Development and validation of an XGBoost-based prediction model for acute liver injury in statin users

Published on Aug. 28, 2025Total Views: 49 times Total Downloads: 14 times Download Mobile

Author: MENG Xianglong ^1, ² YU Yuelin ^1, ² SUN Yexiang ³ SHEN Peng ³ JIANG Zhiqin ⁴ ZHU Yu ⁴ YIN Yueqi ³ ZHAN Siyan ^1, ^2, ⁵  WANG Shengfeng ^1, ^2, ⁵

Affiliation: 1. Department of Epidemiology and Biostatistics, School of Public Health, Peking University Health Science Center, Beijing 100191, China 2. Key Laboratory of Epidemiology of Major Diseases (Peking University), Ministry of Education, Beijing 100191, China 3. Department of Data Center, Yinzhou District Center for Disease Control and Prevention of Ningbo, Ningbo 315100, Zhejiang Province, China 4. Yinzhou District Health Bureau of Ningbo, Ningbo 315100, Zhejiang Province, China 5. Institude for Artificial Intelligence, Peking University, Beijing 100191, China

Keywords: Statins Acute liver injury Prediction model XGBoost algorithm Cost-sensitive learning

DOI: 10.12173/j.issn.1005-0698.202502023

Reference: MENG Xianglong, YU Yuelin, SUN Yexiang, SHEN Peng, JIANG Zhiqin, ZHU Yu, YIN Yueqi, ZHAN Siyan, WANG Shengfeng. Development and validation of an XGBoost-based prediction model for acute liver injury in statin users[J]. Yaowu Liuxingbingxue Zazhi, 2025, 34(8): 867-876. DOI: 10.12173/j.issn.1005-0698.202502023.[Article in Chinese]  Copied

Abstract
Full-text
References

Abstract

Objective To develop and validate a prediction model to identify high-risk individuals who are at-risk to develop acute liver injury (ALI) within 180 days in new statin users, and to support early clinical intervention.

Methods Data were sourced from the Yinzhou Regional Health Information Platform, covering statin initiators aged 18 years and older from January 1, 2010, to October 31, 2021. The dataset was divided into a derivation cohort and a temporal validation cohort based on the time of statin initiation. Predictors were selected using LASSO regression, and the model was constructed using the extreme gradient boosting (XGBoost) algorithm combined with cost-sensitive learning. Model performance was evaluated using Brier scores, Harrell’s C-index, and calibration curves.

Results A total of 126,440 statin initiators were included, with 90,542 in the derivation cohort and 35,898 in the validation cohort. Within 180 days of initial statin use, 412 (0.33%) patients developed ALI, including 305 (0.34%) in the derivation cohort and 107 (0.30%) in the validation cohort. The final model incorporated 16 predictors, which included demographic characteristics, lifestyle factors, family history, medical history, statin use, and concomitant medication use. The model demonstrated excellent overall performance [Brier score=0.0043, 95%CI (0.0038, 0.0049)], discrimination [Harrell’s C-index=0.761, 95%CI (0.725, 0.794)], and calibration in internal validation. In temporal validation, the model also performed well [Brier score=0.0044, 95%CI (0.0036, 0.0052), Harrell’s C-index= 0.703, 95%CI (0.614, 0.781)].

Conclusion This study develope and validate a prediction model for ALI in statin users, providing clinicians with a reliable tool for individualized risk assessment. This model can help achieve risk stratification and reduce the occurrence of ALI.

Full-text

Please download the PDF version to read the full text: download

References

1.Kim DS, Scherer PE. Obesity, diabetes, and increased cancer progression[J]. Diabetes Metab J, 2021, 45(6): 799-812. DOI: 10.4093/dmj.2021.0077.

2.中国血脂管理指南修订联合专家委员会. 中国血脂管理指南（基层版2024年）[J]. 中华心血管病杂志, 2024, 52(4): 330-337. [Joint Committee on the Chinese Guidelines for Lipid Management. Chinese guideline for lipid management (primary care version 2024)[J]. Chinese Journal of Cardiology, 2024, 52(4): 330-337.] DOI: 10.3760/cma.j.cn112148-20240102-00002.

3.Newman CB, Preiss D, Tobert JA, et al. Statin safety and associated adverse events: a scientific statement from the American Heart Association[J]. Arterioscler Thromb Vasc Biol, 2019, 39(2): e38-e81. DOI: 10.1161/atv.0000000000000073.

4.韦诗友, 郑莉. 他汀类药物在老年患者临床应用安全性的评价进展[J]. 华西医学, 2017, 32(2): 290-297. DOI: 10.7507/1002-0179.201507088.

5.Björnsson E, Jacobsen EI, Kalaitzakis E. Hepatotoxicity associated with statins: reports of idiosyncratic liver injury post-marketing[J]. J Hepatol, 2012, 56(2): 374-380. DOI: 10.1016/j.jhep.2011.07.023.

6.Law M, Rudnicka AR. Statin safety: a systematic review[J]. Am J Cardiol, 2006, 97(8a): 52c-60c. DOI: 10.1016/j.amjcard. 2005.12.010.

7.孔飞飞, 谭兴起, 郭良君. 阿托伐他汀钙致肝功能异常[J]. 药物流行病学杂志, 2011, 20(5): 267-267. DOI: 10.19960/j.cnki.issn1005-0698.2011.05.022.

8.他汀类药物安全性评价工作组. 他汀类药物安全性评价专家共识[J]. 中华心血管病杂志, 2014, 42(11): 890-894. [Working Group of the Evaluation on the Safety of Statins. Experts consensus of the evaluation on the statin drugs safty[J]. Chinese Journal of Cardiology, 2014, 42(11): 890-894.] DOI: 10.3760/cma.j.issn.0253-3758.2014.11.002.

9.Wang B, Huang S, Li S, et al. Hepatotoxicity of statins: a real-world study based on the US Food and Drug Administration Adverse Event Reporting System database[J]. Front Pharmacol, 2024, 15: 1502791. DOI: 10.3389/fphar.2024.1502791.

10.Horodinschi RN, Stanescu AMA, Bratu OG, et al. Treatment with statins in elderly patients[J]. Medicina (Kaunas), 2019, 55(11): 721. DOI: 10.3390/medicina55110721.

11.Björnsson ES. Hepatotoxicity of statins and other lipid-lowering agents[J]. Liver Int, 2017, 37(2): 173-178. DOI: 10.1111/liv. 13308.

12.Allen RM, Marquart TJ, Albert CJ, et al. miR-33 controls the expression of biliary transporters, and mediates statin- and diet-induced hepatotoxicity[J]. EMBO Mol Med, 2012, 4(9): 882-895.DOI: 10.1002/emmm.201201228.

13.Cooper-DeHoff RM, Niemi M, Ramsey LB, et al. The clinical pharmacogenetics implementation consortium guideline for SLCO1B1, ABCG2, and CYP2C9 genotypes and statin-associated musculoskeletal symptoms[J]. Clin Pharmacol Ther, 2022, 111(5): 1007-1021. DOI: 10.1002/cpt.2557.

14.Xiong Y, Liu X, Wang Q, et al. Machine learning-based prediction model for the efficacy and safety of statins[J]. Front Pharmacol, 2024, 15: 1334929. DOI: 10.3389/fphar.2024.1334929.

15.Lin H, Tang X, Shen P, et al. Using big data to improve cardiovascular care and outcomes in China: a protocol for the Chinese Electronic Health Records Research in Yinzhou (CHERRY) Study[J]. BMJ Open, 2018, 8(2): e019698. DOI: 10.1136/bmjopen-2017-019698.

16.赵厚宇, 柴三葆, 孙烨祥, 等. 二甲双胍与2型糖尿病患者痴呆症发病风险相关性的回顾性队列研究[J]. 中国糖尿病杂志, 2024, 32(8): 567-575. [Zhao HY, Chai SB, Sun YX, et al. Retrospective cohort study on the relationship between metformin and the risk of dementia in patients with type 2 diabetes mellitus[J]. Chinese Journal of Diabetes, 2024, 32(8): 567-575.] DOI: 10.3969/j.issn.1006-6187.2024.08.002.

17.Lund JL, Richardson DB, Stürmer T. The active comparator, new user study design in pharmacoepidemiology: historical foundations and contemporary application[J]. Curr Epidemiol Rep, 2015, 2(4): 221-228. DOI: 10.1007/s40471-015-0053-5.

18.De Vriese AS. Should statins be banned from dialysis?[J]. J Am Soc Nephrol, 2017, 28(6): 1675-1676. DOI: 10.1681/asn. 2017020201.

19.Danan G, Teschke R. Roussel uclaf causality assessment method for drug-induced liver injury: present and future[J]. Front Pharmacol, 2019, 10: 853. DOI: 10.3389/fphar.2019.00853.

20.中国医药生物技术协会药物性肝损伤防治技术专业委员会, 中华医学会肝病学分会药物性肝病学组. 中国药物性肝损伤诊治指南（2023年版）[J]. 中华肝脏病杂志, 2023, 31(4): 355-384. [Technology Committee on DILI Prevention and Management, Chinese Medical Biotechnology Association; Study Group of Drug-Induced Liver Disease, Chinese Medical Association for the Study of Liver Diseases. Chinese guideline for diagnosis and management of drug-induced liver injury (2023 version)[J]. Chinese Journal of Hepatology, 2023, 31(4): 355-384.] DOI: 10.3760/cma.j.cn501113-20230419-00176-1.

21.García-Rodríguez LA, González-Pérez A, Stang MR, et al. The safety of rosuvastatin in comparison with other statins in over 25,000 statin users in the Saskatchewan Health Databases[J]. Pharmacoepidemiol Drug Saf, 2008, 17(10): 953-961. DOI: 10.1002/pds.1602.

22.Douglas IJ, Langham J, Bhaskaran K, et al. Orlistat and the risk of acute liver injury: self controlled case series study in UK Clinical Practice Research Datalink[J]. BMJ, 2013, 346: f1936. DOI: 10.1136/bmj.f1936.

23.Falconer N, Nand S, Liow D, et al. Development of an electronic patient prioritization tool for clinical pharmacist interventions[J]. Am J Health Syst Pharm, 2014, 71(4): 311-320. DOI: 10.2146/ajhp130247.

24.Alfirevic A, Neely D, Armitage J, et al. Phenotype standardization for statin-induced myotoxicity[J]. Clin Pharmacol Ther, 2014, 96(4): 470-476. DOI: 10.1038/clpt.2014.121.

25.White IR, Royston P, Wood AM. Multiple imputation using chained equations: Issues and guidance for practice[J]. Stat Med, 2011, 30(4): 377-399. DOI: 10.1002/sim.4067.

26.Heidarian Miri H, Hassanzadeh J, Rajaeefard A, et al. Multiple imputation to correct for nonresponse bias: application in non-communicable disease risk factors survey[J]. Glob J Health Sci, 2015, 8(1): 133-142. DOI: 10.5539/gjhs.v8n1p133.

27.Mao B, Ma J, Duan S, et al. Preoperative classification of primary and metastatic liver cancer via machine learning-based ultrasound radiomics[J]. Eur Radiol, 2021, 31(7): 4576-4586. DOI: 10.1007/s00330-020-07562-6.

28.Bradic J, Fan J, Jiang J. Regularization for Cox's proportional hazards model with NP-dimensionality[J]. Ann Stat, 2011, 39(6): 3092-3120. DOI: 10.1214/11-aos911.

29.Friedman JH. Stochastic gradient boosting[J]. Comput Stat Data An, 2002, 38(4): 367-378. DOI: 10.1016/S0167-9473(01)00065-2.

30.Aldraimli M, Soria D, Grishchuck D, et al. A data science approach for early-stage prediction of patient's susceptibility to acute side effects of advanced radiotherapy[J]. Comput Biol Med, 2021, 135: 104624. DOI: 10.1016/j.compbiomed.2021.104624.

31.Pan Z, Zhang R, Shen S, et al. OWL: an optimized and independently validated machine learning prediction model for lung cancer screening based on the UK Biobank, PLCO, and NLST populations[J]. EBioMedicine, 2023, 88: 104443. DOI: 10.1016/j.ebiom.2023.104443.

32.Hosmer DW Jr LS, Sturdivant RX, eds. Applied logistic regression[M]. Hoboken: John Wiley & Sons, Inc., 2013: 117.

33.Collins GS, Reitsma JB, Altman DG, et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement[J]. BMJ, 2015, 350: g7594. DOI: 10.1136/bmj.g7594.

34.郭恒, 李丹丹, 温爱萍, 等. 9城市老年患者使用他汀类药物潜在药物相互作用分析[J]. 中南药学, 2023, 21(5): 1377-1382. [Guo H, Li DD, Wen AP, et al. Potential drug-drug interactions with statins among elderly patients in 9 cities in China[J]. Central South Pharmacy, 2023, 21(5): 1377-1382.] DOI: 10.7539/j.issn.1672-2981.2023.05.042.

35.Bytyçi I, Penson PE, Mikhailidis DP, et al. Prevalence of statin intolerance: a Meta-analysis[J]. Eur Heart J, 2022, 43(34): 3213-3223. DOI: 10.1093/eurheartj/ehac015.

36.Escobar C, Echarri R, Barrios V. Relative safety profiles of high dose statin regimens[J]. Vasc Health Risk Manag, 2008, 4(3): 525-533. DOI: 10.2147/vhrm.s2048.

37.国家药品不良反应监测中心. 国家药品不良反应监测年度报告（2022年）[J]. 中国病毒病杂志, 2023, 13(4): 245-251. [Chinese national center for adverse drug reaction monitoring. Annual report of national adverse drug reaction monitoring (2022) [J]. Chinese Journal of Viral Diseases, 2023, 13(4): 245-251.] DOI: 10.16505/j.2095-0136.2023.4003.

38.Cai T, Abel L, Langford O, et al. Associations between statins and adverse events in primary prevention of cardiovascular disease: systematic review with pairwise, network, and dose-response Meta-analyses[J]. BMJ, 2021, 374: n1537. DOI: 10.1136/bmj.n1537.

39.Kaniwa N, Saito Y. Pharmacogenomics of severe cutaneous adverse reactions and drug-induced liver injury[J]. J Hum Genet, 2013, 58(6): 317-326. DOI: 10.1038/jhg.2013.37.

40.Wang CW, Preclaro IAC, Lin WH, et al. An updated review of genetic associations with severe adverse drug reactions: translation and implementation of pharmacogenomic testing in clinical practice[J]. Front Pharmacol, 2022, 13: 886377. DOI: 10.3389/fphar.2022.886377.

41.Floyd JS, Bloch KM, Brody JA, et al. Pharmacogenomics of statin-related myopathy: Meta-analysis of rare variants from whole-exome sequencing[J]. PLoS One, 2019, 14(6): e0218115. DOI: 10.1371/journal.pone.0218115.

42.江林双, 陈茂伟. 阿托伐他汀药物性肝损伤的临床特征分析[J]. 中国全科医学, 2024, 27(30): 3772-3775, 3783. [Jiang LS, Chen MW. Clinical characteristics of liver injury induced by atorvastatin[J]. Chinese General Practice, 2024, 27(30): 3772-3775, 3783.] DOI: 10.12114/j.issn.1007-9572.2023.0698.

43.邰隽, 于淼, 张琳, 等. 基于自然语言处理技术的儿童病例注射用尖吻蝮蛇血凝酶不良反应主动监测方法构建与验证研究[J]. 中国药物警戒, 2023, 20(9): 1011-1016. [Tai J, Yu M, Zhang L. Active monitoring of adverse reactions related to haemocoagulase agkistrodon for injection in children[J]. Chinese Journal of Pharmacovigilance, 20(9): 1011-1016.] DOI: 10.19803/j.1672-8629.20220736.

44.Moons KG, Kengne AP, Grobbee DE, et al. Risk prediction models: II. External validation, model updating, and impact assessment[J]. Heart, 2012, 98(9): 691-698. DOI: 10.1136/heartjnl-2011-301247.