{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:11:19Z","timestamp":1785247879705,"version":"3.55.0"},"reference-count":46,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Therapeutic Advances in Drug Safety"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Drug-induced liver injury (DILI) is difficult to diagnose and manage in routine care because it lacks pathognomonic biomarkers and is often recognized only after clinically meaningful injury has occurred. Existing computational approaches are largely drug-centric and do not routinely incorporate patient-level clinical data available in electronic health records (EHRs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives:<\/jats:title>\n                    <jats:p>To develop and temporally validate a machine learning model for episode-level risk stratification of Roussel Uclaf Causality Assessment Method (RUCAM)-defined DILI using routinely available baseline clinical data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design:<\/jats:title>\n                    <jats:p>This was an observational cohort study conducted at Hai Phong International Hospital using linked EHR, laboratory, and pharmacy data. The final labeled cohort was partitioned chronologically at the patient level into a retrospective development cohort (2019\u20132023) and a temporally subsequent prospective validation cohort (2024\u20132025).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>Eligible drug-exposure episodes with complete baseline liver biochemistry and key exposure covariates were included. Analysis-ready episodes were monitored for biochemical liver injury triggers, and trigger-positive episodes underwent clinical review and RUCAM adjudication. DILI was defined as RUCAM \u2a7e6. Predictors were limited to baseline demographics, comorbidities, laboratory values, drug-exposure features, and FDA DILIrank 2.0 metadata. Candidate models included logistic regression, elastic-net logistic regression, random forest, ExtraTrees, XGBoost, and LightGBM.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>Among 5095 eligible episodes from 3579 patients, 2786 episodes from 2712 patients were analysis-ready after exclusions. The final labeled cohort comprised 274 DILI-positive and 2512 non-DILI episodes. The prospective validation cohort included 828 episodes, of which 108 (13.0%) were DILI-positive. Tree-based ensemble models outperformed regression-based models. Logistic regression achieved an area under the receiver operating characteristic curve (AUROC) of 0.777 and an area under the precision\u2013recall curve (PR-AUC) of 0.349, whereas the final LightGBM model achieved an AUROC of 0.965 (95% CI 0.942\u20130.983), a PR-AUC of 0.903 (95% CI 0.856\u20130.943), and a Brier score of 0.034.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>A prospectively validated machine learning model using routinely collected baseline clinical data showed excellent performance for DILI risk stratification and may strengthen hospital pharmacovigilance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20420986261467891","type":"journal-article","created":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T09:11:40Z","timestamp":1784970700000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and prospective validation of a machine learning model for risk stratification of drug-induced liver injury using real-world clinical data"],"prefix":"10.1177","volume":"17","author":[{"given":"Ngan Thi","family":"Tran","sequence":"first","affiliation":[{"name":"Faculty of Pharmacy, Hai Phong University of Medicine and Pharmacy, Hai Phong, Vietnam"},{"name":"Department of Pharmacy, Hai Phong International Hospital, Hai Phong, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tung My","family":"Pham","sequence":"additional","affiliation":[{"name":"Faculty of Pharmacy, Hai Phong University of Medicine and Pharmacy, Hai Phong, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mai Thi Quynh","family":"Ngo","sequence":"additional","affiliation":[{"name":"Faculty of Pharmacy, Hai Phong University of Medicine and Pharmacy, Hai Phong, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anh Van","family":"Tran","sequence":"additional","affiliation":[{"name":"Faculty of Pharmacy, Hai Phong University of Medicine and Pharmacy, Hai Phong, Vietnam"},{"name":"Department of Pharmacy, Hai Phong International Hospital, Hai Phong, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thu Thi Kim","family":"Ninh","sequence":"additional","affiliation":[{"name":"Faculty of Pharmacy, Hai Phong University of Medicine and Pharmacy, Hai Phong, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long Duc","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, Hai Phong International Hospital, Hai Phong, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dung Van","family":"Hoang","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Hai Phong International Hospital, Hai Phong, Vietnam"},{"name":"Department of Internal Medicine, Hai Phong University of Medicine and Pharmacy, Hai Phong, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0523-0852","authenticated-orcid":false,"given":"Phuong Thi Thu","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Faculty of Pharmacy, Hai Phong University of Medicine and Pharmacy, Hai Phong 180000, Vietnam"},{"name":"Department of Pharmacy, Hai Phong International Hospital, Hai Phong, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,7,25]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2008.09.011"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00663-0_1"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1053\/jhep.2002.34857"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2013.02.006"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1002\/hep.23937"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1038\/clpt.2011.63"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra052270"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/nrd1750"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1006\/rtph.2000.1399"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2019.02.014"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.14309\/ajg.0000000000001259"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/0895-4356(93)90101-6"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1002\/hep.22442"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0016-5085(00)70192-2"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.1002\/hep.26208"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1111\/cts.12629"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dmpk.2016.11.008"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.638410"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1111\/liv.70038"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41572-019-0105-0"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v24.i13.1373"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2016.02.015"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2024.1497397"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.2196\/29226"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-24282-3"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1002\/jcph.70131"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2024-082505"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1002\/bcp.70446"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.phrs.2023.107030"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102430"},{"key":"e_1_3_4_35_2","volume-title":"Proceedings of the 31st international conference on neural information processing systems","author":"Ke G","year":"2017","unstructured":"Ke G, Meng Q, Finley T, et al. LightGBM: a highly efficient gradient boosting decision tree. Proceedings of the 31st international conference on neural information processing systems, Long Beach, CA, USA, 2017."},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1002\/jcph.1955"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1080\/10715760410001694026"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2009.05.012"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1002\/med.21660"},{"key":"e_1_3_4_40_2","doi-asserted-by":"publisher","DOI":"10.1182\/hematology.2022000408"},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1002\/hep.21669"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2015.03.006"},{"key":"e_1_3_4_43_2","article-title":"The gamma-glutamyl transpeptidase to platelet ratio: a good noninvasive biomarker for predicting for the occurrence and prognosis of patients with hepatitis E virus-related acute liver failure","volume":"12","author":"Zhu S","year":"2025","unstructured":"Zhu S, Yuan J, Ju F, et al. The gamma-glutamyl transpeptidase to platelet ratio: a good noninvasive biomarker for predicting for the occurrence and prognosis of patients with hepatitis E virus-related acute liver failure. Front Med (Lausanne) 2025; 12: 1573114.","journal-title":"Front Med (Lausanne)"},{"key":"e_1_3_4_44_2","article-title":"Simple models based on gamma-glutamyl transpeptidase and platelets for predicting survival in hepatitis B-associated hepatocellular carcinoma","volume":"9","author":"Pang Q","year":"2016","unstructured":"Pang Q, Bi JB, Wang ZX, et al. Simple models based on gamma-glutamyl transpeptidase and platelets for predicting survival in hepatitis B-associated hepatocellular carcinoma. Onco Targets Ther 2016; 9: 2099\u20132109.","journal-title":"Onco Targets Ther"},{"key":"e_1_3_4_45_2","doi-asserted-by":"publisher","DOI":"10.21037\/tcr-21-2559"},{"key":"e_1_3_4_46_2","doi-asserted-by":"publisher","DOI":"10.1002\/hep.21095"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2019.09.022"}],"container-title":["Therapeutic Advances in Drug Safety"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20420986261467891","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20420986261467891","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20420986261467891","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T13:47:02Z","timestamp":1785246422000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20420986261467891"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":46,"alternative-id":["10.1177\/20420986261467891"],"URL":"https:\/\/doi.org\/10.1177\/20420986261467891","relation":{},"ISSN":["2042-0986","2042-0994"],"issn-type":[{"value":"2042-0986","type":"print"},{"value":"2042-0994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"article-number":"20420986261467891"}}