Objective  To explore the risk factors for vancomycin-related acute kidney injury (VA-AKI) in elderly patients.

Methods  Clinical data of elderly inpatients who used vancomycin at the Inner Mongolia Autonomous Region People's Hospital from January 2021 to June 2024 were retrospectively collected. The incidence of VA-AKI and the situation of treatment drug monitoring (TDM) were statistically analyzed. LASSO regression was used for feature selection, and this process was repeated 10,000 times. In each iteration, 75% of the training samples were randomly selected, and the frequency of each feature being selected was counted. Finally, the features with higher frequency in multiple iterations were selected for model training. The data were divided into training set and test set at an 8∶2 ratio. Four machine learning prediction models, including Logistic regression, random forest, extreme gradient boosting (XGBoost), and support vector machine (SVM), were established. The accuracy and area under the receiver operating characteristic curve (AUC) of the above prediction models were calculated in the test set. The minimum depth distribution was used to visualize the importance of the characteristics of the model.

Results  A total of 305 elderly patients receiving vancomycin were included, among which 49 cases (16.07%) developed VA-AKI. LASSO regression analysis selected 7 characteristic variables to build 4 machine learning models, and finally selected the random forest model as the risk prediction model. The random forest model has an AUC value of 0.91, an accuracy of 0.89, an accuracy of 0.88, a recall rate of 0.98, and an F1 value of 0.93. The predictor importance ranking was in order of post-treatment creatinine level, C-reactive protein (CRP), albumin(Alb), respiratory failure, cardiac insufficiency, trough concentration time, and dose.

Conclusion  Post-treatment creatinine level, respiratory weakness, trough concentration time, cardiac insufficiency, Alb, CRP, and dosage were the risk factors for VA-AKI. The random forest model is the most effective in predicting the risk of VA-AKI in elderly patients, providing a reference for rational use of vancomycin in elderly patients.

1.Rybak MJ, Le J, Lodise TP, et al. Therapeutic monitoring of vancomycin for serious methicillin-resistant staphylococcus aureus infections: a revised consensus guideline and review by the American Society of health-system pharmacists, the infectious diseases society of america, the pediatric infectious diseases society, and the society of infectious diseases pharmacists[J]. Am J Health Syst Pharm, 2020, 77(11): 835-864. DOI: 10.1093/ajhp/zxaa036.

2.Mangin O, Urien S, Mainardi JL, et al. Vancomycin pharmacokinetic and pharmacodynamic models for critically ill patients with post-sternotomy mediastinitis[J]. Clin Pharmacokinet, 2014, 53(9): 849-861. DOI: 10.1007/s40262-014-0164-z.

3.Geraci JE, Heilman FR, Nichols DR, et al. Antibiotic therapy of bacterial endocarditis. VII. Vancomycin for acute micrococcal endocarditis; preliminary report[J]. Proc Staff Meet Mayo Clin, 1958, 33(7):172-181. https://pubmed.ncbi.nlm.nih.gov/13542649/.

4.何笑荣, 金鹏飞, 赵紫楠, 等. 万古霉素诱发的肾毒性及其危险因素研究进展[J]. 临床药物治疗杂志, 2017, 15(11): 5-8, 19. [He XR, Jin PF, Zhao ZN, et al. Advances in study of vancomycin-induced nephrotoxicity and its risk factors[J]. Clinical Medication Journal, 2017, 15(11): 5-8, 19.] DOI: 10.3969/j.issn.1672-3384.2017.11.002.

5.潘坤明, 马凌云, 向倩, 等. 老年人群万古霉素相关急性肾损伤现状调查及其风险因素[J]. 中国新药杂志, 2017, 26(15): 1848-1856. [Pan KM, Ma LY, Xiang Q, et al. Current situation survey and risk factors of vancomycin-associated acute kidney injury in older patients[J]. Chinese Journal of New Drugs, 2017, 26(15): 1848-1856.] https://d.wanfangdata.com.cn/periodical/ChVQZXJpb2RpY2FsQ0hJMjAyNTA2MjISD3pneHl6ejIwMTcxNTAyMhoId3RtcDVnam4%3D.

6.Topol EJ. High-performance medicine:the convergence of human and artificial intelligence[J]. Nat Med, 2019, 25(1): 44-56. DOI: 10.1038/s41591-018-0300-7.

7.Rank N, Pfahringer B, Kempfert J, et al. Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance[J]. NPJ Digit Med, 2020, 3: 139. DOI: 10.1038/s41746-020-00346-8.

8.Tseng PY, Chen YT, Wang CH, et al. Prediction of the development of acute kidney injury following cardiac surgery by machine learning[J]. Crit Care, 2020, 24(1): 478. DOI: 10.1186/s13054-020-03179-9.

9.Verwijmeren L, Bosma M, Vernooij LM, et al. Associations between preoperative biomarkers and cardiac surgery-associated acute kidney injury in elderly patients: a cohort study[J]. Anesth Analg, 2021,133(3): 570-577. DOI: 10.1213/ANE.0000000000005650.

10.Ostermann M, Bellomo R, Burdmann EA, et al. Controversies in acute kidney injury: conclusions from a kidney disease: improving global outcomes (KDIGO) conference[J]. Kidney Int, 2020, 98(2): 294-309. DOI: 10.1016/j.kint.2020.04.020.

11.王海萍, 孙晶, 王荣. 肾脏衰老与老年肾脏疾病的研究进展[J]. 老年医学研究, 2021, 2(5): 51-55. [Wang HP, Sun J, Wang R. Research progress of renal aging and senile renal disease[J]. Geriatrics Research, 2021, 2(5): 51-55.] DOI: 10.3969/j.issn.2096-9058.2021.05.010.

12.樊丽娟, 张智琪, 程晓军, 等. 机器学习辅助处方合理性预测模型在围手术期合理用药管理中的应用[J]. 药物流行病学杂志, 2024, 33(11): 1219-1228. [Fan LJ, Zhang ZQ, Cheng XJ, et al. Application of a machine learning-assisted prescription rationality prediction model in perioperative rational drug use management[J]. Chinese Journal of Pharmacoepidemiology, 2024, 33(11): 1219-1228.] DOI: 10.12173/j.issn.1005-0698.202409026.

13.郝云涛, 丁玲玲, 万艳波, 等. 急性STEMI患者pPCI术后6个月内MACE的影响因素分析及风险预测Nomogram模型构建[J]. 数理医药学杂志, 2024, 37(2): 108-118. [Hao YT, Ding LL, Wan YB, et al. Analysis of the influencing factors of MACE within 6 months after pPCI in acute STEMI patients and construction of risk prediction nomogram model[J]. Journal of Mathematical Medicine, 2024, 37(2): 108-118.] DOI: 10.12173/j.issn.1004-4337.202310106.

14.陈冰, 杨婉花. 群体药代动力学在万古霉素治疗药物监测的应用[J]. 中国临床药理学杂志, 2011, 27(9): 713-717. [Chen B,Yang WH. Application of population pharmacokinetics in the therapeutic drug monitoring of vancomycin[J]. The Chinese Journal of Clinical Pharmacology, 2011, 27(9): 713-717.] DOI: 10.3969/j.issn.1001-6821.2011.09.018.

15.徐丽, 孙鹏. 脓毒症相关急性肾损伤的诊治进展[J]. 内科急危重症杂志, 2023, 29(6): 503-505, 519. DOI: 10.11768/nkjwzzzz20230615.

16.Mohamed W, Asimakopoulos G. Preoperative C-reactive protein as a predictor of postoperative acute kidney injury in patients undergoing coronary artery bypass grafting[J]. Perfusion, 2021, 36(4): 330-337. DOI: 10.1177/0267659120947684.

17.Pegues MA, McCrory MA, Zarjou A, et al. C-reactive protein exacerbates renal ischemia-reperfusion injury[J]. Am J Physiol Renal Physiol, 2013, 304(11): F1358-F1365. DOI: 10.1152/ajprenal.00476.2012.

18.Pan KM, Wu Y, Chen C, et al. Vancomycin-induced acute kidney injury in elderly Chinese patients: a single-centre cross-sectional study[J]. Br J Clin Pharmacol, 2018, 84(8): 1706-1718. DOI: 10.1111/bcp.13594.

19.Liu Y, Yin Y, Liu XZ, et al. Retrospective analysis of vancomycin nephrotoxicity in elderly Chinese patients[J]. Pharmacology, 2015, 95(5-6): 279-284. DOI: 10.1159/000381783.

20.梁子安, 禤晓燕, 马春成, 等. 脑钠肽在鉴别肾性与肾前性急性肾损伤的应用价值探讨[J]. 中外医学研究, 2015, 13(12): 8-10. [Liang ZA, Xuan XY, Ma CC, et al. The value of brain natriuretic peptide on differential diagnosis between prerenal acute renal injury and renal acute kidney Injury[J]. Chinese and Foreign Medical Research, 2015, 13(12): 8-10.] DOI: 10.14033/j.cnki.cfmr.2015.12.004.

21.谢伟蓉, 汤敏婷, 朱文洪, 等. ICU重症患者万古霉素相关急性肾损伤危险因素分析[J]. 中国急救复苏与灾害医学杂志, 2022, 17(8): 1062-1065. [Xie WR, Tang MT, Zhu WQ, et al. Risk factors of vancomycin-related acute kidney injury in critically ill patients in ICU[J]. China Journal of Emergency Resuscitation and Disaster Medicine, 2022, 17(8): 1062-1065.] DOI: 10.3969/j.issn.1673-6966.2022.08.021.