cp\u003eMethodology: Wanhong Yin, Tongjuan Zou and Xueying Zeng.\u003c/p\u003e\n\u003cp\u003eAcquisition, analysis, or interpretation of data: all authors.\u003c/p\u003e\n\u003cp\u003eDrafting of the manuscript: Wanhong Yin and Qian Wang.\u003c/p\u003e\n\u003cp\u003eStatistical analysis: Ting Bao.\u003c/p\u003e\n\u003cp\u003eSupervision: Wanhong Yin.\u003c/p\u003e\n\u003cp\u003eCritical revision of the manuscript for important intellectual content: all authors read and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003eAcknowledgements\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eDemi L, Wolfram F, Klersy C, et al. New International Guidelines and Consensus on the Use of Lung Ultrasound. J Ultrasound Med. 2023;42(2):309\u0026ndash;44.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBuda N, Mendrala K, Skoczynski S, et al. Basics of Point-of-Care Lung Ultrasonography. N Engl J Med. 2023;389(21):e44.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZochios V, Yusuff H, Schmidt M, et al. Acute right ventricular injury phenotyping in ARDS. Intensive Care Med. 2023;49(1):99\u0026ndash;102.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMatthay MA, Arabi YM, Siegel ER, et al. Phenotypes and personalized medicine in the acute respiratory distress syndrome. Intensive Care Med. 2020;46(12):2136\u0026ndash;52.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMousavizadeh L, Ghasemi S. Genotype and phenotype of COVID-19: Their roles in pathogenesis. J Microbiol Immunol Infect. 2021;54(2):159\u0026ndash;63.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWare LB, Matthay MA, Mebazaa A. Designing an ARDS trial for 2020 and beyond: focus on enrichment strategies. Intensive Care Med. 2020;46(12):2153\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChotalia M, Patel J, Bangash M, et al. Cardiovascular Subphenotypes in ARDS: Diagnostic and Therapeutic Implications and Overlap with Other ARDS Subphenotypes. J Clin Med. 2023;12(11):3695.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePelosi P, Ball L, Barbas CSV et al. Personalized mechanical ventilation in acute respiratory distress syndrome. Crit Care 2021; 25 (1).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVignon P, Evrard B, Asfar P, et al. Fluid administration and monitoring in ARDS: which management? Intensive Care Med. 2020;46(12):2252\u0026ndash;64.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBouhemad B, Mongodi S, Via G, et al. Ultrasound for lung monitoring of ventilated patients. Anesthesiology. 2015;122(2):437\u0026ndash;47.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVolpicelli G, Elbarbary M, Blaivas M, et al. International evidence-based recommendations for point-of-care lung ultrasound. Intensive Care Med. 2012;38(4):577\u0026ndash;91.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHeldeweg MLA, Smit MR, Kramer-Elliott SR, et al. Lung Ultrasound Signs to Diagnose and Discriminate Interstitial Syndromes in ICU Patients: A Diagnostic Accuracy Study in Two Cohorts. Crit Care Med. 2022;50(11):1607\u0026ndash;17.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSultan SR. Association Between Lung Ultrasound Patterns and Pneumonia. Ultrasound Q. 2022;38(3):246\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHeldeweg MLA, Haaksma ME, Smit JM, et al. Lung ultrasound to discriminate non-cardiogenic interstitial syndrome from cardiogenic pulmonary edema: Is gestalt as good as it gets? J Crit Care. 2022;73:154180.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZanforlin A, Smargiassi A, Perrone T, et al. Artifacts and Signs in Lung Ultrasound: The Need for a Revised Classification: Part 1: An Accademia di Ecografia Toracica (AdET) Survey: Part 1: An Accademia di Ecografia Toracica (AdET) Survey. J Ultrasound Med. 2022;41(11):2907\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHaaksma ME, Smit JM, Heldeweg MLA, et al. Extended Lung Ultrasound to Differentiate Between Pneumonia and Atelectasis in Critically Ill Patients: A Diagnostic Accuracy Study. Crit Care Med. 2022;50(5):750\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLichtenstein DA. BLUE-protocol and FALLS-protocol: two applications of lung ultrasound in the critically ill. Chest. 2015;147(6):1659\u0026ndash;70.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMartindale JL, Wakai A, Collins SP, et al. Diagnosing Acute Heart Failure in the Emergency Department: A Systematic Review and Meta-analysis. Acad Emerg Med. 2016;23(3):223\u0026ndash;42.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLlamas-\u0026Aacute;lvarez AM, Tenza-Lozano EM, Latour-P\u0026eacute;rez J. Diaphragm and Lung Ultrasound to Predict Weaning Outcome: Systematic Review and Meta-Analysis. Chest. 2017;152(6):1140\u0026ndash;50.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDargent A, Chatelain E, Kreitmann L, et al. Lung ultrasound score to monitor COVID-19 pneumonia progression in patients with ARDS. PLoS ONE. 2020;15(7):e0236312.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJu\u0026aacute;rez-Villa JD, Vargas-Rojas JA, Amores-Tamay CA, et al. Lung ultrasound: clinical applications and its teaching in medical education. Rev Med Inst Mex Seguro Soc. 2020;58(6):709\u0026ndash;18.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLichtenstein DA. Lung ultrasound for the cardiologist-a basic application: The B-profile of the Bedside Lung Ultrasound in Emergencies protocol for diagnosing haemodynamic pulmonary oedema. Arch Cardiovasc Dis. 2020;113(8\u0026ndash;9):489\u0026ndash;91.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang G, Ji X, Xu Y, et al. Lung ultrasound: a promising tool to monitor ventilator-associated pneumonia in critically ill patients. Crit Care. 2016;20(1):320.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFrankel HL, Kirkpatrick AW, Elbarbary M, et al. Guidelines for the Appropriate Use of Bedside General and Cardiac Ultrasonography in the Evaluation of Critically Ill Patients-Part I: General Ultrasonography. Crit Care Med. 2015;43(11):2479\u0026ndash;502.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZou T, Yin W, Kang Y. Application of Critical Care Ultrasound in Patients With COVID-19: Our Experience and Perspective. IEEE Trans Ultrason Ferroelectr Freq Control. 2020;67(11):2197\u0026ndash;206.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYin W, Zou T, Qin Y, et al. Poor lung ultrasound score in shock patients admitted to the ICU is associated with worse outcome. BMC Pulm Med. 2019;19(1):1.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRocca E, Zanza C, Longhitano Y, et al. Lung Ultrasound in Critical Care and Emergency Medicine: Clinical Review. Adv Respir Med. 2023;91(3):203\u0026ndash;23.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim K, Macruz F, Wu D et al. Point-of-care AI-assisted stepwise ultrasound pneumothorax diagnosis. Phys Med Biol 2023; 68 (20).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXirouchaki N, Kondili E, Prinianakis G, et al. Impact of lung ultrasound on clinical decision making in critically ill patients. Intensive Care Med. 2014;40(1):57\u0026ndash;65.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLichtenstein D. Lung ultrasound in the critically ill. Curr Opin Crit Care. 2014;20(3):315\u0026ndash;22.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZou T, Yin W, Diddams M, et al. The Global and Regional Lung Ultrasound Score Can Accurately Evaluate the Severity of Lung Disease in Critically Ill Patients. J Ultrasound Med. 2020;39(9):1879\u0026ndash;80.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShrestha GS, Weeratunga D, Baker K. Point-of-Care Lung Ultrasound in Critically ill Patients. Rev Recent Clin Trials. 2018;13(1):15\u0026ndash;26.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSmit MR, Hagens LA, Heijnen NFL, et al. Lung Ultrasound Prediction Model for Acute Respiratory Distress Syndrome: A Multicenter Prospective Observational Study. Am J Respir Crit Care Med. 2023;207(12):1591\u0026ndash;601.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNhat PTH, Van Hao N, Tho PV, et al. Clinical benefit of AI-assisted lung ultrasound in a resource-limited intensive care unit. Crit Care. 2023;27(1):257.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSecco G, Delorenzo M, Salinaro F, et al. Lung ultrasound presentation of COVID-19 patients: phenotypes and correlations. Intern Emerg Med. 2021;16(5):1317\u0026ndash;27.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDargent A, Chatelain E, Si-Mohamed S, et al. Lung ultrasound score as a tool to monitor disease progression and detect ventilator-associated pneumonia during COVID-19-associated ARDS. Heart Lung. 2021;50(5):700\u0026ndash;5.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eReissig A, Copetti R, Mathis G, et al. Lung ultrasound in the diagnosis and follow-up of community-acquired pneumonia: a prospective, multicenter, diagnostic accuracy study. Chest. 2012;142(4):965\u0026ndash;72.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChavez MA, Shams N, Ellington LE, et al. Lung ultrasound for the diagnosis of pneumonia in adults: a systematic review and meta-analysis. Respir Res. 2014;15(1):50.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStaub LJ, Biscaro RRM, Maurici R. Accuracy and Applications of Lung Ultrasound to Diagnose Ventilator-Associated Pneumonia: A Systematic Review. J Intensive Care Med. 2018;33(8):447\u0026ndash;55.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGarcia-de-Acilu M, Santafe M, Roca O. Use of thoracic ultrasound in acute respiratory distress syndrome. Ann Transl Med. 2023;11(9):320.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCaltabeloti F, Monsel A, Arbelot C, et al. Early fluid loading in acute respiratory distress syndrome with septic shock deteriorates lung aeration without impairing arterial oxygenation: a lung ultrasound observational study. Crit Care. 2014;18(3):R91.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang XT, Ding X, Zhang HM, et al. Lung ultrasound can be used to predict the potential of prone positioning and assess prognosis in patients with acute respiratory distress syndrome. Crit Care. 2016;20(1):385.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGargani L. Ultrasound of the Lungs: More than a Room with a View. Heart Fail Clin. 2019;15(2):297\u0026ndash;303.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGutierrez M, Tardella M, Rodriguez L, et al. Ultrasound as a potential tool for the assessment of interstitial lung disease in rheumatic patients. Where are we now? Radiol Med. 2019;124(10):989\u0026ndash;99.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang Y, Liu T, Huang S, et al. Screening value of lung ultrasound in connective tissue disease related interstitial lung disease. Heart Lung. 2023;57:110\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLichtenstein DA, Menu Y. A bedside ultrasound sign ruling out pneumothorax in the critically ill. Lung sliding Chest. 1995;108(5):1345\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLichtenstein D, M\u0026eacute;zi\u0026egrave;re G, Biderman P, et al. The comet-tail artifact. An ultrasound sign of alveolar-interstitial syndrome. Am J Respir Crit Care Med. 1997;156(5):1640\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLichtenstein D, Meziere G, Biderman P, et al. The lung point: an ultrasound sign specific to pneumothorax. Intensive Care Med. 2000;26(10):1434\u0026ndash;40.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLichtenstein DA, Lascols N, Prin S, et al. The lung pulse: an early ultrasound sign of complete atelectasis. Intensive Care Med. 2003;29(12):2187\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLichtenstein DA, Lascols N, Meziere G, et al. Ultrasound diagnosis of alveolar consolidation in the critically ill. Intensive Care Med. 2004;30(2):276\u0026ndash;81.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLichtenstein DA. Ultrasound in the management of thoracic disease. Crit Care Med. 2007;35(5 Suppl):250\u0026ndash;61.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLichtenstein DA. Ultrasound examination of the lungs in the intensive care unit. Pediatr Crit Care Med. 2009;10(6):693\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRousset D, Sarton B, Riu B, et al. Bedside ultrasound monitoring of prone position induced lung inflation. Intensive Care Med. 2021;47(5):626\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Critical care ultrasound, Lung ultrasound, Phenotype, ICU, Diagnosis","lastPublishedDoi":"10.21203/rs.3.rs-3946340/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3946340/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eLung phenotypes have been extensively utilized to assess lung injury and guide precise treatment. However, current phenotypic evaluation methods rely on CT scans and other techniques. Although lung ultrasound (LUS) is widely employed in critically ill patients, there is a lack of comprehensive and systematic identification of LUS phenotypes based on clinical data and assessment of their clinical value.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eOur study was based on a retrospective database. A total of 821 patients were included from September 2019 to October 2020. 1902 LUS examinations were performed in this period. Using a dataset of 55 LUS examinations focused on lung injuries, a group of experts developed an algorithm for classifying LUS phenotypes based on clinical practice, expert experience, and lecture review. This algorithm was subsequently validated and refined using images from an additional 140 LUS examinations. Finally, machine learning was used to apply the validated algorithm to 1902 LUS phenotypes. After sampling 30% of LUS phenotypes, experts substantiated the efficacy of the machine learning algorithm through meticulous manual verification. By utilizing K-means cluster analysis and expert selection of images from a total of 1902 LUS examinations, we established seven distinct LUS phenotypes. To further explore the diagnostic value of these phenotypes for clinical diagnosis, we investigated their auxiliary diagnostic capabilities.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eA total of 1902 LUS phenotypes were tested by randomly selecting 30% to verify the phenotypic accuracy. With the 1902 LUS phenotypes, seven lung ultrasound phenotypes were established through statistical K-means cluster analysis and expert screening. The acute respiratory distress syndrome (ARDS) exhibited gravity-dependent phenotypes, while the cardiogenic pulmonary edema exhibited nongravity phenotypes. The baseline characteristics of the 821 patients included age (66.14\u0026thinsp;\u0026plusmn;\u0026thinsp;11.76), sex (560/321), heart rate (96.99\u0026thinsp;\u0026plusmn;\u0026thinsp;23.75), mean arterial pressure (86.5\u0026thinsp;\u0026plusmn;\u0026thinsp;13.57), Acute Physiology and Chronic Health Evaluation II( APACHE II )score (20.49\u0026thinsp;\u0026plusmn;\u0026thinsp;8.60), and duration of ICU stay (24.50\u0026thinsp;\u0026plusmn;\u0026thinsp;26.22); among the 821 patients, 78.8% were cured. In severe pneumonia patients, the gravity-dependent phenotype accounted for 42% of the cases, whereas the nongravity-dependent phenotype constituted 58%. These findings highlight the value of applying different LUS phenotypes in various diagnoses.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eSeven sets of LUS phenotypes were established through machine learning analysis of retrospective data; these phenotypes could represent the typical characteristics of patients with different types of critical illness.\u003c/p\u003e","manuscriptTitle":"Establishment of seven lung ultrasound phenotypes: a retrospective observational study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-14 18:37:00","doi":"10.21203/rs.3.rs-3946340/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c8ff7f96-c9e9-4066-93e2-5d2083542aaf","owner":[],"postedDate":"February 14th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-02-21T10:01:48+00:00","versionOfRecord":[],"versionCreatedAt":"2024-02-14 18:37:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3946340","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3946340","identity":"rs-3946340","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}