A machine learning-based prediction model for poor prognosis in sepsis using lymphocyte count: a national, multicenter prospective cohort.

Background: Sepsis, a life-threatening organ dysfunction caused by deregulation of body response to an infection with a high mortality rate. Pro-inflammatory cytokines are related to early mortality related sepsis, and immune dysfunction and suppression characterized by lymphocyte loss are related to late mortality. Persistent lymphopenia is a good biomarker for immunosuppression and predicts mortality in sepsis patients. Lymphocyte counts are easily measured and cheaper than other inflammation marker for sepsis. Aims: The objective of this study was to determine whether persistent lymphopenia has a predictive value for mortality in septic patients at Dr. Sardjito General Hospital. Methods: This study was a retrospective cohort study, sepsis and lymphogenic patients admitted to Internal Medicine ward between January 1, 2016 and December 31, 2017. Lymphocytes were count at day 1 and 4 following the diagnosis of sepsis. Persistent lymphopenia was defined as an absolute lymphocyte count of 1.62x10/μL or less on day 4. The primary outcome was mortality at the end of hospitalization. Results: 126 adult patients, 101 with persistent lymphopenia, 25 non-persistent lymphopenia, 47 patients died (37.3%). Patients with persistent lymphopenia significantly at risk of death (P=0.003, OR 5.66, 95% CI 1.59-20.13) than non-persistent lymphopenia. Logistic regression was used to account for potential confounding factors, persistent lymphopenia (p = 0.003, OR 8.01, 95% CI 2.04-31.45) and skin and soft tissue infection (p= 0.017, OR 2.94, 95% CI 1.21-7.14) were significantly associated with mortality in sepsis patients at Dr. Sardjito General Hospital. Conclusion: Persistent lymphopenia predicts mortality in adult patients with sepsis at Dr. Sardjito GeneralHospital.

Development and validation of interpretable machine learning models for predicting long-term functional outcomes in elderly patients with aneurysmal subarachnoid hemorrhage.

Sepsis is a severe complication in leukemia patients, contributing to high mortality rates. Identifying early predictors of sepsis is crucial for timely intervention. This study aimed to develop and validate a predictive model for sepsis risk in leukemia patients using machine learning techniques. This retrospective study included 4310 leukemia patients admitted to the Affiliated Hospital of Guangdong Medical University from 2005 to 2024, using 70% for training and 30% for validation. Feature selection was performed using univariate logistic regression, LASSO, and the Boruta algorithm, followed by multivariate logistic regression analysis. Seven machine learning models were constructed and evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Shapley additive explanations (SHAP) were applied to interpret the results, and restricted cubic spline (RCS) regression explored the nonlinear relationships between variables and sepsis risk. Furthermore, we examined the interactions among predictors to better understand their potential interrelationships. The random forest (RF) model outperformed all others, achieving an AUC of 0.765 in the training cohort and 0.700 in the validation cohort. Key predictors of sepsis identified by SHAP analysis included C-reactive protein (CRP), procalcitonin (PCT), neutrophil count (Neut), lymphocyte count (Lymph), thrombin time (TT), red blood cell count (RBC), total bile acid (TBA), and systolic blood pressure (SBP). RCS analysis revealed significant non-linear associations between CPR, PCT, Neut, Lymph, TT, RBC and SBP with sepsis risk. Pairwise correlation analysis further revealed interactions among these variables. The RF model exhibited robust predictive power for sepsis in leukemia patients, providing clinicians with a valuable tool for early risk assessment and the optimization of treatment strategies.

Sepsis triggers immune responseboth pro-inflammatory and anti-inflammatory. Lymphocytes play an important role in the regulation of the inflammatory response. The decrease in lymphocyte numbers due to continuous apoptosis by sepsiscan suppress the immune system and failure to resolve inflammation. Persistent lymphopenia is also associated with a poor prognosis of sepsis. Currently, there are limited studies about persistent lymphopenia in sepsis patients in low- and middle-income countries, including Indonesia. This study aimed to describe the sociodemographic, clinical, and laboratory patterns of sepsis patients with persistent lymphopenia. This was a descriptive study that analyzed patients’ medical records who were treated at the Department of Internal Medicine, Dr. Sardjito General Hospital, Yogyakarta from January 1st, 2016, to December 31th, 2017. Patients diagnosed with clinical sepsis and persistent lymphopenia were included in the study. The status of persistent lymphopenia was described as lymphocyte counts that remained low or lower (<1.62x103/L) on day 4± 24 h compared to the initial value at the time of sepsis diagnosis (day one). Information of patients’ individual and clinical characteristics, complete blood cell count profiles and culture results were included. The outcomes of interest were the survival status and length of stay of the patients. A total of 101 patients with sepsis and persistent lymphopenia were involved in this study. The average increase in lymphocyte numbers was 73.63 ± 426.86/µL. The main source of infection was pulmonary infection, with a mortality rate of 43.6% and a median survival of 19 days. The average length of stay was 13.1±6.8. Persistent lymphopenia in patients with sepsis has a high mortality. Further research is needed to determine the clinical ramifications of persistent lymphopenia.

Cerebral Toxoplasmosis in a Patient with Prolonged CD4 Lymphopenia Post Autologous Haematopoietic Stem Cell Transplant

Objective To investigate the value of multiple inflammatory cells and clinical score in early diagnosis and prognosis assessment of trauma sepsis risks. Methods This retrospective control study enrolled 209 severe trauma patients admitted from January 2010 and May 2016. White blood cell count, lymphocyte count and percentage, monocyte count and percentage, neutrophil count and percentage, ratio of neutrophil to lymphocyte count (N/L), acute physiology and chronic health evaluation (APACHE) Ⅱ score, sequential organ failure assessment (SOFA), improved early warning score (MEWS), Glasgow coma score (GCS), multiple organ dysfunction syndrome (MODS) score and lactic acid (LAC) were collected on the day of admission and 3, 5, 7 days after trauma. These data were applied to construct weighted and biological score models for early diagnosis and prognosis of traumatic sepsis. Receiver operating characteristic curve (ROC) was performed and area under the curve (AUC) was calculated to measure the value of the two models in early diagnosis and prognosis of sepsis. Results AUC of the weighted model combined by APACHE Ⅱ score, SOFA score and MEWS was 0.729 on the day of admission. AUC of the weighted model combined by inflammatory cells was 0.680 and AUC of the biological score model was 0.800 3 days after trauma (P 0.05). AUC of the biological score model had significant difference 3 days and 5 days after trauma (P<0.05). Of the weighted model combined by APACHE Ⅱ score, MODS score, GCS and LAC to evaluate the prognosis of sepsis, the AUC showed significant difference on the day of admission (0.838), 3 days after trauma (0.878), 5 days after trauma (0.947) and 7 days after trauma (0.936) (P<0.05). Conclusions Biological score possesses better effect on early diagnosis of sepsis 3 days after trauma. Weighted model combined by APACHE Ⅱ score, MODS score, GCS and LAC can effectively predict the prognosis of sepsis 5 days after trauma. Key words: Sepsis; Diagnosis, differential; Prognosis

The high incidence of Gleason score upgrade (GSU) can lead urologists to underestimate tumor aggressiveness, resulting in suboptimal treatment decisions. This study aimed to develop an interpretable machine learning model to predict the risk of GSU in individuals with prostate cancer (PCa) based on readily available clinical parameters. A retrospective analysis was conducted on patients who underwent radical prostatectomy (RP) at Shanghai General Hospital and West China Hospital. Data from Shanghai General Hospital were categorized into a training set (80%) and a test set (20%), while data from West China Hospital were used for external validation. Preoperative clinical and pathological data were collected. Nine machine learning models [including random forest (RF) and light gradient boosting machine (LightGBM)], were developed, and the model demonstrating the best predictive performance was selected as the final model. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, decision curves, and SHapley Additive exPlanations (SHAP) interpretation. The LightGBM model demonstrated strong predictive performance, achieving an area under the ROC curve of 84.53% in the test set and 76.61% in external validation. Significant factors associated with GSU included the International Society of Urological Pathology (ISUP) grade, age, clinical tumor stage (T stage), body mass index, prostate-specific antigen (PSA), free-to-total PSA ratio (f/t PSA), platelet-to-lymphocyte ratio (PLR), and bilateral tumor involvement. An online prediction tool was developed based on this model. A machine learning model and an online prediction tool were developed to accurately predict GSU and identify factors associated with this process. This approach may assist clinicians in identifying individuals at high-risk for GSU and facilitating evidence-based treatment decisions.

Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method

Asthma is a prevalent chronic respiratory disease with significant morbidity and healthcare burden. Identifying novel biomarkers for asthma risk prediction is crucial for early intervention and personalized management. The monocyte-to-high-density lipoprotein cholesterol ratio (MHR) has emerged as a potential inflammatory marker in various chronic diseases. This study aimed to investigate the association between MHR and asthma risk using data from the National Health and Nutrition Examination Survey (NHANES) and to develop a predictive model for asthma risk incorporating MHR and other clinical variables. Data from NHANES (2001-2018) were used. Weighted logistic regression was employed to assess the relationship between MHR and asthma risk. Participants were randomly divided into training (70%) and validation (30%) cohorts. The Boruta algorithm was used to evaluate the training cohort, select the best model, and identify potential confounding factors. A nomogram-based predictive model was constructed using variables selected by the Boruta algorithm [smoke, age, hypertension, cardiovascular disease (CVD), marital status, gender, race, poverty-income ratio (PIR), body mass index (BMI), cancer, education, diabetes, and MHR]. The model's performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) curves. The variables selected by Boruta algorithm are included in the machine learning (ML) model for analysis. SHAP (SHapley Additive exPlanations) analysis was performed to assess the contribution of each variable. A total of 28,855 participants were included after excluding those with missing data. MHR was positively associated with asthma incidence (P < 0.05). The Boruta algorithm achieved an AUC of 0.64 in the validation cohort. Among the ML models, the Xgboost model demonstrated the best performance with an AUC of 0.640 (95% CI 0.623-0.656). SHAP analysis identified CVD as the most influential factor, followed by age, BMI, PIR, and gender. This study demonstrates a positive association between the MHR and asthma risk, indicating a significant cross-sectional relationship. The nomogram-based predictive model incorporating MHR and other clinical variables showed moderate discriminative ability.

Sepsis is a severe systemic inflammatory response, typically triggered by infection. When the body's response to infection becomes dysregulated, it can result in organ dysfunction, tissue damage, and even death. Sepsis can affect people of all ages, but older adults, individuals with weakened immune systems, and those with chronic illnesses are at greater risk. Timely diagnosis and immediate intervention are essential to enhance the chances of survival. This study aims to develop a mortality risk prediction model for sepsis patients utilizing tree-based ensemble classifiers, with post-hoc interpretation through Shapley Additive Explanations (SHAP), to support clinical decision-making. Clinical data of sepsis patients admitted to the intensive care unit (ICU) of the First Affiliated Hospital of Xinjiang Medical University were collected. The mice package was used to handle missing data, and the Synthetic Minority Oversampling Technique(SMOTE) algorithm was applied to oversample the minority class to address data imbalance. We applied seven models, including Random Forest(RF), k-Nearest Neighbors(KNN), Support Vector Machine (SVM), logistic regression, eXtreme Gradient Boosting (XGBoost), Logistic_Lasso Regression (Logistic_Lasso), and Light Gradient Boosting Machine (LightGBM), and compared their prediction performance using the area under the receiver operating characteristic curve (AUC), Precision-Recall Curve (PR), and Decision Curve Analysis (DCA). Based on these models, we applied both global and local interpretation approaches to elucidate model predictions and explore prognostic risk factors in sepsis patients. The RF model showed the best performance among the seven Machine Learning (ML) models, achieving an AUC of 0.9816. Both global and local explainability techniques were applied to interpret the decision-making mechanisms of the ML models. Local explanation methods can interpret how ML models make predictions for individual outcomes. Global interpretation techniques help reveal how ML models respond across the entire feature landscape.

Background: The study developed accurate explainable machine learning (ML) models for predicting first-time acute exacerbation of chronic obstructive pulmonary disease (COPD, AECOPD) at an individual level. Methods: We conducted a retrospective case–control study. A total of 606 patients with COPD were screened for eligibility using registry data from the COPD Pay-for-Performance Program (COPD P4P program) database at Changhua Christian Hospital between January 2017 and December 2019. Recursive feature elimination technology was used to select the optimal subset of features for predicting the occurrence of AECOPD. We developed four ML models to predict first-time AECOPD, and the highest-performing model was applied. Finally, an explainable approach based on ML and the SHapley Additive exPlanations (SHAP) and a local explanation method were used to evaluate the risk of AECOPD and to generate individual explanations of the model’s decisions. Results: The gradient boosting machine (GBM) and support vector machine (SVM) models exhibited superior discrimination ability (area under curve [AUC] = 0.833 [95% confidence interval (CI) 0.745–0.921] and AUC = 0.836 [95% CI 0.757–0.915], respectively). The decision curve analysis indicated that the GBM model exhibited a higher net benefit in distinguishing patients at high risk for AECOPD when the threshold probability was <0.55. The COPD Assessment Test (CAT) and the symptom of wheezing were the two most important features and exhibited the highest SHAP values, followed by monocyte count and white blood cell (WBC) count, coughing, red blood cell (RBC) count, breathing rate, oral long-acting bronchodilator use, chronic pulmonary disease (CPD), systolic blood pressure (SBP), and others. Higher CAT score; monocyte, WBC, and RBC counts; BMI; diastolic blood pressure (DBP); neutrophil-to-lymphocyte ratio; and eosinophil and lymphocyte counts were associated with AECOPD. The presence of symptoms (wheezing, dyspnea, coughing), chronic disease (CPD, congestive heart failure [CHF], sleep disorders, and pneumonia), and use of COPD medications (triple-therapy long-acting bronchodilators, short-acting bronchodilators, oral long-acting bronchodilators, and antibiotics) were also positively associated with AECOPD. A high breathing rate, heart rate, or systolic blood pressure and methylxanthine use were negatively correlated with AECOPD. Conclusions: The ML model was able to accurately assess the risk of AECOPD. The ML model combined with SHAP and the local explanation method were able to provide interpretable and visual explanations of individualized risk predictions, which may assist clinical physicians in understanding the effects of key features in the model and the model’s decision-making process.

The objective of this study is to develop accurate machine learning (ML) models for predicting the neurological status at hospital discharge of critically ill patients with hemorrhagic and ischemic stroke and identify the risk factors associated with the neurological outcome of stroke, thereby providing healthcare professionals with enhanced clinical decision-making guidance. Data of stroke patients were extracted from the eICU Collaborative Research Database (eICU-CRD) for training and testing sets and the Medical Information Mart for Intensive Care IV (MIMIC IV) database for external validation. Four machine learning models, namely gradient boosting classifier (GBC), logistic regression (LR), multi-layer perceptron (MLP), and random forest (RF), were used for prediction of neurological outcome. Furthermore, shapley additive explanations (SHAP) algorithm was applied to explain models visually. A total of 1,216 hemorrhagic stroke patients and 954 ischemic stroke patients from eICU-CRD and 921 hemorrhagic stroke patients 902 ischemic stroke patients from MIMIC IV were included in this study. In the hemorrhagic stroke cohort, the LR model achieved the highest area under curve (AUC) of 0.887 in the test cohort, while in the ischemic stroke cohort, the RF model demonstrated the best performance with an AUC of 0.867 in the test cohort. Further analysis of risk factors was conducted using SHAP analysis and the results of this study were converted into an online prediction tool. ML models are reliable tools for predicting hemorrhagic and ischemic stroke neurological outcome and have the potential to improve critical care of stroke patients. The summarized risk factors obtained from SHAP enable a more nuanced understanding of the reasoning behind prediction outcomes and the optimization of the treatment strategy.

Dear Editor Pneumonia is a major cause of death worldwide, especially in aging and immunodeficient patients [1]. Common symptoms such as cough, fever, dyspnea, chest pain, and wheezes occur not only in pneumonia but also in many other illnesses. Early diagnosis of pneumonia is crucial, especially when symptoms are mild, to avoid overuse of antibiotics and prevent development of antibiotic resistance [2]. Therefore, rapid biomarkers are required to assist the initial evaluation and differentiation of low-grade pneumonia from upper respiratory infection (URI). The delta neutrophil index (DNI), an automated hematology analyzer-based marker, was recently introduced. DNI is the fraction of immature granulocytes identified automatically by the ADVIA 2120i Hematology Analyzer (Siemens Healthcare Diagnostics Inc., Erlangen, Germany). DNI is associated with the diagnosis and prognosis of sepsis [3,4]. In this study, we evaluated the diagnostic power of DNI for the differentiation of low-grade community acquired pneumonia (CAP) from URI in patients with clinically ambiguous symptoms. After obtaining approval from the institutional review board (IRB) of the Catholic Medical Center (IRB number: UC12SISI 0087), we recruited 127 patients (mean age±SD 58.3±24.2 yr, Table 1A) for the study, which was carried out from September 2013 through November 2013. The inclusion criterion for patients with low-grade CAP was low severity, according to the CURB-65 system (score 0 or 1) [5]. URI (known as the common cold) was defined as a typical acute infection involving the nose, paranasal sinuses, pharynx, larynx, and trachea without radiographic findings of pulmonary infiltrate. Patients without infection were used as the control group. Table 1 (A) Clinical characteristics and (B) receiver operating characteristics analysis of biomarkers for the prediction of low-grade CAP Total and differential leukocyte counts and DNI values were obtained with an ADVIA 2120i system. DNI was calculated with the following formula: DNI (%)=(neutrophil %+eosinophil % measured in the myeloperoxidase [MPO] channel with the cytochemical MPO reaction)-(polymorphonuclear neutrophil % measured in the nuclear lobularity channel). The level of C-reactive protein (CRP) was measured with a Hitachi 7600 Modular Chemistry Analyzer (Hitachi, Tokyo, Japan). Sputum and blood microbial cultures were performed before the start of antibiotic therapy. Among the 22 total isolates, the main CAP isolates were Staphylococcus aureus (n=9), Acinetobacter baumannii (n=4), Klebsiella pneumoniae (n=3), and Streptococcus pneumoniae (n=2). Bacteremia was found in two of 59 (3.4%) CAP patients and was not found in the URI and control groups. All of the patients recovered. The results of biomarker determination in the three groups are presented as medians (first to third interquartile range) and were analyzed by Kruskal-Wallis test (Fig. 1). DNI was the highest in the low-grade CAP group, intermediate in the URI group, and the lowest in the control group (P<0.05). CRP, DNI, and lymphocyte and monocyte counts were significantly different between the low-grade CAP and the URI and control groups (P=0.001). Lymphocyte count was significantly different between the URI group and the control group (P=0.001). No significant differences in total leukocytes were observed among the groups. Fig. 1 Medians (and first to third interquartile ranges) of the delta neutrophil index (DNI, %), C-reactive protein (CRP), white blood cell (WBC) count, neutrophil count, lymphocyte count, and monocyte count in each group (A, pneumonia; B, upper respiratory ... An ROC analysis was performed to compare the diagnostic power for discriminating low-grade CAP from URI and controls (Table 1B). CRP, lymphocyte count, and DNI showed the highest areas under the curve (AUCs) among the tested biomarkers for the prediction of CAP. The optimal cutoffs for the prediction of CAP were DNI >1.7%, CRP >1.48 mg/L, neutrophils >5.23 ×109/L, and lymphocytes ≤1.57×109/L. To investigate the diagnostic power of the combination of DNI, CRP, and lymphocyte count, we performed an ROC analysis with the following: sum of DNI %+CRP mg/L+(10 -lymphocytes [×109/L]). Compared with the individual biomarkers, the combination of DNI, CRP, and lymphocyte count had the highest AUC (0.974; see Table 1B). Furthermore, compared with the individual biomarkers, the combination of DNI and CRP had a higher AUC (0.949). DNI is provided with complete blood count without additional cost and has the advantage of being rapid, thus providing results relatively quickly. DNI showed significantly better diagnostic power in the lower-grade CAP group than in the URI and control groups. Compared with DNI, total leukocytes and neutrophils showed less diagnostic power for differentiating CAP from URI. CRP showed the highest diagnostic power among individual biomarkers for differentiating low-grade CAP from URI. The combination of CRP and DNI increased the diagnostic power than individual biomarkers. Therefore, DNI may be useful for diagnosing CAP without additional cost, prescribing appropriate treatment in patients who need antibiotics, and preventing unnecessary use of antibiotics in patients with ambiguous clinical symptoms.

Diabetic foot ulcers (DFUs) constitute a significant complication among individuals with diabetes and serve as a primary cause of nontraumatic lower-extremity amputation (LEA) within this population. We aimed to develop machine learning (ML) models to predict the risk of LEA in DFU patients and used SHapley additive explanations (SHAPs) to interpret the model. In this retrospective study, data from 1,035 patients with DFUs at Sun Yat-sen Memorial Hospital were utilized as the training cohort to develop the ML models. Data from 297 patients across multiple tertiary centers were used for external validation. We then used least absolute shrinkage and selection operator analysis to identify predictors of amputation. We developed five ML models [logistic regression (LR), support vector machine (SVM), random forest (RF), k-nearest neighbors (KNN) and extreme gradient boosting (XGBoost)] to predict LEA in DFU patients. The performance of these models was evaluated using several metrics, including the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), precision, recall, accuracy, and F1 score. Finally, the SHAP method was used to ascertain the significance of the features and to interpret the model. In the final cohort comprising 1332 individuals, 600 patients underwent amputation. Following hyperparameter optimization, the XGBoost model achieved the best amputation prediction performance with an accuracy of 0.94, a precision of 0.96, an F1 score of 0.94 and an AUC of 0.93 for the internal validation set on the basis of the 17 features. For the external validation set, the model attained an accuracy of 0.78, a precision of 0.93, an F1 score of 0.78, and an AUC of 0.83. Through SHAP analysis, we identified white blood cell counts, lymphocyte counts, and blood urea nitrogen levels as the model's main predictors. The XGBoost algorithm-based prediction model can be used to dynamically estimate the risk of LEA in DFU patients, making it a valuable tool for preventing the progression of DFUs to amputation.

BackgroundIn sepsis, the relationship between lymphocyte counts and patient outcomes is complex. Lymphocytopenia and lymphocytosis significantly influence survival, illustrating the dual functionality of lymphocytes in responding to infections. This study investigates this complex interaction, focusing on how variations in lymphocyte counts correlate with all-cause hospital mortality among sepsis patients.MethodsThis retrospective cohort study analyzed data from two extensive critical care databases: the Medical Information Mart for Intensive Care IV 2.0 (MIMIC-IV 2.0) from Beth Israel Deaconess Medical Center, Boston, Massachusetts, and the eICU Collaborative Research Database (eICU-CRD), which was Multi-center database from over 200 hospitals across the United States conducted by Philips eICU Research Institute. We included adult patients aged 18 years and older who met the Sepsis-3 criteria, characterized by documented or suspected infection and a Sequential Organ Failure Assessment (SOFA) score of 2 or higher. Sepsis patients were categorized into quartiles based on lymphocyte counts. The primary outcome was all-cause mortality in the hospital, with 90 and 60-day all-cause mortality as the secondary outcomes. Univariable and multivariable Cox proportional hazard regressions were utilized to assess lymphocyte counts' impact on hospital mortality. An adjusted restricted cubic spline (RCS) analysis was performed to elucidate this relationship further. Subgroup analyses were also conducted to explore the association across various comorbidity groups among sepsis and septic shock patients.ResultsOur study included 37,054 patients, with an observed in-hospital mortality rate of 16.6%. Univariable and multivariable Cox proportional hazard regression models showed that lymphocyte counts were independently associated with in-hospital mortality (HR = 1.04, P < 0.01; HR = 1.06, P < 0.01). RCS regression analysis revealed a U-shaped relationship between lymphocyte levels and hospital mortality risk in sepsis and septic shock patients (P for overall < 0.001, P for nonliner < 0.01; P for overall = 0.002, P for nonliner = 0.014). Subgroup analyses revealed that elevated lymphocyte counts correlated with increased hospital mortality among sepsis patients with liver disease and requiring renal replacement therapy (P for overall = 0.021, P for nonliner = 0.158; P for overall = 0.025, P for nonliner = 0.759). These findings suggest that lymphocytes may have enhanced prognostic value in specific subsets of critically ill sepsis patients.ConclusionOur findings demonstrate that lymphocyte counts are a significant independent predictor of hospital mortality in sepsis and septic shock patients. We observed a U-shaped association between lymphocyte levels and mortality risk, indicating that high and low counts are linked to increased mortality. This result highlights the complex role of lymphocytes in sepsis outcomes and suggests the need for further investigation into the underlying mechanisms and potential therapeutic approaches. Integrating lymphocyte count assessment into risk stratification algorithms and clinical decision support tools could enhance the early identification of high-risk sepsis patients.