A diagnostic model for discrimination between Pneumocystis jirovecii pneumonia and asymptomatic colonization based on multiple parameters

A diagnostic model for discrimination between Pneumocystis jirovecii pneumonia and asymptomatic colonization based on multiple parameters | 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 Article A diagnostic model for discrimination between Pneumocystis jirovecii pneumonia and asymptomatic colonization based on multiple parameters Qianyu Ye, Bo Xiang, Jufeng Pan, Xiaoqi Luo, Gang Huang, Peisong Chen, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8251095/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Apr, 2026 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Distinguishing Pneumocystis jirovecii pneumonia (PJP) from colonization (PJC) is crucial due to overlapping symptoms but different treatments. This study aims to evaluate whether peripheral blood parameters can serve as a non-invasive tool for distinguishing PJP from PJC. We retrospectively enrolled 174 patients with PJP and 61 with PJC from the First Affiliated Hospital of Sun Yat-sen University (April 2022–March 2024). peripheral blood parameters were analyzed and compared between groups. Normally distributed variables were assessed using Student’s t-test, while non-parametric data were analyzed with the Wilcoxon rank-sum test. A diagnostic model was subsequently developed based on significant hematological indicators. Utilizing a significance threshold of p < 0.05, red blood cell (RBC) and lymphocyte count (Lym%), while excluding neutrophil percentage (Neu%), procalcitonin (PCT), and lactic dehydrogenase (LDH) were used to build a random forest diagnostic model. The optimal XGBoost model achieved an AUC of 0.9991 internally and 0.787 in external validation. A web-based tool was developed to assist diagnosis. The findings of this study offer an effective tool for clinical practice, enabling physicians to accurately diagnose and differentiate between PJP and PJC, guiding appropriate treatment for patients. Health sciences/Diseases Health sciences/Medical research Pneumocystis jirovecii pneumonia Colonization Random Forest Diagnosis model Peripheral blood parameters Figures Figure 1 Figure 2 Figure 3 Figure 4 Introduction Pneumocystis jirovecii pneumonia (PJP) is a life-threatening opportunistic infection predominantly observed in immunocompromised individuals, particularly those with HIV infection. Despite advances in antimicrobial prophylaxis and antiretroviral therapy, PJP continues to pose a significant clinical challenge, with mortality rates reaching up to 50% in high-risk populations, emphasizing the critical need for early diagnosis and vigilant monitoring [ 1 , 2 ]. The COVID-19 pandemic complicated PJP presentations, including cases without HIV or immunodeficiency [ 3 ]. Such patients often exhibit atypical symptoms, increasing misdiagnosis risks and rapid clinical deterioration, ultimately worsening outcomes [ 4 ]. Pneumocystis jirovecii colonization (PJC) is increasingly recognized as a distinct clinical entity, particularly in immunocompetent hosts, where it is typically asymptomatic or associated with mild respiratory symptoms [ 5 , 6 ]. Distinguishing between PJC and infection (PJP) directly impacts therapeutic decision-making, prognostic evaluation, and public health strategies. Particularly in the context of a growing immunocompromised population, accurate differentiation is critical for personalized medicine. Current PJP diagnostics, including metagenomic next-generation sequencing (mNGS) and droplet digital quantitative PCR (dd-qPCR), exhibit high sensitivity but limited specificity in distinguishing PJP from colonization. While mNGS demonstrates superior pathogen detection in immunosuppressed non-HIV patients compared to conventional PCR, it remains unable to reliably differentiate infection from colonization [ 7 ]. Similarly, qPCR shows high sensitivity but poor specificity [ 8 ]. Blood tests are more convenient and time-efficient for differential diagnoses of fungal infection. Detecting serum BDG levels is an effective method for distinguishing Pneumocystis jirovecii infection from colonization with BAL or blood [ 9 , 10 ]. Peripheral blood parameters show potential in rapid diagnosing PJP and PJC as an adjuvant diagnostic tool for mNGS. These markers offer a convenient and effective diagnostic option for guiding treatment strategies and preventing antibiotic misuse, especially for mild clinical presentation, but no study has yet shown their effective use for this purpose, indicating a need for further research [ 11 ]. To meet this goal, we conducted a retrospective study at the First Affiliated Hospital of Sun Yat-sen University, to compare clinical symptoms, imaging, and blood markers of PJP and PJC. Our objective is to enhance understanding and improve diagnosis and patient outcomes for these conditions. Methods Data collection Clinical laboratory data were retrospectively obtained from patients who attended the outpatient department of the First Affiliated Hospital of Sun Yat-sen University, between April 18, 2022, and September 19, 2024. The data were extracted from digital medical records and included variables such as age, sex, and blood test results at the onset of illness. Specifically, the blood test parameters collected were white blood cell count (WBC), lymphocyte percentage (Lym%), neutrophil percentage (Neu%), Monocyte percentage (mono%), red blood cell count (RBC), platelet count (PLT), C-reactive protein (CRP), procalcitonin (PCT), lactic dehydrogenase (LDH). A total of 1058 patients with suspected PJP infection were enrolled, and 235 patients were diagnosed with positive for Pneumocystis jirovecii by BALF real-time quantitative polymerase chain reaction (RT-qPCR). We used uniform diagnostic criteria for the differential diagnosis of PJP and PJC based on host fator and clinical characteristics. Diagnostic classification of PJP or PJC was performed through independent evaluation by two unblinded physicians. Any diagnostic discrepancies were resolved through adjudication by a third senior clinician. Patients with positive clinical metagenomic test results for P. jirovecii were systematically included. The clinical diagnosis of PJP was confirmed when a patient satisfied all of the following criteria: (1) Positive microscopic identification of Pneumocystis jirovecii mNGS detection in BAL fluid; (2) Presence of at least two of the PCP manifestations-dyspnea, fever, non-productive cough, hypoxemia (oxygen saturation less than 90% on room air); (3) Characteristic bilateral pulmonary opacities on chest computed tomography (CT), typically manifesting as diffuse ground-glass infiltrates; After applying the inclusion criteria, we implemented the following exclusion criteria: (1) Patients with alternative pulmonary pathologies demonstrating CT findings indistinguishable from PJP, including laboratory-confirmed SARS-CoV-2 infection and microbiologically proven invasive aspergillosis; (2) A negative result of BALF RT-qPCR; (3) Unavailability of BALF mNGS data. Patients not meeting these exclusion criteria were subsequently classified as having Pneumocystis jirovecii colonization [ 12 ]. This non-interventional study was approved by the ethics committee of the First Affiliated Hospital, Sun Yet-sen University ([2023]459). All PJP and PJC patients agreed to participate in this study and signed the informed consent form by themselves or their legal guardians based on the Helsinki Declaration. Data preprocessing In this study, a total of 1058 cases were initially collected. To precisely elucidate the critical role of various blood test indicators in diagnosing PJP and PJC among pediatric patients, the study rigorously excluded cases with incomplete test data, subjects with co-infections from other respiratory pathogens. Following data preprocessing, 235 cases were retained for analysis, comprising 174 cases of PJP and 61 cases of PJC (Chart1). We utilized the Deepwise & Beckman Coulter DxAI platform, an online statistical tool available at http://dxonline.deepwise.com/ , to develop a machine learning-based algorithm. This platform is specifically designed to autonomously select suitable machine learning models, present analytical data, and facilitate online analysis. We implemented a series of increasingly sophisticated models, including Random Forest (RF), Multilayer Perceptron (MP), Gradient Boosting (GB), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA) [ 13 , 14 ]. The dataset was partitioned into training and validation sets in a 7:3 ratio through random allocation, and this process was repeated across 100 iterations to ensure robustness. To further validate the reliability and reproducibility of the algorithm, we conducted an additional round of validation using a cross-sectional study. This study was conducted at the same hospital, covering the period from January 16th to January 27th, 2024, and adhered to the same diagnostic protocols. Laboratory test results from this period were processed using the algorithm. The dataset was partitioned into training and validation subsets in a 7:3 ratio through random allocation. This partitioning process was iteratively performed 100 times to enhance robustness. To further ensure the reliability and reproducibility of the algorithm, an additional validation round was conducted using a cross-sectional study. This study was derived from The First Affiliated Hospital of Guangzhou Medical University, encompassing the period from January 16th to January 27th, 2024, and adhered to consistent diagnostic protocols. Laboratory test results from this timeframe were processed using the algorithm. The efficacy of algorithm was evaluated using several key metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, recall rate, F1 score, sensitivity, specificity, and both positive and negative predictive values. Chart1 Patient enrolment and flow through the study Statistical analysis Data analysis was conducted utilizing SPSS version 26.0. The normality of the data distribution was examined via the Kolmogorov-Smirnov test. For blood test indicators that adhered to a normal distribution, between-group differences were assessed using the T-test, whereas the Wilcoxon test was applied to indicators that deviated from a normal distribution. Differences in sex among groups were evaluated using the Chi-square test. Continuous variables were reported as medians with interquartile ranges (P25, P75), while categorical variables were presented as means ± standard deviation. The diagnostic efficacy of the models was assessed through Receiver Operating Characteristic (ROC) analysis. The performance of each model was detailed and compared using metrics such as the area under the curve (AUC), accuracy, F1 score, sensitivity, specificity, positive predictive value, and negative predictive value. The Delong test was used to compare the AUC values of different models, with statistical significance set at a p-value of less than 0.05. Results Comparative analysis of the clinical characteristics in the cross-sectional study The study cohort comprised 235 hospitalized patients, including 174 Pneumocystis jirovecii pneumonia cases and 61 Pneumocystis jirovecii colonization cases. The median age of the patients was 61 years, with 160 (68.1%) males and 75 (31.9%) females. Demographic analysis revealed comparable sex distribution between groups ( p > 0.05). While clinical manifestations including Shortness of breath and Chest tightness showed intergroup differences ( p < 0.05), significant variations emerged in a state of immune insufficiency: PJ infection patients demonstrated higher solid organ transplant rate and Malignant hematologic diseases rate ( p < 0.01) compared to PJ colonization counterparts. Complete demographic and clinical profiles are detailed in Table 1 . Table 1 Demographic and Clinical Characteristics of Study Cohort Characteristics PJ infection (n = 174) PJ colonization (n = 61) All patients (n = 235) P- value Demographics Age 60 (47.25-70) 65 (50–71) 61 (48–70) 0.136 Sex 0.865 Femal 55 (31.6%) 20 (32.8%) 75 (31.9%) Male 119 (68.4%) 41 (67.2%) 160 (68.1%) Clinical symptoms (n [%]) Fever 89 (51.1%) 32 (52.5%) 121 (51.5%) 0.86 Cough 99 (56.9%) 30 (49.2%) 129 (54.9%) 0.297 Shortness of breath 82 (47.1%) 19 (31.1%) 101 (43.0%) 0.030 * Productive cough 72 (41.4%) 25 (41.0%) 97 (41.3%) 0.957 Chest tightness 35 (20.1%) 4 (6.6%) 39 (16.6%) 0.014 * Dyspnea 19 (10.9%) 3 (4.9%) 22 (9.4%) 0.166 Immunocompromised (n [%]) Autoimmune diseases 12 (6.9%) 1 (1.6%) 13 (5.5%) 0.222 Solid organ transplant 24 (13.8%) 1 (1.6%) 25 (10.6%) 0.008 * Solid tumors 43 (24.7%) 10 (16.4%) 53 (22.6%) 0.181 Chronic kidney disease 15 (8.6%) 3 (4.9%) 18 (7.7%) 0.512 Malignant hematologic diseases 22 (12.6%) 2 (3.3%) 24 (10.2%) 0.038 * * p < 0.05, ** p < 0.01 Laboratory Parameter Comparisons As presented in Table 2 , the majority of test results demonstrated significant differences between the two groups ( p < 0.05). Individuals with Pneumocystis jirovecii infection exhibited RBC and Lym% but higher Neu%, PCT and LDH compared to those Pneumocystis jirovecii colonization patients ( p 0.05). Table 2 Hematological Profile Comparisons Characteristics PJ infection (n = 174) PJ colonization (n = 61) All patients (n = 235) P- value WBC 7.21 (5.188–10.957) 7.445 (5.713–9.503) 7.325 (5.328–10.61) 0.759 Neu% 0.832 (0.712–0.913) 0.734 (0.67–0.875) 0.812 (0.702–0.897) 0.015 * Lym% 0.098 (0.048–0.172) 0.161 (0.067–0.24) 0.104 (0.055–0.192) 0.010 ** Mono% 0.052 (0.03–0.084) 0.062 (0.051–0.082) 0.058 (0.032–0.084) 0.09 RBC 3.3 (2.8–3.95) 4.065 (3.33–4.48) 3.455 (2.842–4.158) 0.000 ** PLT 184.5 (115-280.25) 227 (150.5–306) 191 (127–285) 0.107 CRP 45.35 (14.62–98.9) 42.38 (7.27–75.46) 43.39 (11.33–87.11) 0.255 PCT 0.23 (0.11–1.107) 0.1 (0.05–0.467) 0.205 (0.08–0.898) 0.003 ** LDH 345.5 (263.75–577) 251 (197–406) 335 (233-525.5) 0.000 ** BDG 65.01(37.5-241.12) 37.5(37.5-43.18) 46.42(37.5-177.15) 0.000 ** * p < 0.05, ** p < 0.01 WBC: White Blood Cell; Lym%: Lymphocyte percentage; Neu%: Neutrophil percentage; Mono#: Monocyte percentage; RBC: Red Blood Cell; PLT: Platelet count; CRP: C-reactive protein; PCT: procalcitonin; LDH: lactic dehydrogenase Development of the PJ infeciton vs colonization model Predictors for machine learning models were selected by the least absolute shrinkage and selection operator (LASSO) algorithm and clinical experience. By LASSO algorithm, six predictors including RBC, Lym%, PCT, LDH, Shortness of breath and Chest tightness were were selected (shown in Supplementary Figure S1 ). Since previous studies have demonstrated the significance of neutrophils in the diagnosis and prognosis of PJP [ 15 – 18 ], we included Neu% as a predictive factor in the model in this study. Seven candidate predictors (RBC, Lym%, Neu%, PCT, LDH, Shortness of breath and Chest tightness) were initially selected for model construction based on Table 1 and Table 2 findings. Five machine learning algorithms were evaluated: Random Forest (RF), Support Vector Machine (SVM), XGBoost (XGB), Linear Discriminant Analysis (LDA), and Multilayer Perceptron (MP). The performance of these models was evaluated using the DeLong test, and their predictive capabilities are presented in Table 3 and Fig. 1 . As shown in Fig. 1 , all five models demonstrated effective predictive performance in distinguishing patients with Pneumocystis jirovecii pneumonia from those Pneumocystis jirovecii colonization. The results of the DeLong tests for both the training and validation sets of the five models are specifically presented in Table 3 . Based on the highest AUC of the XGB model in the training set and its positive difference compared to the other four models (p < 0.01) in Table 4 , we ultimately selected the XGB model, termed PJ infection vs colonization model, as our predictive algorithm. Table 3 PJ infection and colonization Model Performance Metrics Model AUC ACC F1 score Recall NPV PPV SE SP XGB Training 0.9991 0.9408 0.9617 1 1 0.9262 1 0.7692 Validation 0.7228 0.7711 0.8571 0.9344 0.6364 0.7917 0.9344 0.3182 RF Training 0.9145 0.8289 0.8943 0.9735 0.8421 0.8271 0.9735 0.4103 Validation 0.7095 0.7447 0.8454 0.9425 0.5238 0.7664 0.9425 0.1803 SVM Training 0.7667 0.6579 0.7263 0.6106 0.4133 0.8961 0.6106 0.7949 Validation 0.7064 0.7108 0.7895 0.7377 0.4667 0.8491 0.7377 0.6364 MP Training 0.7468 0.7763 0.8682 0.9912 0.8571 0.7724 0.9912 0.1538 Validation 0.6431 0.7108 0.831 0.9672 0 0.7284 0.9672 0 LDA Training 0.7347 0.7697 0.8617 0.9646 0.6667 0.7786 0.9646 0.2051 Validation 0.6833 0.7108 0.8235 0.918 0.375 0.7467 0.918 0.1364 *In the training data set, the DeLong test showed that the XGB model had a larger AUC than the LDA, SVM, MP, and RF models (p 0.05) AUC: area under the curve; ACC: accuracy; SE: sensitivity; SP: specificity; NPV: negative predictive value; PPV: positive predictive value. Table 4 Delong test between the five models Training Delong z p Validation Delong z p XGB-RF 3.851 0.000 ** XGB-RF 1.605 0.108 XGB-SVM 5.566 0.000 ** XGB-SVM 0.243 0.808 XGB-MP -5.519 0.000 ** XGB-MP -1.141 0.254 XGB-LDA 5.693 0.000 ** XGB-LDA 0.565 0.572 RF-SVM 4.514 0.000 ** RF-SVM -0.708 0.479 RF-MP -4.619 0.000 ** RF-MP -0.281 0.778 RF-LDA 4.8 0.000 ** RF-LDA -0.366 0.714 SVM-MP -0.674 0.5 SVM-MP -1.083 0.279 SVM-LDA -1.752 0.08 SVM-LDA -0.763 0.445 MP-LDA 0.523 0.601 MP-LDA -0.782 0.434 * p < 0.05, ** p < 0.01 XGB-RF: Delong test between XGBoost and Random Forest; XGB-SVM: Delong test between XGBoost and Support Vector Machine; XGB-MP: Delong test between XGBoost and Multilayer Perceptron; XGB-LDA: Delong test between XGBoost and Linear Discriminant Analysis; RF-SVM: Delong test between Random Forest Analysis and Support Vector Machine; RF-MP: Delong test between Random Forest Analysis and Multilayer Perceptron; RF-LDA: Delong test between Random Forest and Linear Discriminant Analysis; SVM-MP: Delong test between Support Vector Machine and Multilayer Perceptron, SVM-LDA: Delong test between Support Vector Machine and Linear Discriminant Analysis, MP-LDA: Delong test between Multilayer Perceptron and Linear Discriminant Analysis Feature Importance of the Model Figure 2 showed the significance values of the selected factors in the PJ infection vs colonization model algorithm. Within this algorithm, seven factors were retained, with LDH having the utmost weight. External validation We selected 66 cases from The First Affiliated Hospital of Guangzhou Medical University diagnosed with Pneumocystis jirovecii pneumonia or Pneumocystis jirovecii colonization cases for PJ infection vs colonization model validation. The diagnostic efficacy of PJ infection vs colonization model in this validation group was summarized in Table 5 , with an AUC of 0.787, as displayed in Fig. 3 . Table 5 Interlaboratory validation of the model AUC ACC F1 score Recall NPV PPV SE SP Interlaboratory validation 0.787 0.79 0.800 0.818 0.600 0.783 0.818 0.545 Webpage tool of PJ infection model For clinical translation, we developed a web-based decision tool ( https://dxonline.deepwise.com/prediction/index.html?baseUrl=%2Fapi%2F&id=50566&topicName=undefined&from=share&platformType=wisdom ) enabling real-time risk stratification through parameter input (Fig. 4 ). In addition, we have also provided the QR code link of the model for easy access to it. This is to facilitate the usage of the model (shown in Supplementary Figure S2). This digital implementation preserves model accuracy while enhancing bedside accessibility. Discussion Accurate and timely diagnosis is critical for reducing mortality from PJP, particularly in immunocompromised populations. Conventional diagnostic approaches, which depend on microscopic examination of BAL fluid, are limited by suboptimal sensitivity and often necessitate invasive procedures [ 19 ]. Emerging molecular techniques, including PCR and CRISPR/Cas13-based assays, permit highly sensitive detection of P. jirovecii from non-invasive specimens such as sputum and serum [ 20 ]. These advancements offer valuable diagnostic alternatives for patients who are unsuitable candidates for bronchoscopy [ 21 ]. The COVID-19 pandemic has further complicated PJP management, with increased incidence and diagnostic challenges arising from clinical and radiological similarities between PJP and SARS-CoV-2 infection [ 22 , 23 ]. Immunosuppression secondary to COVID-19 or its therapeutic regimens has been shown to significantly elevate PJP risk, particularly among solid organ transplant recipients [ 22 , 24 ]. These developments highlight the urgent need for reliable diagnostic algorithms and optimized treatment protocols to enhance clinical outcomes in this vulnerable patient population. In this retrospective medical record review, we investigated patients with PJP arising from colonization. Through comprehensive clinical evaluation and mNGS analysis, we identified 235 individuals with P. jirovecii infection. These cases were subsequently stratified into two distinct cohorts: 174 patients with confirmed PJP and 61 cases demonstrating PJC. Our comparative analysis of clinical characteristics between patients with PJP and those with PJC revealed distinct symptomatic profiles. The most prevalent clinical manifestations among infected individuals included fever, cough (both productive and non-productive), dyspnea, chest tightness, and shortness of breath. Notably, PJP patients demonstrated significantly more severe respiratory symptoms, particularly dyspnea and chest tightness, compared to their PJC counterparts, a finding consistent with previous reports by Xing et al [ 25 ]. Demographic analysis showed no statistically significant differences in age or sex distribution between the study groups ( p > 0.05). This pattern remained consistent regardless of concurrent infections with influenza virus or Mycoplasma pneumoniae, supporting the observations made by Liu et al [ 26 ]. These findings suggest that while demographic factors may not serve as discriminative markers, clinical symptom severity appears to be a reliable indicator for differentiating PJP from PJC. Our comprehensive analysis of peripheral blood parameters in patients with PJP and PJC revealed several statistically significant differential markers, including RBC, Lym%, Neu%, PCT and LDH levels. While these parameters demonstrated relative discriminative value, none exhibited sufficient diagnostic accuracy when used individually. To enhance diagnostic precision, we explored the potential of artificial intelligence-based multiparametric analysis. Five key hematological parameters were incorporated into various machine learning models. This approach significantly improved diagnostic performance, as evidenced by increased AUC values. Among the evaluated algorithms - including XGB, RF, SVM, MP, and LDA-all demonstrated clinically meaningful predictive capability (AUC > 0.68) in distinguishing PJP from PJC across both training and validation datasets. Notably, the XGB model achieved superior performance (AUC > 0.99, p < 0.01 versus comparator models) and was therefore selected as our final predictive algorithm. Furthermore, refinement of the Random Forest model - a well-established machine learning approach in biomedical research [ 27 , 28 ] - identified a core panel of five discriminative parameters (RBC, Lym#, Neu%, PCT, and LDH) that collectively optimize diagnostic differentiation between these clinical entities. RBC are widely considered to be an important indicator of fungus infection, particularly noting that patients with weakened immune systems often experience higher rates of fungal infections and altered blood parameters [ 29 ]. Compared with PJC patients, PJP usually have a decrease in RBC[4.065 (3.33–4.48) vs. 3.3 (2.8–3.95), p < 0.0001]. Lymphocyte(Lym) significantly changes after fungal infections, particularly in immunosuppressed patients. For instance, those with invasive fungal infections and sepsis exhibit notably reduced lymphocyte counts, highlighting an immunosuppressive condition [ 30 ]. Compared with PJC patients, PJP had a higher lymphocyte percentage[0.098 (0.048–0.172) vs. 0.161 (0.067–0.24), p = 0.01]. Neutrophils(Neu) are vital in defending against fungal infections through mechanisms like phagocytosis, oxidative burst, and the release of neutrophil extracellular traps (NETs), which are particularly effective against larger pathogens. Beyond direct pathogen clearance, neutrophils undergo transcriptomic changes and produce effector molecules, such as chemokines CCL2, CCL3, and CCL4, to enhance their chemotactic ability and recruit other immune cells to aid in the response [ 31 – 33 ].In our study, we found that the Neu% level of PJP patients [0.832 (0.712–0.913)] was significantly higher than that of PJC patients [0.734 (0.67–0.875)], p = 0.015, indicating that the neutrophil level may play an important role in distinguishing these two diseases. Procalcitonin (PCT) is a biomarker useful in diagnosing fungal infections. In immunocompromised patients, high C-reactive protein (CRP) and low PCT levels can help identify systemic fungal infections, simplifying diagnosis in complex cases. Studies show PCT levels can rise with fungal bloodstream infections and correlate with disease severity [ 34 – 36 ]. Our research also found that the PCT of PJP patients [0.23 (0.11–1.107) vs. 0.1 (0.05–0.467), p = 0.003] is high, which demonstrated PJP is a more severe clinical type. Our study is the first to propose that PCT can differentiate between PJP and colonization. Pneumocystis infection elevates pro-inflammatory cytokines like IL-1β,TNF-α, IL-6 and IFN-γ, potentially stimulating pulmonary PCT release [ 37 – 41 ]. While pneumocystis colonization causes only minimal pulmonary tissue injury and less cytokines production. Therefore, PCT have the potential to be a promising valuable indicator to distinguish these two diseases. Elevated lactate dehydrogenase (LDH) levels are a key biomarker for diagnosing and assessing the prognosis of PJP, especially in HIV-negative patients. In HIV-positive individuals, combining LDH with BDG enhances diagnostic accuracy. This combination, alongside clinical criteria, offers high sensitivity and specificity for PJP diagnosis. Additionally, LDH levels can help predict mortality risk, as demonstrated by a risk scoring system incorporating age, gender, and LDH levels. This risk score outperformed the traditional CURB-65 in predicting mortality in PJP patients without HIV. LDH changes in Pneumocystis jirovecii infection are crucial for diagnosis and assessing prognosis and mortality risk. These findings offer valuable insights for clinical practice, aiding in the management and treatment of PJP patients [ 42 – 44 ]. We found that the LDH level of PJP patients [345.5 (263.75–577)] was significantly higher than that of PJC patients [251 (197–406)], p < 0.0001, indicating that the LDH level may play an important role in distinguishing these two diseases. Serum (1→3)-β-D-glucan (BDG) has demonstrated clinical utility, yet its diagnostic performance exhibits notable limitations in the diagnostic evaluation of PJP. Current evidence reveals suboptimal sensitivity as low as 39.39% in some studies and variable specificity, particularly when compared to more advanced diagnostic modalities [ 45 ]. Initial analysis revealed significantly elevated BDG levels in patients with PJP[65.01(37.5-241.12)] compared to those with PJC[37.5(37.5-43.18)], p < 0.0001. Consequently, BDG was included as a candidate parameter in our predictive model. However, multivariate regression analysis demonstrated that BDG failed to achieve statistical significance as an independent predictor, leading to its exclusion from the final model. These findings suggest that while BDG test for PJP diagnosis has some diagnostic value but suffers from limited specificity and potential confounding factors. Our analysis revealed that the model-retained indicators (RBC, Lym#, Neu%, PCT, and LDH) demonstrate significant discriminative capacity for differentiating PJP from PJC. The XGB model was selected for its outstanding AUC of 0.9991. To further validate the model's performance, we established an independent external validation cohort comprising 66 consecutively enrolled cases from the First Affiliated Hospital of Guangzhou Medical University. All cases met stringent inclusion criteria (no significant age and sex differences) and were processed using standardized protocols with identical laboratory equipment. The random forest-based algorithm exhibited robust diagnostic performance in the external validation, achieving an AUC of 0.787. This finding highlights the clinical potential of our model as a decision-support tool for distinguishing these respiratory conditions. Importantly, the combination of multiple hematological parameters provided superior diagnostic discrimination compared to individual markers alone, suggesting enhanced clinical utility for PJP and PJC differentiation. Notably, we have previously successfully applied these machine learning algorithms to distinguish influenza and Mycoplasma pneumoniae infections, confirming their robust diagnostic performance [ 46 ]. The clinical landscape of respiratory infections encompasses diverse pathogens including respiratory syncytial virus (RSV) [ 47 ], adenoviruses [ 48 ], human rhinoviruses [ 49 ], and SARS-CoV-2 [ 50 ], each exhibiting distinct biological characteristics and clinical presentations. This pathogen diversity, combined with their varying epidemiological patterns across populations and temporal distributions, highlights the critical need for adaptive diagnostic tools. This study has several limitations. First, the inherent non-specificity of hematological parameters in differentiating pulmonary pathogens, and substantial interpatient physiological variability. Second, the retrospective design inherently limits data completeness and introduces potential confounding variables that could not be controlled for during analysis. Finally, while our findings provide preliminary evidence, the relatively modest sample size may affect the generalizability of the models, warranting validation through larger, prospective multicenter studies. Our results validate both the generalizability and diagnostic efficacy of our model while demonstrating its potential for broader implementation in respiratory pathogen detection. The inherent adaptability of our model renders it a robust diagnostic tool capable of dynamically integrating novel epidemiological and clinical data, thereby addressing the evolving challenges in respiratory pathogen identification and differentiation. Declarations Ethics statement Not applicable. Conflicts of interest The authors declare no competing interests. Funding This work is funded by Guangdong Provincial Center for Disease Control and Prevention Supports Talent Projects (0720240122); Noncommunicable Chronic Diseases-National Science and Technology Major Project (2024ZD0533100 & 2024ZD0533106); Basic and Applied Basic Research Foundation of Guangdong Province (2023A1515012526 & 2024A1515012332). Author Contribution JP, XL and GH were involved in data collection. QY and BX analyzed the data and prepared manuscript draft. PC, WL, YC designed the study and revised the manuscript. All the participating authors read and approved the submitted manuscript. Acknowledgements Not applicable Data Availability The original contributions presented in the study are included in the article. Further inquiries can be directed to the corresponding author. References Rhoads, S., Maloney, J., Mantha, A., Van Hook, R. & Henao-Martínez, A. F. Pneumocystis jirovecii Pneumonia in HIV-Negative, Non-transplant Patients: Epidemiology, Clinical Manifestations, Diagnosis, Treatment, and Prevention. Curr. Fungal Infect. Rep. 18 , 125–135. 10.1007/s12281-024-00482-8 (2024). Salzer, H. J. F. et al. Clinical, Diagnostic, and Treatment Disparities between HIV-Infected and Non-HIV-Infected Immunocompromised Patients with Pneumocystis jirovecii Pneumonia. Respiration 96 , 52–65. 10.1159/000487713 (2018). Yu, S., Yang, T. & Non -HIV Immunocompetent Patient with COVID-19 and Severe Pneumocystis jirovecii Pneumonia Co-Infection. Emerg. Infect. Dis. 30 , 1948–1952. 10.3201/eid3009.240615 (2024). Gioia, F., Albasata, H. & Hosseini-Moghaddam, S. M. Concurrent Infection with SARS-CoV-2 and Pneumocystis jirovecii in Immunocompromised and Immunocompetent Individuals. J. Fungi (Basel) . 8 10.3390/jof8060585 (2022). Morris, A. & Norris, K. A. Colonization by Pneumocystis jirovecii and its role in disease. Clin. Microbiol. Rev. 25 , 297–317. 10.1128/cmr.00013-12 (2012). Cañas-Arboleda, A. et al. Colonization by Pneumocystis jirovecii in patients with chronic obstructive pulmonary disease: association with exacerbations and lung function status. Braz J. Infect. Dis. 23 , 352–357. 10.1016/j.bjid.2019.08.008 (2019). Li, S. et al. Study on mNGS Technique in Diagnosing Pneumocystis jirovecii Pneumonia in Non-HIV-Infected Patients. Infect. Drug Resist. 17 , 1397–1405. 10.2147/idr.S450878 (2024). Damiani, C. et al. Combined quantification of pulmonary Pneumocystis jirovecii DNA and serum (1->3)-β-D-glucan for differential diagnosis of pneumocystis pneumonia and Pneumocystis colonization. J. Clin. Microbiol. 51 , 3380–3388. 10.1128/jcm.01554-13 (2013). Matsumura, Y. et al. Quantitative real-time PCR and the (1→3)-β-D-glucan assay for differentiation between Pneumocystis jirovecii pneumonia and colonization. Clin. Microbiol. Infect. 18 , 591–597. 10.1111/j.1469-0691.2011.03605.x (2012). Desoubeaux, G. et al. Combination of β-(1, 3)-D-glucan testing in serum and qPCR in nasopharyngeal aspirate for facilitated diagnosis of Pneumocystis jirovecii pneumonia. Mycoses 62 , 1015–1022. 10.1111/myc.12997 (2019). Esteves, F. et al. Diagnosis of Pneumocystis pneumonia: evaluation of four serologic biomarkers. Clin. Microbiol. Infect. 21 , 379e371–379e310. 10.1016/j.cmi.2014.11.025 (2015). Jiang, Y. et al. Clinical Characteristics and Prognosis of Patients With Severe Pneumonia With Pneumocystis jirovecii Colonization: A Multicenter, Retrospective Study. Chest 167 , 54–66. 10.1016/j.chest.2024.07.140 (2025). Zhang, F. et al. TT@MHA: A machine learning-based webpage tool for discriminating thalassemia trait from microcytic hypochromic anemia patients. Clin. Chim. Acta . 545 10.1016/j.cca.2023.117368 (2023). 1 Zhang, F. et al. Enhancing thalassemia gene carrier identification in non-anemic populations using artificial intelligence erythrocyte morphology analysis and machine learning. Eur. J. Haematol. 112 , 692–700. 10.1111/ejh.14160 (2024). Li, X., Xiong, X., Liang, Z. & Tang, Y. A machine learning diagnostic model for Pneumocystis jirovecii pneumonia in patients with severe pneumonia. Intern. Emerg. Med. 18 , 1741–1749. 10.1007/s11739-023-03353-1 (2023). Lian, Q. et al. Alterations of lung microbiota in lung transplant recipients with pneumocystis jirovecii pneumonia. Respir Res. 25 10.1186/s12931-024-02755-9 (2024). Sayson, S. G., Ashbaugh, A., Porollo, A., Smulian, G. & Cushion, M. T. Pneumocystis murina promotes inflammasome formation and NETosis during Pneumocystis pneumonia. mBio 15 , e0140924. 10.1128/mbio.01409-24 (2024). Kim, S. J. et al. Prognostic factors of Pneumocystis jirovecii pneumonia in patients without HIV infection. J. Infect. 69 , 88–95. 10.1016/j.jinf.2014.02.015 (2014). Bateman, M., Oladele, R. & Kolls, J. K. Diagnosing Pneumocystis jirovecii pneumonia: A review of current methods and novel approaches. Med. Mycol. 58 , 1015–1028. 10.1093/mmy/myaa024 (2020). Zhan, Y. et al. Development and Evaluation of Rapid and Accurate CRISPR/Cas13-Based RNA Diagnostics for Pneumocystis jirovecii Pneumonia. Front. Cell. Infect. Microbiol. 12 10.3389/fcimb.2022.904485 (2022). Moreno, A., Epstein, D., Budvytiene, I. & Banaei, N. Accuracy of Pneumocystis jirovecii Plasma Cell-Free DNA PCR for Noninvasive Diagnosis of Pneumocystis Pneumonia. J. Clin. Microbiol. 60 , e0010122. 10.1128/jcm.00101-22 (2022). Szydłowicz, M. & Matos, O. Pneumocystis pneumonia in the COVID-19 pandemic era: similarities and challenges. Trends Parasitol. 37 , 859–862. 10.1016/j.pt.2021.07.010 (2021). Peng, J. et al. Successful treatment of a kidney transplant patient with COVID-19 and late-onset Pneumocystis jirovecii pneumonia. Ann. Clin. Microbiol. Antimicrob. 20 10.1186/s12941-021-00489-w (2021). Yehouenou Tessi, R. T. et al. An etiology of ground - glass images during COVID-19: Pneumocystis jiroveci pneumonia. SAGE Open. Med. Case Rep. 10 , 2050313x221091391. 10.1177/2050313x221091391 (2022). Xing, F. et al. Rapid Diagnosis of Pneumocystis jirovecii Pneumonia and Respiratory Tract Colonization by Next-Generation Sequencing. Mycopathologia 189 10.1007/s11046-024-00849-y (2024). Liu, L., Yuan, M., Shi, Y. & Su, X. Clinical Performance of BAL Metagenomic Next-Generation Sequence and Serum (1,3)-β-D-Glucan for Differential Diagnosis of Pneumocystis jirovecii Pneumonia and Pneumocystis jirovecii Colonisation. Front. Cell. Infect. Microbiol. 11 , 784236. 10.3389/fcimb.2021.784236 (2021). Lind, A. P. & Anderson, P. C. Predicting drug activity against cancer cells by random forest models based on minimal genomic information and chemical properties. PLoS One . 14 , e0219774. 10.1371/journal.pone.0219774 (2019). Zeng, J. et al. Development of a machine learning model to predict early recurrence for hepatocellular carcinoma after curative resection. Hepatobiliary Surg. Nutr. 11 , 176–187. 10.21037/hbsn-20-466 (2022). Hughes, K. R., Biagini, G. A. & Craig, A. G. Continued cytoadherence of Plasmodium falciparum infected red blood cells after antimalarial treatment. Mol. Biochem. Parasitol. 169 , 71–78. 10.1016/j.molbiopara.2009.09.007 (2010). King, I. L. et al. Intestinal helminth infection impacts the systemic distribution and function of the naive lymphocyte pool. Mucosal Immunol. 10 , 1160–1168. 10.1038/mi.2016.127 (2017). Sarkar, A. et al. Infection of neutrophil granulocytes with Leishmania major activates ERK 1/2 and modulates multiple apoptotic pathways to inhibit apoptosis. Med. Microbiol. Immunol. 202 , 25–35. 10.1007/s00430-012-0246-1 (2013). Carlsen, E. D. et al. Leishmania amazonensis amastigotes trigger neutrophil activation but resist neutrophil microbicidal mechanisms. Infect. Immun. 81 , 3966–3974. 10.1128/iai.00770-13 (2013). Ihedioha, O. C. et al. Leishmania major surface components and DKK1 signalling via LRP6 promote migration and longevity of neutrophils in the infection site. Front. Immunol. 15 , 1473133. 10.3389/fimmu.2024.1473133 (2024). Pasyar, N., Alborzi, A. & Pouladfar, G. R. Evaluation of serum procalcitonin levels for diagnosis of secondary bacterial infections in visceral leishmaniasis patients. Am. J. Trop. Med. Hyg. 86 , 119–121. 10.4269/ajtmh.2012.11-0079 (2012). Katte, J. C. et al. Procalcitonin levels in children affected by severe malaria compared to those with uncomplicated malaria in the absence of bacterial infection: a cross-sectional study. Trop. Dis. Travel Med. Vaccines . 8 (5). 10.1186/s40794-022-00163-9 (2022). Vijayan, A. L. et al. Procalcitonin: a promising diagnostic marker for sepsis and antibiotic therapy. J. Intensive Care . 5 10.1186/s40560-017-0246-8 (2017). Kutty, G. et al. β-Glucans Are Masked but Contribute to Pulmonary Inflammation During Pneumocystis Pneumonia. J. Infect. Dis. 214 , 782–791. 10.1093/infdis/jiw249 (2016). Chou, C. W., Lin, F. C., Tsai, H. C. & Chang, S. C. The importance of pro-inflammatory and anti-inflammatory cytokines in Pneumocystis jirovecii pneumonia. Med. Mycol. 51 , 704–712. 10.3109/13693786.2013.772689 (2013). Kottom, T. J., Carmona, E. M. & Limper, A. H. Targeting CARD9 with Small-Molecule Therapeutics Inhibits Innate Immune Signaling and Inflammatory Response to Pneumocystis carinii β-Glucans. Antimicrob. Agents Chemother. 64 10.1128/aac.01210-20 (2020). Endeman, H. et al. Systemic cytokine response in patients with community-acquired pneumonia. Eur. Respir J. 37 , 1431–1438. 10.1183/09031936.00074410 (2011). Paats, M. S. et al. Local and systemic cytokine profiles in nonsevere and severe community-acquired pneumonia. Eur. Respir J. 41 , 1378–1385. 10.1183/09031936.00060112 (2013). Vogel, M. et al. Accuracy of serum LDH elevation for the diagnosis of Pneumocystis jiroveci pneumonia. Swiss Med. Wkly. 141 , w13184. 10.4414/smw.2011.13184 (2011). Esteves, F. et al. 1–3)-beta-D-glucan in association with lactate dehydrogenase as biomarkers of Pneumocystis pneumonia (PcP) in HIV-infected patients. Eur. J. Clin. Microbiol. Infect. Dis. 33 , 1173–1180. 10.1007/s10096-014-2054-6 (2014). Sun, J. et al. Plasma IL-6/IL-10 Ratio and IL-8, LDH, and HBDH Level Predict the Severity and the Risk of Death in AIDS Patients with Pneumocystis Pneumonia. J Immunol Res 1583951, (2016). (2016). 10.1155/2016/1583951 Chen, Q. et al. Diagnostic values of BALF metagenomic next-generation sequencing, BALF real-time PCR and serum BDG for Pneumocystis jirovecii pneumonia in HIV-infected patients. Front. Microbiol. 15 , 1421660. 10.3389/fmicb.2024.1421660 (2024). Chen, J. et al. Application of peripheral blood routine parameters in the diagnosis of influenza and Mycoplasma pneumoniae. Virol. J. 21 , 162. 10.1186/s12985-024-02429-4 (2024). Gong, X. et al. Clinical research on RSV prevention in children and pregnant women: progress and perspectives. Front. Immunol. 14 , 1329426. 10.3389/fimmu.2023.1329426 (2023). Greber, U. F. Adenoviruses - Infection, pathogenesis and therapy. FEBS Lett. 594 , 1818–1827. 10.1002/1873-3468.13849 (2020). Jacobs, S. E., Lamson, D. M., George, S., Walsh, T. J. & K. & Human rhinoviruses. Clin. Microbiol. Rev. 26 , 135–162. 10.1128/cmr.00077-12 (2013). Chen, J. et al. Epidemiological and laboratory characteristics of Omicron infection in a general hospital in Guangzhou: a retrospective study. Front. Public. Health . 11 , 1289668. 10.3389/fpubh.2023.1289668 (2023). Chart Chart 1 is available in the Supplementary Files section. Additional Declarations No competing interests reported. Supplementary Files Flowchart1.tif Chart1 Patient enrolment and flow through the study SupplementaryFiguresofPJPvs.PJC.pdf Cite Share Download PDF Status: Published Journal Publication published 25 Apr, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 19 Jan, 2026 Reviews received at journal 10 Jan, 2026 Reviews received at journal 31 Dec, 2025 Reviewers agreed at journal 18 Dec, 2025 Reviewers agreed at journal 16 Dec, 2025 Reviewers invited by journal 16 Dec, 2025 Editor assigned by journal 16 Dec, 2025 Editor invited by journal 09 Dec, 2025 Submission checks completed at journal 08 Dec, 2025 First submitted to journal 08 Dec, 2025 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-8251095","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":562208571,"identity":"ffec1e76-f91c-4ea6-b178-4a62f6a009f8","order_by":0,"name":"Qianyu Ye","email":"","orcid":"","institution":"The First Affiliated Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Qianyu","middleName":"","lastName":"Ye","suffix":""},{"id":562208572,"identity":"70e428b2-9f53-4ff7-a9c9-72889e198af2","order_by":1,"name":"Bo Xiang","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Xiang","suffix":""},{"id":562208573,"identity":"df21e858-6029-4d87-9ff6-524216a6e3bc","order_by":2,"name":"Jufeng Pan","email":"","orcid":"","institution":"The Fourth People's Hospital of Nanhai","correspondingAuthor":false,"prefix":"","firstName":"Jufeng","middleName":"","lastName":"Pan","suffix":""},{"id":562208578,"identity":"e5733a83-8269-497a-8a7e-6c2b6a7df486","order_by":3,"name":"Xiaoqi Luo","email":"","orcid":"","institution":"Guangzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoqi","middleName":"","lastName":"Luo","suffix":""},{"id":562208579,"identity":"9d359d9e-6e69-4c3b-ba51-91057bbc043a","order_by":4,"name":"Gang Huang","email":"","orcid":"","institution":"The First Affiliated Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Gang","middleName":"","lastName":"Huang","suffix":""},{"id":562208580,"identity":"a338f2d4-63ea-4aa0-873a-0cd7bd835daa","order_by":5,"name":"Peisong Chen","email":"","orcid":"","institution":"The First Affiliated Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Peisong","middleName":"","lastName":"Chen","suffix":""},{"id":562208581,"identity":"f730a4e3-e598-499e-b0f6-a083a59e4dbb","order_by":6,"name":"Wenbin Lin","email":"","orcid":"","institution":"The First Affiliated Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Wenbin","middleName":"","lastName":"Lin","suffix":""},{"id":562208583,"identity":"99e3525a-b237-41cf-9fc5-63a8fb5c10e7","order_by":7,"name":"Yili Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABC0lEQVRIiWNgGAWjYDACCRBRIGHHD6QOPICJ8hDUYiCRLNkA1JJAghYGxg0HgDRRWvhnNx97zGNgwWx87fBDoC11ifNnJDA+eNvGIG+Oy5I7x9KNeQwk+MxupxkAtRxO3HAjgdlwbhuD4c4G7FoMJHLMpIFamM1uJ4C0HEjcIJHAJs3bxgDk4tKS/w2khXHz7PQPMIex/8avJYcNrGWDdA7IFubEhhsJbMz4tEjcSDOTnAMMZInbOQUHEgwOG28487BZcs45CcMNOLTwz0h+JvGmos6Of3b65g8fKupk57cnH/zwpsxGHpctIMCEiAUDBscGBsYGBmh84QSMP5A49niVjoJRMApGwYgEAA5EWN7+YctVAAAAAElFTkSuQmCC","orcid":"","institution":"The First Affiliated Hospital, Sun Yat-sen University","correspondingAuthor":true,"prefix":"","firstName":"Yili","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-12-01 13:53:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8251095/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8251095/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-48520-4","type":"published","date":"2026-04-25T15:59:09+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":98779389,"identity":"27626025-40a5-436c-a33f-e6330296df6c","added_by":"auto","created_at":"2025-12-22 12:30:19","extension":"tiff","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4892778,"visible":true,"origin":"","legend":"","description":"","filename":"Fig1.tiff","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/58cc0b39bd9b39b9340a0ebd.tiff"},{"id":98778518,"identity":"a7aabb6c-7438-4fa3-869c-74992798debb","added_by":"auto","created_at":"2025-12-22 12:29:24","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":112639,"visible":true,"origin":"","legend":"","description":"","filename":"PJPArticle1201revisedmanuscriptv3.docx","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/e7dddd1610b55c21cb07cb1e.docx"},{"id":98779190,"identity":"91784238-9115-4292-8cec-65dca352dd33","added_by":"auto","created_at":"2025-12-22 12:30:03","extension":"tiff","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5192554,"visible":true,"origin":"","legend":"","description":"","filename":"Fig2.tiff","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/3494670a0afb39054673aa89.tiff"},{"id":98761913,"identity":"588c1f06-a6a1-48fa-90fd-093593a6436e","added_by":"auto","created_at":"2025-12-22 09:56:47","extension":"tiff","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5025034,"visible":true,"origin":"","legend":"","description":"","filename":"Fig3.tiff","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/48471552b0ab90737af8837d.tiff"},{"id":98779897,"identity":"97acd962-f906-4da4-b647-e7c42cabe38f","added_by":"auto","created_at":"2025-12-22 12:30:55","extension":"tiff","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5230634,"visible":true,"origin":"","legend":"","description":"","filename":"Fig4.tiff","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/599108f6033b7f54c8d33e28.tiff"},{"id":98779380,"identity":"e4939242-43db-4d82-bbdd-eb81b49f3c7c","added_by":"auto","created_at":"2025-12-22 12:30:18","extension":"tif","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1698078,"visible":true,"origin":"","legend":"","description":"","filename":"Flowchart1.tif","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/6835889acfb5a07e1b6fb419.tif"},{"id":98779895,"identity":"6f075c6e-5ae6-482a-b05a-6573ca2c6c4f","added_by":"auto","created_at":"2025-12-22 12:30:54","extension":"json","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8594,"visible":true,"origin":"","legend":"","description":"","filename":"5eda3bc1ca4b497ba7e215d6bc2d1d2d.json","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/47bb68a4d369651f7a8698db.json"},{"id":98779185,"identity":"589a54b3-2f52-49c6-b3e4-efe092c57b1d","added_by":"auto","created_at":"2025-12-22 12:30:01","extension":"pdf","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":404228,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFiguresofPJPvs.PJC.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/abe10b5d4278815ad2b3c465.pdf"},{"id":98778072,"identity":"4c17b9fd-bfe5-4b92-9a14-68e699f65005","added_by":"auto","created_at":"2025-12-22 12:28:52","extension":"xml","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":145646,"visible":true,"origin":"","legend":"","description":"","filename":"5eda3bc1ca4b497ba7e215d6bc2d1d2d1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/ef9b4409f001fd16f980f2ac.xml"},{"id":98778063,"identity":"4a9fe893-b520-4055-8ad9-940406ad65f9","added_by":"auto","created_at":"2025-12-22 12:28:52","extension":"tiff","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4892778,"visible":true,"origin":"","legend":"","description":"","filename":"Fig1.tiff","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/3ee7e17d7b57fde731d27495.tiff"},{"id":98761920,"identity":"462bd453-d87f-489f-b8cc-45224e00ab7c","added_by":"auto","created_at":"2025-12-22 09:56:47","extension":"tiff","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5192554,"visible":true,"origin":"","legend":"","description":"","filename":"Fig2.tiff","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/5dc78dfe47800bb878c68df9.tiff"},{"id":98761923,"identity":"d48e1ca4-fa7d-4631-8f59-2b7d4c7cd06a","added_by":"auto","created_at":"2025-12-22 09:56:47","extension":"tiff","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5025034,"visible":true,"origin":"","legend":"","description":"","filename":"Fig3.tiff","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/506d19af2a52a65e36255d29.tiff"},{"id":98780659,"identity":"8f5d0b3f-1265-47bf-ad64-c99f36132692","added_by":"auto","created_at":"2025-12-22 12:31:32","extension":"tiff","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5230634,"visible":true,"origin":"","legend":"","description":"","filename":"Fig4.tiff","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/c0015e0adda8a7f2f2af95c2.tiff"},{"id":98761925,"identity":"ef5d8949-5658-43d3-af9e-d57d41b0c193","added_by":"auto","created_at":"2025-12-22 09:56:47","extension":"tif","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1698078,"visible":true,"origin":"","legend":"","description":"","filename":"Flowchart1.tif","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/bbb52348b064351b6639f358.tif"},{"id":98779225,"identity":"f446cbda-5680-40dc-a2e4-27454f712e34","added_by":"auto","created_at":"2025-12-22 12:30:05","extension":"jpeg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93000,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/d4d6410ade5fac8c3b7b06e7.jpeg"},{"id":98777772,"identity":"eb6b74b3-b0af-439b-9a82-415d5bc54ac1","added_by":"auto","created_at":"2025-12-22 12:28:25","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":237426,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFlowchart1.png","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/4a19f19614acfc3ed88029bf.png"},{"id":98779147,"identity":"66a5f90b-ecd0-472f-8c24-8f703f9cb845","added_by":"auto","created_at":"2025-12-22 12:30:00","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23305,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/3e8a10a11a15cc2dd76ef7e6.png"},{"id":98761928,"identity":"f4560a75-95b1-495d-8682-4a511737c94d","added_by":"auto","created_at":"2025-12-22 09:56:47","extension":"xml","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":143637,"visible":true,"origin":"","legend":"","description":"","filename":"5eda3bc1ca4b497ba7e215d6bc2d1d2d1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/eb595421ba0d30387518c026.xml"},{"id":98779340,"identity":"1b119fe5-c72f-48ab-97fa-e55fadb15d93","added_by":"auto","created_at":"2025-12-22 12:30:15","extension":"html","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":158263,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/86989c3e48043d2ef265f238.html"},{"id":98779348,"identity":"191df475-2352-47eb-b100-162756a35e1c","added_by":"auto","created_at":"2025-12-22 12:30:16","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":57408,"visible":true,"origin":"","legend":"\u003cp\u003ePerformance comparisons among five models\u003c/p\u003e","description":"","filename":"OnlineFig1.png","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/d53c72dad4a387244a45e657.png"},{"id":98779382,"identity":"66e0f42c-4b0f-41e0-8a8b-6611732fd988","added_by":"auto","created_at":"2025-12-22 12:30:19","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":17403,"visible":true,"origin":"","legend":"\u003cp\u003eFeature importance of the model\u003c/p\u003e","description":"","filename":"OnlineFig2.png","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/2fd20a50fb51660878571cc8.png"},{"id":98761907,"identity":"3d598d5e-fa3d-4587-b823-363f27302897","added_by":"auto","created_at":"2025-12-22 09:56:46","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":26952,"visible":true,"origin":"","legend":"\u003cp\u003eROC for interlaboratory validation of PJ infection model\u003c/p\u003e","description":"","filename":"OnlineFig3.png","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/ee87b22becfc7ed4fbb33d3a.png"},{"id":98780017,"identity":"9011744f-ccd5-4a6f-9edf-59d2b269a769","added_by":"auto","created_at":"2025-12-22 12:30:59","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":38495,"visible":true,"origin":"","legend":"\u003cp\u003eScreenshot of Web-based Prediction Interface\u003c/p\u003e","description":"","filename":"OnlineFig4.png","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/85c1283f8f12c5f6a7e6a882.png"},{"id":107929177,"identity":"02031fe6-1f5f-4453-9490-39025e34f1db","added_by":"auto","created_at":"2026-04-27 16:14:12","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":719987,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/49ac0664-8c3f-42e8-a12c-a4cd12fe9d35.pdf"},{"id":98761903,"identity":"c3a757d4-f8d2-4142-9d3f-d9034ad4ed82","added_by":"auto","created_at":"2025-12-22 09:56:46","extension":"tif","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1698078,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eChart1\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003ePatient enrolment and flow through the study\u003c/p\u003e","description":"","filename":"Flowchart1.tif","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/951237c23af66feaca46dd62.tif"},{"id":98778559,"identity":"22c5b8a0-dc83-4802-9eb6-7b1e517fb346","added_by":"auto","created_at":"2025-12-22 12:29:27","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":404228,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFiguresofPJPvs.PJC.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8251095/v1/1ccaffe2765967497e3cc251.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A diagnostic model for discrimination between Pneumocystis jirovecii pneumonia and asymptomatic colonization based on multiple parameters","fulltext":[{"header":"Introduction","content":"\u003cp\u003e \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e pneumonia (PJP) is a life-threatening opportunistic infection predominantly observed in immunocompromised individuals, particularly those with HIV infection. Despite advances in antimicrobial prophylaxis and antiretroviral therapy, PJP continues to pose a significant clinical challenge, with mortality rates reaching up to 50% in high-risk populations, emphasizing the critical need for early diagnosis and vigilant monitoring [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. The COVID-19 pandemic complicated PJP presentations, including cases without HIV or immunodeficiency [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Such patients often exhibit atypical symptoms, increasing misdiagnosis risks and rapid clinical deterioration, ultimately worsening outcomes [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e colonization (PJC) is increasingly recognized as a distinct clinical entity, particularly in immunocompetent hosts, where it is typically asymptomatic or associated with mild respiratory symptoms [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Distinguishing between PJC and infection (PJP) directly impacts therapeutic decision-making, prognostic evaluation, and public health strategies. Particularly in the context of a growing immunocompromised population, accurate differentiation is critical for personalized medicine.\u003c/p\u003e \u003cp\u003eCurrent PJP diagnostics, including metagenomic next-generation sequencing (mNGS) and droplet digital quantitative PCR (dd-qPCR), exhibit high sensitivity but limited specificity in distinguishing PJP from colonization. While mNGS demonstrates superior pathogen detection in immunosuppressed non-HIV patients compared to conventional PCR, it remains unable to reliably differentiate infection from colonization [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Similarly, qPCR shows high sensitivity but poor specificity [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Blood tests are more convenient and time-efficient for differential diagnoses of fungal infection. Detecting serum BDG levels is an effective method for distinguishing \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e infection from colonization with BAL or blood [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Peripheral blood parameters show potential in rapid diagnosing PJP and PJC as an adjuvant diagnostic tool for mNGS. These markers offer a convenient and effective diagnostic option for guiding treatment strategies and preventing antibiotic misuse, especially for mild clinical presentation, but no study has yet shown their effective use for this purpose, indicating a need for further research [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eTo meet this goal, we conducted a retrospective study at the First Affiliated Hospital of Sun Yat-sen University, to compare clinical symptoms, imaging, and blood markers of PJP and PJC. Our objective is to enhance understanding and improve diagnosis and patient outcomes for these conditions.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eData collection\u003c/h2\u003e \u003cp\u003e Clinical laboratory data were retrospectively obtained from patients who attended the outpatient department of the First Affiliated Hospital of Sun Yat-sen University, between April 18, 2022, and September 19, 2024. The data were extracted from digital medical records and included variables such as age, sex, and blood test results at the onset of illness. Specifically, the blood test parameters collected were white blood cell count (WBC), lymphocyte percentage (Lym%), neutrophil percentage (Neu%), Monocyte percentage (mono%), red blood cell count (RBC), platelet count (PLT), C-reactive protein (CRP), procalcitonin (PCT), lactic dehydrogenase (LDH).\u003c/p\u003e \u003cp\u003eA total of 1058 patients with suspected PJP infection were enrolled, and 235 patients were diagnosed with positive for \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e by BALF real-time quantitative polymerase chain reaction (RT-qPCR). We used uniform diagnostic criteria for the differential diagnosis of PJP and PJC based on host fator and clinical characteristics. Diagnostic classification of PJP or PJC was performed through independent evaluation by two unblinded physicians. Any diagnostic discrepancies were resolved through adjudication by a third senior clinician. Patients with positive clinical metagenomic test results for \u003cem\u003eP. jirovecii\u003c/em\u003e were systematically included. The clinical diagnosis of PJP was confirmed when a patient satisfied all of the following criteria: (1) Positive microscopic identification of \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e mNGS detection in BAL fluid; (2) Presence of at least two of the PCP manifestations-dyspnea, fever, non-productive cough, hypoxemia (oxygen saturation less than 90% on room air); (3) Characteristic bilateral pulmonary opacities on chest computed tomography (CT), typically manifesting as diffuse ground-glass infiltrates; After applying the inclusion criteria, we implemented the following exclusion criteria: (1) Patients with alternative pulmonary pathologies demonstrating CT findings indistinguishable from PJP, including laboratory-confirmed SARS-CoV-2 infection and microbiologically proven invasive aspergillosis; (2) A negative result of BALF RT-qPCR; (3) Unavailability of BALF mNGS data. Patients not meeting these exclusion criteria were subsequently classified as having \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e colonization [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. This non-interventional study was approved by the ethics committee of the First Affiliated Hospital, Sun Yet-sen University ([2023]459). All PJP and PJC patients agreed to participate in this study and signed the informed consent form by themselves or their legal guardians based on the Helsinki Declaration.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eData preprocessing\u003c/h3\u003e\n\u003cp\u003eIn this study, a total of 1058 cases were initially collected. To precisely elucidate the critical role of various blood test indicators in diagnosing PJP and PJC among pediatric patients, the study rigorously excluded cases with incomplete test data, subjects with co-infections from other respiratory pathogens. Following data preprocessing, 235 cases were retained for analysis, comprising 174 cases of PJP and 61 cases of PJC (Chart1).\u003c/p\u003e \u003cp\u003eWe utilized the Deepwise \u0026amp; Beckman Coulter DxAI platform, an online statistical tool available at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://dxonline.deepwise.com/\u003c/span\u003e\u003cspan address=\"http://dxonline.deepwise.com/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e, to develop a machine learning-based algorithm. This platform is specifically designed to autonomously select suitable machine learning models, present analytical data, and facilitate online analysis. We implemented a series of increasingly sophisticated models, including Random Forest (RF), Multilayer Perceptron (MP), Gradient Boosting (GB), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA) [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. The dataset was partitioned into training and validation sets in a 7:3 ratio through random allocation, and this process was repeated across 100 iterations to ensure robustness. To further validate the reliability and reproducibility of the algorithm, we conducted an additional round of validation using a cross-sectional study. This study was conducted at the same hospital, covering the period from January 16th to January 27th, 2024, and adhered to the same diagnostic protocols. Laboratory test results from this period were processed using the algorithm.\u003c/p\u003e \u003cp\u003eThe dataset was partitioned into training and validation subsets in a 7:3 ratio through random allocation. This partitioning process was iteratively performed 100 times to enhance robustness. To further ensure the reliability and reproducibility of the algorithm, an additional validation round was conducted using a cross-sectional study. This study was derived from The First Affiliated Hospital of Guangzhou Medical University, encompassing the period from January 16th to January 27th, 2024, and adhered to consistent diagnostic protocols. Laboratory test results from this timeframe were processed using the algorithm. The efficacy of algorithm was evaluated using several key metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, recall rate, F1 score, sensitivity, specificity, and both positive and negative predictive values.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e\n\u003ch3\u003eChart1\u003c/h3\u003e\n\u003cp\u003ePatient enrolment and flow through the study\u003c/p\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eData analysis was conducted utilizing SPSS version 26.0. The normality of the data distribution was examined via the Kolmogorov-Smirnov test. For blood test indicators that adhered to a normal distribution, between-group differences were assessed using the T-test, whereas the Wilcoxon test was applied to indicators that deviated from a normal distribution. Differences in sex among groups were evaluated using the Chi-square test. Continuous variables were reported as medians with interquartile ranges (P25, P75), while categorical variables were presented as means\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation. The diagnostic efficacy of the models was assessed through Receiver Operating Characteristic (ROC) analysis. The performance of each model was detailed and compared using metrics such as the area under the curve (AUC), accuracy, F1 score, sensitivity, specificity, positive predictive value, and negative predictive value. The Delong test was used to compare the AUC values of different models, with statistical significance set at a p-value of less than 0.05.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eComparative analysis of the clinical characteristics in the cross-sectional study\u003c/h2\u003e \u003cp\u003eThe study cohort comprised 235 hospitalized patients, including 174 \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e pneumonia cases and 61 \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e colonization cases. The median age of the patients was 61 years, with 160 (68.1%) males and 75 (31.9%) females. Demographic analysis revealed comparable sex distribution between groups (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05). While clinical manifestations including Shortness of breath and Chest tightness showed intergroup differences (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05), significant variations emerged in a state of immune insufficiency: PJ infection patients demonstrated higher solid organ transplant rate and Malignant hematologic diseases rate (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01) compared to PJ colonization counterparts. Complete demographic and clinical profiles are detailed in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\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\u003eDemographic and Clinical Characteristics of Study Cohort\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCharacteristics\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePJ infection\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;174)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePJ colonization\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;61)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAll patients\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;235)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP-\u003c/em\u003evalue\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDemographics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e60 (47.25-70)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e65 (50\u0026ndash;71)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e61 (48\u0026ndash;70)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.136\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSex\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.865\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e55 (31.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e20 (32.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e75 (31.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e119 (68.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e41 (67.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e160 (68.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClinical symptoms (n [%])\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFever\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e89 (51.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32 (52.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e121 (51.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.86\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCough\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e99 (56.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30 (49.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e129 (54.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.297\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eShortness of breath\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e82 (47.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e19 (31.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e101 (43.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.030\u003csup\u003e*\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProductive cough\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e72 (41.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e25 (41.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e97 (41.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.957\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChest tightness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e35 (20.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (6.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e39 (16.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.014\u003csup\u003e*\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDyspnea\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19 (10.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (4.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e22 (9.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.166\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImmunocompromised (n [%])\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAutoimmune diseases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (6.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e13 (5.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.222\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSolid organ transplant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e24 (13.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e25 (10.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.008\u003csup\u003e*\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSolid tumors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e43 (24.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10 (16.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e53 (22.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.181\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic kidney disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e15 (8.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (4.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e18 (7.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.512\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMalignant hematologic diseases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22 (12.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (3.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e24 (10.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.038\u003csup\u003e*\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003e* p\u0026thinsp;\u0026lt;\u0026thinsp;0.05, ** p\u0026thinsp;\u0026lt;\u0026thinsp;0.01\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eLaboratory Parameter Comparisons\u003c/h3\u003e\n\u003cp\u003eAs presented in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, the majority of test results demonstrated significant differences between the two groups (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Individuals with \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e infection exhibited RBC and Lym% but higher Neu%, PCT and LDH compared to those \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e colonization patients (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Notably, inflammatory markers including WBC and CRP showed comparable levels between groups (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05).\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\u003eHematological Profile Comparisons\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\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=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCharacteristics\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePJ infection\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;174)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePJ colonization\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;61)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAll patients\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;235)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP-\u003c/em\u003evalue\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWBC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e7.21 (5.188\u0026ndash;10.957)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.445 (5.713\u0026ndash;9.503)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7.325 (5.328\u0026ndash;10.61)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.759\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeu%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.832 (0.712\u0026ndash;0.913)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.734 (0.67\u0026ndash;0.875)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.812 (0.702\u0026ndash;0.897)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.015\u003csup\u003e*\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLym%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.098 (0.048\u0026ndash;0.172)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.161 (0.067\u0026ndash;0.24)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.104 (0.055\u0026ndash;0.192)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.010\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMono%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.052 (0.03\u0026ndash;0.084)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.062 (0.051\u0026ndash;0.082)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.058 (0.032\u0026ndash;0.084)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.09\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRBC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3.3 (2.8\u0026ndash;3.95)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.065 (3.33\u0026ndash;4.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3.455 (2.842\u0026ndash;4.158)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.000\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePLT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e184.5 (115-280.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e227 (150.5\u0026ndash;306)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e191 (127\u0026ndash;285)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.107\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCRP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e45.35 (14.62\u0026ndash;98.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e42.38 (7.27\u0026ndash;75.46)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e43.39 (11.33\u0026ndash;87.11)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.255\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=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.23 (0.11\u0026ndash;1.107)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.1 (0.05\u0026ndash;0.467)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.205 (0.08\u0026ndash;0.898)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.003\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLDH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e345.5 (263.75\u0026ndash;577)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e251 (197\u0026ndash;406)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e335 (233-525.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.000\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBDG\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e65.01(37.5-241.12)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e37.5(37.5-43.18)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e46.42(37.5-177.15)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.000\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003e* p\u0026thinsp;\u0026lt;\u0026thinsp;0.05, ** p\u0026thinsp;\u0026lt;\u0026thinsp;0.01\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003eWBC: White Blood Cell; Lym%: Lymphocyte percentage; Neu%: Neutrophil percentage; Mono#: Monocyte percentage; RBC: Red Blood Cell; PLT: Platelet count; CRP: C-reactive protein; PCT: procalcitonin; LDH: lactic dehydrogenase\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e\n\u003ch3\u003eDevelopment of the PJ infeciton vs colonization model\u003c/h3\u003e\n\u003cp\u003ePredictors for machine learning models were selected by the least absolute shrinkage and selection operator (LASSO) algorithm and clinical experience. By LASSO algorithm, six predictors including RBC, Lym%, PCT, LDH, Shortness of breath and Chest tightness were were selected (shown in Supplementary Figure \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e). Since previous studies have demonstrated the significance of neutrophils in the diagnosis and prognosis of PJP [\u003cspan additionalcitationids=\"CR16 CR17\" citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e], we included Neu% as a predictive factor in the model in this study. Seven candidate predictors (RBC, Lym%, Neu%, PCT, LDH, Shortness of breath and Chest tightness) were initially selected for model construction based on Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e and Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e findings. Five machine learning algorithms were evaluated: Random Forest (RF), Support Vector Machine (SVM), XGBoost (XGB), Linear Discriminant Analysis (LDA), and Multilayer Perceptron (MP). The performance of these models was evaluated using the DeLong test, and their predictive capabilities are presented in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e and Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, all five models demonstrated effective predictive performance in distinguishing patients with \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e pneumonia from those \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e colonization. The results of the DeLong tests for both the training and validation sets of the five models are specifically presented in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. Based on the highest AUC of the XGB model in the training set and its positive difference compared to the other four models (p\u0026thinsp;\u0026lt;\u0026thinsp;0.01) in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, we ultimately selected the XGB model, termed PJ infection vs colonization model, as our predictive algorithm.\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\u003ePJ infection and colonization Model Performance Metrics\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"11\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAUC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003eACC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eF1 score\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRecall\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNPV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003ePPV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c10\"\u003e \u003cp\u003eSE\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c11\"\u003e \u003cp\u003eSP\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eXGB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTraining\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.9991\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003e0.9408\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.9617\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.9262\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.7692\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\u003eValidation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.7228\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003e0.7711\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.8571\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.9344\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.6364\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.7917\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.9344\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.3182\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTraining\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.9145\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003e0.8289\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.8943\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.9735\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.8421\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.8271\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.9735\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.4103\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\u003eValidation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.7095\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003e0.7447\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.8454\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.9425\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.5238\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.7664\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.9425\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.1803\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTraining\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.7667\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003e0.6579\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.7263\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.6106\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.4133\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.8961\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.6106\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.7949\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\u003eValidation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.7064\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003e0.7108\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.7895\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.7377\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.4667\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.8491\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.7377\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.6364\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTraining\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.7468\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003e0.7763\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.8682\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.9912\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.8571\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.7724\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.9912\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.1538\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\u003eValidation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003e0.6431\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.7108\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.831\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.9672\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.7284\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.9672\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLDA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTraining\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003e0.7347\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.7697\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.8617\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.9646\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.6667\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.7786\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.9646\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.2051\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\u003eValidation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003e0.6833\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.7108\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.8235\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.918\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.375\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.7467\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.918\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.1364\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"11\"\u003e*In the training data set, the DeLong test showed that the XGB model had a larger AUC than the LDA, SVM, MP, and RF models (p\u0026thinsp;\u0026lt;\u0026thinsp;0.01)\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"11\"\u003e*In the validation data set, there were not significantly different between the AUCs of all the models (p\u0026thinsp;\u0026gt;\u0026thinsp;0.05)\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"11\"\u003eAUC: area under the curve; ACC: accuracy; SE: sensitivity; SP: specificity; NPV: negative predictive value; PPV: positive predictive value.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\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=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDelong test between the five models\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTraining Delong\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ez\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eValidation Delong\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003ez\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eXGB-RF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3.851\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.000 **\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eXGB-RF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.605\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.108\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eXGB-SVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5.566\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.000 **\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eXGB-SVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.243\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.808\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eXGB-MP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e-5.519\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.000 **\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eXGB-MP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-1.141\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.254\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eXGB-LDA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5.693\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.000 **\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eXGB-LDA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.565\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.572\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRF-SVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4.514\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.000 **\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRF-SVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-0.708\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.479\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRF-MP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e-4.619\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.000 **\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRF-MP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-0.281\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.778\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRF-LDA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.000 **\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRF-LDA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-0.366\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.714\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSVM-MP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e-0.674\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSVM-MP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-1.083\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.279\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSVM-LDA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e-1.752\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSVM-LDA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-0.763\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.445\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMP-LDA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.523\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.601\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eMP-LDA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-0.782\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.434\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"6\"\u003e* p\u0026thinsp;\u0026lt;\u0026thinsp;0.05, ** p\u0026thinsp;\u0026lt;\u0026thinsp;0.01\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"6\"\u003eXGB-RF: Delong test between XGBoost and Random Forest; XGB-SVM: Delong test between XGBoost and Support Vector Machine; XGB-MP: Delong test between XGBoost and Multilayer Perceptron; XGB-LDA: Delong test between XGBoost and Linear Discriminant Analysis; RF-SVM: Delong test between Random Forest Analysis and Support Vector Machine; RF-MP: Delong test between Random Forest Analysis and Multilayer Perceptron; RF-LDA: Delong test between Random Forest and Linear Discriminant Analysis; SVM-MP: Delong test between Support Vector Machine and Multilayer Perceptron, SVM-LDA: Delong test between Support Vector Machine and Linear Discriminant Analysis, MP-LDA: Delong test between Multilayer Perceptron and Linear Discriminant Analysis\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003eFeature Importance of the Model\u003c/h2\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e showed the significance values of the selected factors in the PJ infection vs colonization model algorithm. Within this algorithm, seven factors were retained, with LDH having the utmost weight.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003eExternal validation\u003c/h2\u003e \u003cp\u003eWe selected 66 cases from The First Affiliated Hospital of Guangzhou Medical University diagnosed with \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e pneumonia or \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e colonization cases for PJ infection vs colonization model validation. The diagnostic efficacy of PJ infection vs colonization model in this validation group was summarized in Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e, with an AUC of 0.787, as displayed in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\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\u003eInterlaboratory validation of the model\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\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\u003eAUC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eACC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF1 score\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRecall\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNPV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003ePPV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eSE\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eSP\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInterlaboratory validation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.787\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.800\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.818\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.600\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.783\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.818\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.545\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 \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003eWebpage tool of PJ infection model\u003c/h2\u003e \u003cp\u003eFor clinical translation, we developed a web-based decision tool (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://dxonline.deepwise.com/prediction/index.html?baseUrl=%2Fapi%2F\u0026amp;id=50566\u0026amp;topicName=undefined\u0026amp;from=share\u0026amp;platformType=wisdom\u003c/span\u003e\u003cspan address=\"https://dxonline.deepwise.com/prediction/index.html?baseUrl=%2Fapi%2F\u0026amp;id=50566\u0026amp;topicName=undefined\u0026amp;from=share\u0026amp;platformType=wisdom\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e) enabling real-time risk stratification through parameter input (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). In addition, we have also provided the QR code link of the model for easy access to it. This is to facilitate the usage of the model (shown in Supplementary Figure S2). This digital implementation preserves model accuracy while enhancing bedside accessibility.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eAccurate and timely diagnosis is critical for reducing mortality from PJP, particularly in immunocompromised populations. Conventional diagnostic approaches, which depend on microscopic examination of BAL fluid, are limited by suboptimal sensitivity and often necessitate invasive procedures [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. Emerging molecular techniques, including PCR and CRISPR/Cas13-based assays, permit highly sensitive detection of \u003cem\u003eP. jirovecii\u003c/em\u003e from non-invasive specimens such as sputum and serum [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. These advancements offer valuable diagnostic alternatives for patients who are unsuitable candidates for bronchoscopy [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. The COVID-19 pandemic has further complicated PJP management, with increased incidence and diagnostic challenges arising from clinical and radiological similarities between PJP and SARS-CoV-2 infection [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. Immunosuppression secondary to COVID-19 or its therapeutic regimens has been shown to significantly elevate PJP risk, particularly among solid organ transplant recipients [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. These developments highlight the urgent need for reliable diagnostic algorithms and optimized treatment protocols to enhance clinical outcomes in this vulnerable patient population.\u003c/p\u003e \u003cp\u003eIn this retrospective medical record review, we investigated patients with PJP arising from colonization. Through comprehensive clinical evaluation and mNGS analysis, we identified 235 individuals with \u003cem\u003eP. jirovecii\u003c/em\u003e infection. These cases were subsequently stratified into two distinct cohorts: 174 patients with confirmed PJP and 61 cases demonstrating PJC. Our comparative analysis of clinical characteristics between patients with PJP and those with PJC revealed distinct symptomatic profiles. The most prevalent clinical manifestations among infected individuals included fever, cough (both productive and non-productive), dyspnea, chest tightness, and shortness of breath. Notably, PJP patients demonstrated significantly more severe respiratory symptoms, particularly dyspnea and chest tightness, compared to their PJC counterparts, a finding consistent with previous reports by Xing et al [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. Demographic analysis showed no statistically significant differences in age or sex distribution between the study groups (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05). This pattern remained consistent regardless of concurrent infections with influenza virus or Mycoplasma pneumoniae, supporting the observations made by Liu et al [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. These findings suggest that while demographic factors may not serve as discriminative markers, clinical symptom severity appears to be a reliable indicator for differentiating PJP from PJC.\u003c/p\u003e \u003cp\u003eOur comprehensive analysis of peripheral blood parameters in patients with PJP and PJC revealed several statistically significant differential markers, including RBC, Lym%, Neu%, PCT and LDH levels. While these parameters demonstrated relative discriminative value, none exhibited sufficient diagnostic accuracy when used individually. To enhance diagnostic precision, we explored the potential of artificial intelligence-based multiparametric analysis. Five key hematological parameters were incorporated into various machine learning models. This approach significantly improved diagnostic performance, as evidenced by increased AUC values. Among the evaluated algorithms - including XGB, RF, SVM, MP, and LDA-all demonstrated clinically meaningful predictive capability (AUC\u0026thinsp;\u0026gt;\u0026thinsp;0.68) in distinguishing PJP from PJC across both training and validation datasets. Notably, the XGB model achieved superior performance (AUC\u0026thinsp;\u0026gt;\u0026thinsp;0.99, p\u0026thinsp;\u0026lt;\u0026thinsp;0.01 versus comparator models) and was therefore selected as our final predictive algorithm. Furthermore, refinement of the Random Forest model - a well-established machine learning approach in biomedical research [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e] - identified a core panel of five discriminative parameters (RBC, Lym#, Neu%, PCT, and LDH) that collectively optimize diagnostic differentiation between these clinical entities.\u003c/p\u003e \u003cp\u003eRBC are widely considered to be an important indicator of fungus infection, particularly noting that patients with weakened immune systems often experience higher rates of fungal infections and altered blood parameters [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Compared with PJC patients, PJP usually have a decrease in RBC[4.065 (3.33\u0026ndash;4.48) vs. 3.3 (2.8\u0026ndash;3.95), p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001].\u003c/p\u003e \u003cp\u003eLymphocyte(Lym) significantly changes after fungal infections, particularly in immunosuppressed patients. For instance, those with invasive fungal infections and sepsis exhibit notably reduced lymphocyte counts, highlighting an immunosuppressive condition [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. Compared with PJC patients, PJP had a higher lymphocyte percentage[0.098 (0.048\u0026ndash;0.172) vs. 0.161 (0.067\u0026ndash;0.24), p\u0026thinsp;=\u0026thinsp;0.01].\u003c/p\u003e \u003cp\u003eNeutrophils(Neu) are vital in defending against fungal infections through mechanisms like phagocytosis, oxidative burst, and the release of neutrophil extracellular traps (NETs), which are particularly effective against larger pathogens. Beyond direct pathogen clearance, neutrophils undergo transcriptomic changes and produce effector molecules, such as chemokines CCL2, CCL3, and CCL4, to enhance their chemotactic ability and recruit other immune cells to aid in the response [\u003cspan additionalcitationids=\"CR32\" citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e].In our study, we found that the Neu% level of PJP patients [0.832 (0.712\u0026ndash;0.913)] was significantly higher than that of PJC patients [0.734 (0.67\u0026ndash;0.875)], p\u0026thinsp;=\u0026thinsp;0.015, indicating that the neutrophil level may play an important role in distinguishing these two diseases.\u003c/p\u003e \u003cp\u003eProcalcitonin (PCT) is a biomarker useful in diagnosing fungal infections. In immunocompromised patients, high C-reactive protein (CRP) and low PCT levels can help identify systemic fungal infections, simplifying diagnosis in complex cases. Studies show PCT levels can rise with fungal bloodstream infections and correlate with disease severity [\u003cspan additionalcitationids=\"CR35\" citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e]. Our research also found that the PCT of PJP patients [0.23 (0.11\u0026ndash;1.107) vs. 0.1 (0.05\u0026ndash;0.467), p\u0026thinsp;=\u0026thinsp;0.003] is high, which demonstrated PJP is a more severe clinical type. Our study is the first to propose that PCT can differentiate between PJP and colonization. Pneumocystis infection elevates pro-inflammatory cytokines like IL-1β,TNF-α, IL-6 and IFN-γ, potentially stimulating pulmonary PCT release [\u003cspan additionalcitationids=\"CR38 CR39 CR40\" citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]. While pneumocystis colonization causes only minimal pulmonary tissue injury and less cytokines production. Therefore, PCT have the potential to be a promising valuable indicator to distinguish these two diseases.\u003c/p\u003e \u003cp\u003eElevated lactate dehydrogenase (LDH) levels are a key biomarker for diagnosing and assessing the prognosis of PJP, especially in HIV-negative patients. In HIV-positive individuals, combining LDH with BDG enhances diagnostic accuracy. This combination, alongside clinical criteria, offers high sensitivity and specificity for PJP diagnosis. Additionally, LDH levels can help predict mortality risk, as demonstrated by a risk scoring system incorporating age, gender, and LDH levels. This risk score outperformed the traditional CURB-65 in predicting mortality in PJP patients without HIV. LDH changes in \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e infection are crucial for diagnosis and assessing prognosis and mortality risk. These findings offer valuable insights for clinical practice, aiding in the management and treatment of PJP patients [\u003cspan additionalcitationids=\"CR43\" citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e]. We found that the LDH level of PJP patients [345.5 (263.75\u0026ndash;577)] was significantly higher than that of PJC patients [251 (197\u0026ndash;406)], p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001, indicating that the LDH level may play an important role in distinguishing these two diseases.\u003c/p\u003e \u003cp\u003eSerum (1\u0026rarr;3)-β-D-glucan (BDG) has demonstrated clinical utility, yet its diagnostic performance exhibits notable limitations in the diagnostic evaluation of PJP. Current evidence reveals suboptimal sensitivity as low as 39.39% in some studies and variable specificity, particularly when compared to more advanced diagnostic modalities [\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e]. Initial analysis revealed significantly elevated BDG levels in patients with PJP[65.01(37.5-241.12)] compared to those with PJC[37.5(37.5-43.18)], p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001. Consequently, BDG was included as a candidate parameter in our predictive model. However, multivariate regression analysis demonstrated that BDG failed to achieve statistical significance as an independent predictor, leading to its exclusion from the final model. These findings suggest that while BDG test for PJP diagnosis has some diagnostic value but suffers from limited specificity and potential confounding factors.\u003c/p\u003e \u003cp\u003eOur analysis revealed that the model-retained indicators (RBC, Lym#, Neu%, PCT, and LDH) demonstrate significant discriminative capacity for differentiating PJP from PJC. The XGB model was selected for its outstanding AUC of 0.9991. To further validate the model's performance, we established an independent external validation cohort comprising 66 consecutively enrolled cases from the First Affiliated Hospital of Guangzhou Medical University. All cases met stringent inclusion criteria (no significant age and sex differences) and were processed using standardized protocols with identical laboratory equipment. The random forest-based algorithm exhibited robust diagnostic performance in the external validation, achieving an AUC of 0.787. This finding highlights the clinical potential of our model as a decision-support tool for distinguishing these respiratory conditions. Importantly, the combination of multiple hematological parameters provided superior diagnostic discrimination compared to individual markers alone, suggesting enhanced clinical utility for PJP and PJC differentiation.\u003c/p\u003e \u003cp\u003eNotably, we have previously successfully applied these machine learning algorithms to distinguish influenza and \u003cem\u003eMycoplasma\u003c/em\u003e pneumoniae infections, confirming their robust diagnostic performance [\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e]. The clinical landscape of respiratory infections encompasses diverse pathogens including respiratory syncytial virus (RSV) [\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e], adenoviruses [\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e], human rhinoviruses [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e], and SARS-CoV-2 [\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e], each exhibiting distinct biological characteristics and clinical presentations. This pathogen diversity, combined with their varying epidemiological patterns across populations and temporal distributions, highlights the critical need for adaptive diagnostic tools.\u003c/p\u003e \u003cp\u003eThis study has several limitations. First, the inherent non-specificity of hematological parameters in differentiating pulmonary pathogens, and substantial interpatient physiological variability. Second, the retrospective design inherently limits data completeness and introduces potential confounding variables that could not be controlled for during analysis. Finally, while our findings provide preliminary evidence, the relatively modest sample size may affect the generalizability of the models, warranting validation through larger, prospective multicenter studies.\u003c/p\u003e \u003cp\u003eOur results validate both the generalizability and diagnostic efficacy of our model while demonstrating its potential for broader implementation in respiratory pathogen detection. The inherent adaptability of our model renders it a robust diagnostic tool capable of dynamically integrating novel epidemiological and clinical data, thereby addressing the evolving challenges in respiratory pathogen identification and differentiation.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eEthics statement\u003c/h2\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003ch2\u003eConflicts of interest\u003c/h2\u003e\n\u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e\n\u003ch2\u003eFunding\u003c/h2\u003e\n\u003cp\u003eThis work is funded by Guangdong Provincial Center for Disease Control and Prevention Supports Talent Projects (0720240122); Noncommunicable Chronic Diseases-National Science and Technology Major Project (2024ZD0533100 \u0026amp; 2024ZD0533106); Basic and Applied Basic Research Foundation of Guangdong Province (2023A1515012526 \u0026amp; 2024A1515012332).\u003c/p\u003e\n\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\n\u003cp\u003eJP, XL and GH were involved in data collection. QY and BX analyzed the data and prepared manuscript draft. PC, WL, YC designed the study and revised the manuscript. All the participating authors read and approved the submitted manuscript.\u003c/p\u003e\n\u003ch2\u003eAcknowledgements\u003c/h2\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003ch2\u003eData Availability\u003c/h2\u003e\n\u003cp\u003eThe original contributions presented in the study are included in the article. Further inquiries can be directed to the corresponding author.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eRhoads, S., Maloney, J., Mantha, A., Van Hook, R. \u0026amp; Henao-Mart\u0026iacute;nez, A. F. Pneumocystis jirovecii Pneumonia in HIV-Negative, Non-transplant Patients: Epidemiology, Clinical Manifestations, Diagnosis, Treatment, and Prevention. \u003cem\u003eCurr. Fungal Infect. Rep.\u003c/em\u003e \u003cb\u003e18\u003c/b\u003e, 125\u0026ndash;135. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s12281-024-00482-8\u003c/span\u003e\u003cspan address=\"10.1007/s12281-024-00482-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSalzer, H. J. F. et al. Clinical, Diagnostic, and Treatment Disparities between HIV-Infected and Non-HIV-Infected Immunocompromised Patients with Pneumocystis jirovecii Pneumonia. \u003cem\u003eRespiration\u003c/em\u003e \u003cb\u003e96\u003c/b\u003e, 52\u0026ndash;65. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1159/000487713\u003c/span\u003e\u003cspan address=\"10.1159/000487713\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYu, S., Yang, T. \u0026amp; Non -HIV Immunocompetent Patient with COVID-19 and Severe Pneumocystis jirovecii Pneumonia Co-Infection. \u003cem\u003eEmerg. Infect. Dis.\u003c/em\u003e \u003cb\u003e30\u003c/b\u003e, 1948\u0026ndash;1952. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3201/eid3009.240615\u003c/span\u003e\u003cspan address=\"10.3201/eid3009.240615\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGioia, F., Albasata, H. \u0026amp; Hosseini-Moghaddam, S. M. Concurrent Infection with SARS-CoV-2 and Pneumocystis jirovecii in Immunocompromised and Immunocompetent Individuals. \u003cem\u003eJ. Fungi (Basel)\u003c/em\u003e. \u003cb\u003e8\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/jof8060585\u003c/span\u003e\u003cspan address=\"10.3390/jof8060585\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMorris, A. \u0026amp; Norris, K. A. Colonization by Pneumocystis jirovecii and its role in disease. \u003cem\u003eClin. Microbiol. Rev.\u003c/em\u003e \u003cb\u003e25\u003c/b\u003e, 297\u0026ndash;317. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1128/cmr.00013-12\u003c/span\u003e\u003cspan address=\"10.1128/cmr.00013-12\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2012).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCa\u0026ntilde;as-Arboleda, A. et al. Colonization by Pneumocystis jirovecii in patients with chronic obstructive pulmonary disease: association with exacerbations and lung function status. \u003cem\u003eBraz J. Infect. Dis.\u003c/em\u003e \u003cb\u003e23\u003c/b\u003e, 352\u0026ndash;357. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.bjid.2019.08.008\u003c/span\u003e\u003cspan address=\"10.1016/j.bjid.2019.08.008\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi, S. et al. Study on mNGS Technique in Diagnosing Pneumocystis jirovecii Pneumonia in Non-HIV-Infected Patients. \u003cem\u003eInfect. Drug Resist.\u003c/em\u003e \u003cb\u003e17\u003c/b\u003e, 1397\u0026ndash;1405. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2147/idr.S450878\u003c/span\u003e\u003cspan address=\"10.2147/idr.S450878\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDamiani, C. et al. Combined quantification of pulmonary Pneumocystis jirovecii DNA and serum (1-\u0026gt;3)-β-D-glucan for differential diagnosis of pneumocystis pneumonia and Pneumocystis colonization. \u003cem\u003eJ. Clin. Microbiol.\u003c/em\u003e \u003cb\u003e51\u003c/b\u003e, 3380\u0026ndash;3388. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1128/jcm.01554-13\u003c/span\u003e\u003cspan address=\"10.1128/jcm.01554-13\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2013).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMatsumura, Y. et al. Quantitative real-time PCR and the (1\u0026rarr;3)-β-D-glucan assay for differentiation between Pneumocystis jirovecii pneumonia and colonization. \u003cem\u003eClin. Microbiol. Infect.\u003c/em\u003e \u003cb\u003e18\u003c/b\u003e, 591\u0026ndash;597. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/j.1469-0691.2011.03605.x\u003c/span\u003e\u003cspan address=\"10.1111/j.1469-0691.2011.03605.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2012).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDesoubeaux, G. et al. Combination of β-(1, 3)-D-glucan testing in serum and qPCR in nasopharyngeal aspirate for facilitated diagnosis of Pneumocystis jirovecii pneumonia. \u003cem\u003eMycoses\u003c/em\u003e \u003cb\u003e62\u003c/b\u003e, 1015\u0026ndash;1022. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/myc.12997\u003c/span\u003e\u003cspan address=\"10.1111/myc.12997\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEsteves, F. et al. Diagnosis of Pneumocystis pneumonia: evaluation of four serologic biomarkers. \u003cem\u003eClin. Microbiol. Infect.\u003c/em\u003e \u003cb\u003e21\u003c/b\u003e, 379e371\u0026ndash;379e310. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.cmi.2014.11.025\u003c/span\u003e\u003cspan address=\"10.1016/j.cmi.2014.11.025\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2015).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJiang, Y. et al. Clinical Characteristics and Prognosis of Patients With Severe Pneumonia With Pneumocystis jirovecii Colonization: A Multicenter, Retrospective Study. \u003cem\u003eChest\u003c/em\u003e \u003cb\u003e167\u003c/b\u003e, 54\u0026ndash;66. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.chest.2024.07.140\u003c/span\u003e\u003cspan address=\"10.1016/j.chest.2024.07.140\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2025).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang, F. et al. TT@MHA: A machine learning-based webpage tool for discriminating thalassemia trait from microcytic hypochromic anemia patients. \u003cem\u003eClin. Chim. Acta\u003c/em\u003e. \u003cb\u003e545\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.cca.2023.117368\u003c/span\u003e\u003cspan address=\"10.1016/j.cca.2023.117368\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003e1 Zhang, F. et al. Enhancing thalassemia gene carrier identification in non-anemic populations using artificial intelligence erythrocyte morphology analysis and machine learning. \u003cem\u003eEur. J. Haematol.\u003c/em\u003e \u003cb\u003e112\u003c/b\u003e, 692\u0026ndash;700. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/ejh.14160\u003c/span\u003e\u003cspan address=\"10.1111/ejh.14160\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi, X., Xiong, X., Liang, Z. \u0026amp; Tang, Y. A machine learning diagnostic model for Pneumocystis jirovecii pneumonia in patients with severe pneumonia. \u003cem\u003eIntern. Emerg. Med.\u003c/em\u003e \u003cb\u003e18\u003c/b\u003e, 1741\u0026ndash;1749. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s11739-023-03353-1\u003c/span\u003e\u003cspan address=\"10.1007/s11739-023-03353-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLian, Q. et al. Alterations of lung microbiota in lung transplant recipients with pneumocystis jirovecii pneumonia. \u003cem\u003eRespir Res.\u003c/em\u003e \u003cb\u003e25\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12931-024-02755-9\u003c/span\u003e\u003cspan address=\"10.1186/s12931-024-02755-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSayson, S. G., Ashbaugh, A., Porollo, A., Smulian, G. \u0026amp; Cushion, M. T. Pneumocystis murina promotes inflammasome formation and NETosis during Pneumocystis pneumonia. \u003cem\u003emBio\u003c/em\u003e \u003cb\u003e15\u003c/b\u003e, e0140924. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1128/mbio.01409-24\u003c/span\u003e\u003cspan address=\"10.1128/mbio.01409-24\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim, S. J. et al. Prognostic factors of Pneumocystis jirovecii pneumonia in patients without HIV infection. \u003cem\u003eJ. Infect.\u003c/em\u003e \u003cb\u003e69\u003c/b\u003e, 88\u0026ndash;95. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jinf.2014.02.015\u003c/span\u003e\u003cspan address=\"10.1016/j.jinf.2014.02.015\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2014).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBateman, M., Oladele, R. \u0026amp; Kolls, J. K. Diagnosing Pneumocystis jirovecii pneumonia: A review of current methods and novel approaches. \u003cem\u003eMed. Mycol.\u003c/em\u003e \u003cb\u003e58\u003c/b\u003e, 1015\u0026ndash;1028. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/mmy/myaa024\u003c/span\u003e\u003cspan address=\"10.1093/mmy/myaa024\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhan, Y. et al. Development and Evaluation of Rapid and Accurate CRISPR/Cas13-Based RNA Diagnostics for Pneumocystis jirovecii Pneumonia. \u003cem\u003eFront. Cell. Infect. Microbiol.\u003c/em\u003e \u003cb\u003e12\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fcimb.2022.904485\u003c/span\u003e\u003cspan address=\"10.3389/fcimb.2022.904485\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoreno, A., Epstein, D., Budvytiene, I. \u0026amp; Banaei, N. Accuracy of Pneumocystis jirovecii Plasma Cell-Free DNA PCR for Noninvasive Diagnosis of Pneumocystis Pneumonia. \u003cem\u003eJ. Clin. Microbiol.\u003c/em\u003e \u003cb\u003e60\u003c/b\u003e, e0010122. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1128/jcm.00101-22\u003c/span\u003e\u003cspan address=\"10.1128/jcm.00101-22\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSzydłowicz, M. \u0026amp; Matos, O. Pneumocystis pneumonia in the COVID-19 pandemic era: similarities and challenges. \u003cem\u003eTrends Parasitol.\u003c/em\u003e \u003cb\u003e37\u003c/b\u003e, 859\u0026ndash;862. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.pt.2021.07.010\u003c/span\u003e\u003cspan address=\"10.1016/j.pt.2021.07.010\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePeng, J. et al. Successful treatment of a kidney transplant patient with COVID-19 and late-onset Pneumocystis jirovecii pneumonia. \u003cem\u003eAnn. Clin. Microbiol. Antimicrob.\u003c/em\u003e \u003cb\u003e20\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12941-021-00489-w\u003c/span\u003e\u003cspan address=\"10.1186/s12941-021-00489-w\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYehouenou Tessi, R. T. et al. An etiology of ground - glass images during COVID-19: Pneumocystis jiroveci pneumonia. \u003cem\u003eSAGE Open. Med. Case Rep.\u003c/em\u003e \u003cb\u003e10\u003c/b\u003e, 2050313x221091391. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/2050313x221091391\u003c/span\u003e\u003cspan address=\"10.1177/2050313x221091391\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXing, F. et al. Rapid Diagnosis of Pneumocystis jirovecii Pneumonia and Respiratory Tract Colonization by Next-Generation Sequencing. \u003cem\u003eMycopathologia\u003c/em\u003e \u003cb\u003e189\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s11046-024-00849-y\u003c/span\u003e\u003cspan address=\"10.1007/s11046-024-00849-y\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu, L., Yuan, M., Shi, Y. \u0026amp; Su, X. Clinical Performance of BAL Metagenomic Next-Generation Sequence and Serum (1,3)-β-D-Glucan for Differential Diagnosis of Pneumocystis jirovecii Pneumonia and Pneumocystis jirovecii Colonisation. \u003cem\u003eFront. Cell. Infect. Microbiol.\u003c/em\u003e \u003cb\u003e11\u003c/b\u003e, 784236. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fcimb.2021.784236\u003c/span\u003e\u003cspan address=\"10.3389/fcimb.2021.784236\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLind, A. P. \u0026amp; Anderson, P. C. Predicting drug activity against cancer cells by random forest models based on minimal genomic information and chemical properties. \u003cem\u003ePLoS One\u003c/em\u003e. \u003cb\u003e14\u003c/b\u003e, e0219774. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1371/journal.pone.0219774\u003c/span\u003e\u003cspan address=\"10.1371/journal.pone.0219774\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZeng, J. et al. Development of a machine learning model to predict early recurrence for hepatocellular carcinoma after curative resection. \u003cem\u003eHepatobiliary Surg. Nutr.\u003c/em\u003e \u003cb\u003e11\u003c/b\u003e, 176\u0026ndash;187. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.21037/hbsn-20-466\u003c/span\u003e\u003cspan address=\"10.21037/hbsn-20-466\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHughes, K. R., Biagini, G. A. \u0026amp; Craig, A. G. Continued cytoadherence of Plasmodium falciparum infected red blood cells after antimalarial treatment. \u003cem\u003eMol. Biochem. Parasitol.\u003c/em\u003e \u003cb\u003e169\u003c/b\u003e, 71\u0026ndash;78. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.molbiopara.2009.09.007\u003c/span\u003e\u003cspan address=\"10.1016/j.molbiopara.2009.09.007\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2010).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKing, I. L. et al. Intestinal helminth infection impacts the systemic distribution and function of the naive lymphocyte pool. \u003cem\u003eMucosal Immunol.\u003c/em\u003e \u003cb\u003e10\u003c/b\u003e, 1160\u0026ndash;1168. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/mi.2016.127\u003c/span\u003e\u003cspan address=\"10.1038/mi.2016.127\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSarkar, A. et al. Infection of neutrophil granulocytes with Leishmania major activates ERK 1/2 and modulates multiple apoptotic pathways to inhibit apoptosis. \u003cem\u003eMed. Microbiol. Immunol.\u003c/em\u003e \u003cb\u003e202\u003c/b\u003e, 25\u0026ndash;35. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s00430-012-0246-1\u003c/span\u003e\u003cspan address=\"10.1007/s00430-012-0246-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2013).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCarlsen, E. D. et al. Leishmania amazonensis amastigotes trigger neutrophil activation but resist neutrophil microbicidal mechanisms. \u003cem\u003eInfect. Immun.\u003c/em\u003e \u003cb\u003e81\u003c/b\u003e, 3966\u0026ndash;3974. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1128/iai.00770-13\u003c/span\u003e\u003cspan address=\"10.1128/iai.00770-13\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2013).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIhedioha, O. C. et al. Leishmania major surface components and DKK1 signalling via LRP6 promote migration and longevity of neutrophils in the infection site. \u003cem\u003eFront. Immunol.\u003c/em\u003e \u003cb\u003e15\u003c/b\u003e, 1473133. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fimmu.2024.1473133\u003c/span\u003e\u003cspan address=\"10.3389/fimmu.2024.1473133\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePasyar, N., Alborzi, A. \u0026amp; Pouladfar, G. R. Evaluation of serum procalcitonin levels for diagnosis of secondary bacterial infections in visceral leishmaniasis patients. \u003cem\u003eAm. J. Trop. Med. Hyg.\u003c/em\u003e \u003cb\u003e86\u003c/b\u003e, 119\u0026ndash;121. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4269/ajtmh.2012.11-0079\u003c/span\u003e\u003cspan address=\"10.4269/ajtmh.2012.11-0079\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2012).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKatte, J. C. et al. Procalcitonin levels in children affected by severe malaria compared to those with uncomplicated malaria in the absence of bacterial infection: a cross-sectional study. \u003cem\u003eTrop. Dis. Travel Med. Vaccines\u003c/em\u003e. \u003cb\u003e8\u003c/b\u003e (5). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s40794-022-00163-9\u003c/span\u003e\u003cspan address=\"10.1186/s40794-022-00163-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVijayan, A. L. et al. Procalcitonin: a promising diagnostic marker for sepsis and antibiotic therapy. \u003cem\u003eJ. Intensive Care\u003c/em\u003e. \u003cb\u003e5\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s40560-017-0246-8\u003c/span\u003e\u003cspan address=\"10.1186/s40560-017-0246-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKutty, G. et al. β-Glucans Are Masked but Contribute to Pulmonary Inflammation During Pneumocystis Pneumonia. \u003cem\u003eJ. Infect. Dis.\u003c/em\u003e \u003cb\u003e214\u003c/b\u003e, 782\u0026ndash;791. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/infdis/jiw249\u003c/span\u003e\u003cspan address=\"10.1093/infdis/jiw249\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2016).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChou, C. W., Lin, F. C., Tsai, H. C. \u0026amp; Chang, S. C. The importance of pro-inflammatory and anti-inflammatory cytokines in Pneumocystis jirovecii pneumonia. \u003cem\u003eMed. Mycol.\u003c/em\u003e \u003cb\u003e51\u003c/b\u003e, 704\u0026ndash;712. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3109/13693786.2013.772689\u003c/span\u003e\u003cspan address=\"10.3109/13693786.2013.772689\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2013).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKottom, T. J., Carmona, E. M. \u0026amp; Limper, A. H. Targeting CARD9 with Small-Molecule Therapeutics Inhibits Innate Immune Signaling and Inflammatory Response to Pneumocystis carinii β-Glucans. \u003cem\u003eAntimicrob. Agents Chemother.\u003c/em\u003e \u003cb\u003e64\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1128/aac.01210-20\u003c/span\u003e\u003cspan address=\"10.1128/aac.01210-20\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEndeman, H. et al. Systemic cytokine response in patients with community-acquired pneumonia. \u003cem\u003eEur. Respir J.\u003c/em\u003e \u003cb\u003e37\u003c/b\u003e, 1431\u0026ndash;1438. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1183/09031936.00074410\u003c/span\u003e\u003cspan address=\"10.1183/09031936.00074410\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2011).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePaats, M. S. et al. Local and systemic cytokine profiles in nonsevere and severe community-acquired pneumonia. \u003cem\u003eEur. Respir J.\u003c/em\u003e \u003cb\u003e41\u003c/b\u003e, 1378\u0026ndash;1385. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1183/09031936.00060112\u003c/span\u003e\u003cspan address=\"10.1183/09031936.00060112\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2013).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVogel, M. et al. Accuracy of serum LDH elevation for the diagnosis of Pneumocystis jiroveci pneumonia. \u003cem\u003eSwiss Med. Wkly.\u003c/em\u003e \u003cb\u003e141\u003c/b\u003e, w13184. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4414/smw.2011.13184\u003c/span\u003e\u003cspan address=\"10.4414/smw.2011.13184\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2011).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEsteves, F. et al. 1\u0026ndash;3)-beta-D-glucan in association with lactate dehydrogenase as biomarkers of Pneumocystis pneumonia (PcP) in HIV-infected patients. \u003cem\u003eEur. J. Clin. Microbiol. Infect. Dis.\u003c/em\u003e \u003cb\u003e33\u003c/b\u003e, 1173\u0026ndash;1180. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s10096-014-2054-6\u003c/span\u003e\u003cspan address=\"10.1007/s10096-014-2054-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2014).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSun, J. et al. Plasma IL-6/IL-10 Ratio and IL-8, LDH, and HBDH Level Predict the Severity and the Risk of Death in AIDS Patients with Pneumocystis Pneumonia. \u003cem\u003eJ Immunol Res\u003c/em\u003e 1583951, (2016). (2016). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1155/2016/1583951\u003c/span\u003e\u003cspan address=\"10.1155/2016/1583951\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen, Q. et al. Diagnostic values of BALF metagenomic next-generation sequencing, BALF real-time PCR and serum BDG for Pneumocystis jirovecii pneumonia in HIV-infected patients. \u003cem\u003eFront. Microbiol.\u003c/em\u003e \u003cb\u003e15\u003c/b\u003e, 1421660. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fmicb.2024.1421660\u003c/span\u003e\u003cspan address=\"10.3389/fmicb.2024.1421660\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen, J. et al. Application of peripheral blood routine parameters in the diagnosis of influenza and Mycoplasma pneumoniae. \u003cem\u003eVirol. J.\u003c/em\u003e \u003cb\u003e21\u003c/b\u003e, 162. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12985-024-02429-4\u003c/span\u003e\u003cspan address=\"10.1186/s12985-024-02429-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGong, X. et al. Clinical research on RSV prevention in children and pregnant women: progress and perspectives. \u003cem\u003eFront. Immunol.\u003c/em\u003e \u003cb\u003e14\u003c/b\u003e, 1329426. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fimmu.2023.1329426\u003c/span\u003e\u003cspan address=\"10.3389/fimmu.2023.1329426\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGreber, U. F. Adenoviruses - Infection, pathogenesis and therapy. \u003cem\u003eFEBS Lett.\u003c/em\u003e \u003cb\u003e594\u003c/b\u003e, 1818\u0026ndash;1827. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/1873-3468.13849\u003c/span\u003e\u003cspan address=\"10.1002/1873-3468.13849\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJacobs, S. E., Lamson, D. M., George, S., Walsh, T. J. \u0026amp; K. \u0026amp; Human rhinoviruses. \u003cem\u003eClin. Microbiol. Rev.\u003c/em\u003e \u003cb\u003e26\u003c/b\u003e, 135\u0026ndash;162. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1128/cmr.00077-12\u003c/span\u003e\u003cspan address=\"10.1128/cmr.00077-12\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2013).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen, J. et al. Epidemiological and laboratory characteristics of Omicron infection in a general hospital in Guangzhou: a retrospective study. \u003cem\u003eFront. Public. Health\u003c/em\u003e. \u003cb\u003e11\u003c/b\u003e, 1289668. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fpubh.2023.1289668\u003c/span\u003e\u003cspan address=\"10.3389/fpubh.2023.1289668\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"},{"header":"Chart","content":"\u003cp\u003eChart 1 is available in the Supplementary Files section.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Pneumocystis jirovecii pneumonia, Colonization, Random Forest, Diagnosis model, Peripheral blood parameters","lastPublishedDoi":"10.21203/rs.3.rs-8251095/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8251095/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDistinguishing \u003cem\u003ePneumocystis jirovecii\u003c/em\u003e pneumonia (PJP) from colonization (PJC) is crucial due to overlapping symptoms but different treatments. This study aims to evaluate whether peripheral blood parameters can serve as a non-invasive tool for distinguishing PJP from PJC. We retrospectively enrolled 174 patients with PJP and 61 with PJC from the First Affiliated Hospital of Sun Yat-sen University (April 2022\u0026ndash;March 2024). peripheral blood parameters were analyzed and compared between groups. Normally distributed variables were assessed using Student\u0026rsquo;s t-test, while non-parametric data were analyzed with the Wilcoxon rank-sum test. A diagnostic model was subsequently developed based on significant hematological indicators. Utilizing a significance threshold of p\u0026thinsp;\u0026lt;\u0026thinsp;0.05, red blood cell (RBC) and lymphocyte count (Lym%), while excluding neutrophil percentage (Neu%), procalcitonin (PCT), and lactic dehydrogenase (LDH) were used to build a random forest diagnostic model. The optimal XGBoost model achieved an AUC of 0.9991 internally and 0.787 in external validation. A web-based tool was developed to assist diagnosis. The findings of this study offer an effective tool for clinical practice, enabling physicians to accurately diagnose and differentiate between PJP and PJC, guiding appropriate treatment for patients.\u003c/p\u003e","manuscriptTitle":"A diagnostic model for discrimination between Pneumocystis jirovecii pneumonia and asymptomatic colonization based on multiple parameters","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-22 09:56:42","doi":"10.21203/rs.3.rs-8251095/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-19T06:25:29+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-10T11:37:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-31T22:39:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"95886542202186677080331309207644384238","date":"2025-12-18T07:29:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"220278762992744376185189428549596806789","date":"2025-12-16T21:02:55+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-16T20:48:21+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-16T20:45:51+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-12-09T15:24:46+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-08T17:42:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-12-08T17:33:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"cc76b98f-adea-4164-851b-b1fa3dbf588c","owner":[],"postedDate":"December 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":59866194,"name":"Health sciences/Diseases"},{"id":59866195,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-04-27T16:12:39+00:00","versionOfRecord":{"articleIdentity":"rs-8251095","link":"https://doi.org/10.1038/s41598-026-48520-4","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-04-25 15:59:09","publishedOnDateReadable":"April 25th, 2026"},"versionCreatedAt":"2025-12-22 09:56:42","video":"","vorDoi":"10.1038/s41598-026-48520-4","vorDoiUrl":"https://doi.org/10.1038/s41598-026-48520-4","workflowStages":[]},"version":"v1","identity":"rs-8251095","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8251095","identity":"rs-8251095","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}