{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T10:41:28Z","timestamp":1769596888650,"version":"3.49.0"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T00:00:00Z","timestamp":1769472000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Sepsis-related liver injury (SRLI) is associated with poor prognosis and high morbidity in septic patients. Early mitigation of liver injury is crucial for improving outcomes in the critically ill. However, early detection and intervention remain challenging, due in part to the lack of effective diagnostic and screening strategies. This study aimed to apply machine learning (ML) approaches to identify significant predictors for the onset of SRLI, with the goal of facilitating early identification of high-risk patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study utilized data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, divided into training and internal validation cohorts. An additional external validation cohort consisted of 120 sepsis patients from Nanjing Jinling Hospital. We constructed seven ML models and two conventional assessment scales to predict the risk of SRLI in patients who did not meet the SRLI criteria within the first 24 h of ICU admission. The Boruta algorithm was employed for feature selection. Hyperparameter tuning was performed on the training set using grid search. Model performance was evaluated by the area under the receiver operating characteristic curve (ROC-AUC) and precision\u2013recall area under the curve (PR-AUC), along with specificity, sensitivity, accuracy, F1 score. The clinical utility of the models was evaluated using decision curve analysis. Shapley additive explanation (SHAP) was used to provide clinicians with an intuitive understanding of the machine learning model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>After applying exclusion criteria, 9,434 sepsis patients from MIMIC-IV were included for model development. The Random Forest (RF) model demonstrated superior overall predictive performance in internal validation, achieving an area under the curve of 0.867, precision\u2013recall area under the curve of 0.392. Decision curve analysis indicated the RF model provided a positive net benefit across a wide range of high risk thresholds. In the RF model, total bilirubin, international normalized ratio, sequential organ failure assessment, logistic organ dysfunction system, and prothrombin time were the most important indexes during the initial 24 hours following ICU admission, according to SHAP value. In the external validation, the RF model also outperformed all others (ROC-AUC: 0.862, PR-AUC: 0.735).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our study explored ML-based models for predicting SRLI among sepsis at an earlier stage and the performance of random forest model ranked best. The significant predictive contribution of prothrombin time highlights its potential as a key monitoring marker for early risk stratification in septic patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1649101","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:42:24Z","timestamp":1769496144000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Early risk stratification of sepsis-related liver injury via machine learning: a multicohort study"],"prefix":"10.3389","volume":"13","author":[{"given":"Xin","family":"Chen","sequence":"first","affiliation":[{"name":"Department of General Surgery, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University","place":["Nanjing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pinwen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University","place":["Nanjing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University","place":["Nanjing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University","place":["Nanjing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingbin","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University","place":["Nanjing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University","place":["Nanjing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinying","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University","place":["Nanjing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,27]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1001\/jama.2016.0287","article-title":"The third international consensus definitions for sepsis and septic shock (Sepsis-3).","volume":"315","author":"Singer","year":"2016","journal-title":"JAMA."},{"key":"B2","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s10020-023-00658-x","article-title":"Indole-3-propionic acid alleviates sepsis-associated acute liver injury by activating pregnane X receptor.","volume":"29","author":"Wang","year":"2023","journal-title":"Mol Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"547","DOI":"10.17219\/acem\/68363","article-title":"Liver dysfunction in sepsis.","volume":"27","author":"Wo\u017anica","year":"2018","journal-title":"Adv Clin Exp Med."},{"key":"B4","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1038\/nrgastro.2016.168","article-title":"Liver - guardian, modifier and target of sepsis.","volume":"14","author":"Strnad","year":"2017","journal-title":"Nat Rev Gastroenterol Hepatol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1111\/j.1872-034X.2012.01069.x","article-title":"Sepsis-associated liver injury: incidence, classification and the clinical significance.","volume":"43","author":"Kobashi","year":"2013","journal-title":"Hepatol Res."},{"key":"B6","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.cca.2022.10.004","article-title":"Clinical characteristics and construction of a predictive model for patients with sepsis related liver injury.","volume":"537","author":"Xie","year":"2022","journal-title":"Clin Chim Acta."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1097\/01.CCM.0000259462.97164.A0","article-title":"Austrian epidemiologic study on intensive care, ASDI study group. Incidence and prognosis of early hepatic dysfunction in critically ill patients\u2013a prospective multicenter study.","volume":"35","author":"Kramer","year":"2007","journal-title":"Crit Care Med."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1504223","DOI":"10.3389\/fcimb.2025.1504223","article-title":"Mechanisms of sepsis-induced acute liver injury: a comprehensive review.","volume":"15","author":"Guo","year":"2025","journal-title":"Front Cell Infect Microbiol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"670","DOI":"10.3350\/cmh.2022.0103","article-title":"Acute-on-chronic liver failure: terminology, mechanisms and management.","volume":"29","author":"Br","year":"2023","journal-title":"Clin Mol Hepatol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.4103\/2321-3868.132689","article-title":"Advances in sepsis-associated liver dysfunction.","volume":"2","author":"Wang","year":"2014","journal-title":"Burns Trauma."},{"key":"B11","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1007\/s00134-003-1731-1","article-title":"Drotrecogin alfa (activated) in the treatment of severe sepsis patients with multiple-organ dysfunction: data from the PROWESS trial.","volume":"29","author":"Dhainaut","year":"2003","journal-title":"Intens Care Med."},{"key":"B12","doi-asserted-by":"publisher","first-page":"765","DOI":"10.2147\/IJN.S394802","article-title":"An overview of drug delivery nanosystems for sepsis-related liver injury treatment.","volume":"18","author":"Lu","year":"2023","journal-title":"Int J Nanomed."},{"key":"B13","doi-asserted-by":"publisher","first-page":"e1001341","DOI":"10.1371\/journal.pmed.1001341","article-title":"New translational research provides insights into liver dysfunction in sepsis.","volume":"9","author":"Marshall","year":"2012","journal-title":"PLoS Med."},{"key":"B14","doi-asserted-by":"publisher","first-page":"8052954","DOI":"10.1155\/2020\/8052954","article-title":"Apolipoprotein A-V is a novel diagnostic and prognostic predictor in pediatric patients with sepsis: a prospective pilot study in PICU.","volume":"2020","author":"Wang","year":"2020","journal-title":"Mediators Inflammation."},{"key":"B15","doi-asserted-by":"publisher","first-page":"4846","DOI":"10.3390\/ijerph20064846","article-title":"The role of plasminogen activator inhibitor 1 in predicting sepsis-associated liver dysfunction: an observational study.","volume":"20","author":"Wo\u017anica-Niesobska","year":"2023","journal-title":"Int J Environ Res Public Health."},{"key":"B16","doi-asserted-by":"publisher","first-page":"2105","DOI":"10.1002\/hep4.1949","article-title":"Soluble factors and suppressive monocytes can predict early development of sepsis in acute-on-chronic liver failure.","volume":"6","author":"Yadav","year":"2022","journal-title":"Hepatol Commun."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1002\/(sici)1097-0258(19970815)16:153.0.co;2-v","article-title":"Interpretation of the odds ratio from logistic regression after a transformation of the covariate vector.","volume":"16","author":"Elswick","year":"1997","journal-title":"Stat Med."},{"key":"B18","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1186\/s12967-022-03364-0","article-title":"Machine learning for the prediction of acute kidney injury in patients with sepsis.","volume":"20","author":"Yue","year":"2022","journal-title":"J Transl Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1140755","DOI":"10.3389\/fimmu.2023.1140755","article-title":"Machine learning for the prediction of all-cause mortality in patients with sepsis-associated acute kidney injury during hospitalization.","volume":"14","author":"Zhou","year":"2023","journal-title":"Front Immunol."},{"key":"B20","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1186\/s12967-022-03469-6","article-title":"Clinical applications of machine learning in the survival prediction and classification of sepsis: coagulation and heparin usage matter.","volume":"20","author":"Guo","year":"2022","journal-title":"J Transl Med."},{"key":"B21","doi-asserted-by":"publisher","first-page":"104394","DOI":"10.1016\/j.ebiom.2022.104394","article-title":"Sepsis biomarkers and diagnostic tools with a focus on machine learning.","volume":"86","author":"Komorowski","year":"2022","journal-title":"eBioMedicine."},{"key":"B22","doi-asserted-by":"publisher","first-page":"648805","DOI":"10.3389\/fphar.2021.648805","article-title":"Predicting drug-induced liver injury using machine learning on a diverse set of predictors.","volume":"12","author":"Adeluwa","year":"2021","journal-title":"Front Pharmacol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1111\/jgh.16038","article-title":"Clustering using unsupervised machine learning to stratify the risk of immune-related liver injury.","volume":"38","author":"Yamamoto","year":"2023","journal-title":"J Gastroen Hepatol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1002\/hep.32655","article-title":"Machine learning models are superior to noninvasive tests in identifying clinically significant stages of NAFLD and NAFLD-related cirrhosis.","volume":"77","author":"Chang","year":"2023","journal-title":"Hepatology."},{"key":"B25","doi-asserted-by":"publisher","first-page":"E215","DOI":"10.1161\/01.cir.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals.","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation."},{"key":"B26","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1136\/gutjnl-2017-315730","article-title":"Comparison of prognostic models to predict the occurrence of colorectal cancer in asymptomatic individuals: a systematic literature review and external validation in the EPIC and UK Biobank prospective cohort studies.","volume":"68","author":"Smith","year":"2019","journal-title":"Gut."},{"key":"B27","doi-asserted-by":"publisher","first-page":"869499","DOI":"10.3389\/fphar.2022.869499","article-title":"The use of antibiotics for ventilator-associated pneumonia in the MIMIC-IV database.","volume":"13","author":"Yang","year":"2022","journal-title":"Front Pharmacol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1097\/CCM.0000000000002949","article-title":"Delay within the 3-hour surviving sepsis campaign guideline on mortality for patients with severe sepsis and septic shock.","volume":"46","author":"Pruinelli","year":"2018","journal-title":"Crit Care Med."},{"key":"B29","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1111\/jebm.12373","article-title":"Brief introduction of medical database and data mining technology in big data era.","volume":"13","author":"Yang","year":"2020","journal-title":"J Evid Based Med."},{"key":"B30","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1002\/mpr.329","article-title":"Multiple imputation by chained equations: what is it and how does it work?","volume":"20","author":"Azur","year":"2011","journal-title":"Int J Meth Psych Res."},{"key":"B31","doi-asserted-by":"publisher","first-page":"719352","DOI":"10.3389\/fped.2021.719352","article-title":"Risk identification of bronchopulmonary dysplasia in premature infants based on machine learning.","volume":"9","author":"Lei","year":"2021","journal-title":"Front Pediatr."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1174429","DOI":"10.3389\/fmed.2023.1174429","article-title":"Chinese experts\u2019 consensus on the application of intensive care big data.","volume":"10","author":"Su","year":"2023","journal-title":"Front Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1186\/s13054-019-2579-2","article-title":"Impact of post-sepsis cardiovascular complications on mortality in sepsis survivors: a population-based study.","volume":"23","author":"Wu","year":"2019","journal-title":"Crit Care."},{"key":"B34","doi-asserted-by":"publisher","first-page":"1489015","DOI":"10.3389\/fimmu.2025.1489015","article-title":"Regulatory role of S1P and its receptors in sepsis-induced liver injury.","volume":"16","author":"Wang","year":"2025","journal-title":"Front Immunol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"107596","DOI":"10.1016\/j.phrs.2025.107596","article-title":"Noncoding RNAs in sepsis-associated acute liver injury: roles, mechanisms, and therapeutic applications.","volume":"212","author":"Wang","year":"2025","journal-title":"Pharmacol Res."},{"key":"B36","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1186\/s13054-020-03327-1","article-title":"Gut-liver crosstalk in sepsis-induced liver injury.","volume":"24","author":"Sun","year":"2020","journal-title":"Crit Care."},{"key":"B37","doi-asserted-by":"publisher","first-page":"3662","DOI":"10.1038\/s41598-023-30235-5","article-title":"Development of a nomogram for predicting 90-day mortality in patients with sepsis-associated liver injury.","volume":"13","author":"Cui","year":"2023","journal-title":"Sci Rep-UK."},{"key":"B38","doi-asserted-by":"publisher","first-page":"498","DOI":"10.3109\/08830185.2014.889129","article-title":"The role of the liver in sepsis.","volume":"33","author":"Yan","year":"2014","journal-title":"Int Rev Immunol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"797363","DOI":"10.3389\/fmed.2021.797363","article-title":"Establishment and validation of a non-invasive diagnostic nomogram to identify spontaneous bacterial peritonitis in patients with decompensated cirrhosis.","volume":"8","author":"Xiang","year":"2021","journal-title":"Front Med Lausanne."},{"key":"B40","doi-asserted-by":"publisher","first-page":"2843","DOI":"10.1097\/CM9.0000000000002282","article-title":"Adjunctive sepsis therapy with aminophylline (STAP): a randomized controlled trial.","volume":"135","author":"Zhang","year":"2022","journal-title":"Chinese Med J-peking."},{"key":"B41","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/BF01709751","article-title":"The SOFA (sepsis-related organ failure assessment) score to describe organ dysfunction\/failure. On behalf of the working group on sepsis-related problems of the european society of intensive care medicine.","volume":"22","author":"Vincent","year":"1996","journal-title":"Intensive Care Med."},{"key":"B42","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1007\/s12325-019-0889-z","article-title":"SOFA score can effectively predict the incidence of sepsis and 30-day mortality in liver transplant patients: a retrospective study.","volume":"36","author":"Wang","year":"2019","journal-title":"Adv Ther."},{"key":"B43","doi-asserted-by":"publisher","first-page":"2957","DOI":"10.1001\/jama.270.24.2957","article-title":"A new simplified acute physiology score (SAPS II) based on a European\/North American multicenter study.","volume":"270","author":"Le Gall","year":"1993","journal-title":"JAMA."},{"key":"B44","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1016\/j.sjbs.2014.06.005","article-title":"Protective effects of Parinari curatellifolia flavonoids against acetaminophen-induced hepatic necrosis in rats.","volume":"21","author":"Olaleye","year":"2014","journal-title":"Saudi J Biol Sci."},{"key":"B45","doi-asserted-by":"publisher","first-page":"R158","DOI":"10.1186\/cc7157","article-title":"Incidence, organ dysfunction and mortality in severe sepsis: a Spanish multicentre study.","volume":"12","author":"Blanco","year":"2008","journal-title":"Crit Care."},{"key":"B46","doi-asserted-by":"publisher","first-page":"e0107042","DOI":"10.1371\/journal.pone.0107042","article-title":"Disaggregating census data for population mapping using random forests with remotely-sensed and ancillary data.","volume":"10","author":"Stevens","year":"2015","journal-title":"PLoS One."},{"key":"B47","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1007\/s40121-022-00671-3","article-title":"Explainable machine-learning model for prediction of in-hospital mortality in septic patients requiring intensive care unit readmission.","volume":"11","author":"Hu","year":"2022","journal-title":"Infect Dis Ther."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1649101\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:42:28Z","timestamp":1769496148000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1649101\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,27]]},"references-count":47,"alternative-id":["10.3389\/fmed.2026.1649101"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1649101","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,27]]},"article-number":"1649101"}}