Objective  To explore the influencing factors of rational perioperative drug use, and to establish a rationality prediction model based on machine learning to assist pharmacists in prescription review.

Methods  A retrospective analysis was conducted on the perioperative prescription data of neurosurgery patients from a tertiary hospital and a central hospital in Shanxi Province between March 2021 and March 2023. Univariate analysis and multivariate Logistic regression were initially used to identify factors influencing rational drug use, followed by Lasso regression and multicollinearity analysis to select important variables. The data was split into a training set and test set at a ratio of 7∶3, and decision tree (DT), multi-layer perceptron (MLP), extreme gradient boosting (XGBoost), support vector machine (SVM), and random forest (RF) learning models were constructed.

Results  A total of 1 500 prescriptions were included, of which 668 were classified as rational and 832 as irrational. In both the training and test sets, the AUC values of the DT, XGBoost, and RF models exceeded 0.9. The DT model showed the highest sensitivity (0.81), while the RF model demonstrated the highest specificity (0.90). In the RF model, the number of comorbidities, preoperative waiting time, total hospitalization cost, prescribing physician's title, and adverse reaction occurrence negatively impacted prescription rationality, whereas the number of drugs, age, and administration route positively influenced rationality.

Conclusion  The machine learning-based rational drug use prediction model demonstrates strong predictive performance, effectively assisting pharmacists in prescription review and helping to reduce the incidence of irrational drug use.

1.唐景财, 朱钊铭, 秦柳霄, 等. 临床药师在DRG背景下参与神经内科药事精细化管理的实践探索[J]. 中国药事, 2024, 38(5): 588-593. [Tang JC, Zhu ZM, Qin LX, et al. Exploring the practice of clinical pharmacists participating in fine management of neurology pharmacy under the background of DRG[J]. Chinese Pharmaceutical Affairs, 2024, 38(5): 588-593.] DOI: 10.16153/j.1002-7777.2024.05.011.

2.中华人民共和国卫生健康委中医药局. 关于进一步加强用药安全管理提升合理用药水平的通知（国卫医函[2022]122号）[EB/OL]. (2022-07-27) [2024-11-04]. https://www.gov.cn/zhengce/zhengceku/2022-07/30/content_5703604.htm.

3.苏艳, 文思莹, 董超. 神经外科中成药用药与处方审核的必要性[J]. 中医药管理杂志, 2024, 32(5): 99-101. DOI: 10.16690/j.cnki.1007-9203.2024.05.029.

4.李文撼. 临床药学服务对头孢菌素类药物治疗腹腔感染合理用药的影响[J]. 临床合理用药, 2024, 17(2): 133-135, 139. DOI: 10.15887/j.cnki.13-1389/r.2024. 02.039.

5.李丹滢, 邵腾飞, 李俐, 等. 临床路径中药物治疗方案的优化探索——以南京鼓楼医院帕金森病药物治疗路径为例[J]. 药物评价研究, 2023, 46(11): 2467-2473. [Li DY, Shao TF, Li L, et al. Exploration on optimization of drug treatment scheme in clinical pathway: a case study of drug treatment pathway for Parkinson's disease in Nanjing Drum Tower Hospital[J]. Drug Evaluation Research, 2023, 46(11): 2467-2473.] DOI: 10.7501/j.issn.1674-6376.2023.11.024.

6.蒋君好, 郑航, 严波. 临床药师队伍的现状、问题与建设措施[J]. 中国高等医学教育, 2024(3): 32-33, 36. DOI: 10.3969/i.issn.1002-1701.2024.03.012.

7.郑琰莉, 韩福海, 李舒玉, 等. 人工智能大模型在医疗领域的应用现状与前景展望[J]. 医学信息学杂志, 2024, 45(6): 24-29. [Zheng YL, Ham FH, Li SY, et al. Application status and prospect of artificial intelligence large models in medicine[J]. Journal of Medical Intelligence, 2024, 45(6): 24-29.] DOI: 10.3969/i.issn.1673 -6036.2024.06.005.

8.Sirocchi C, Bogliolo A, Montagna S. Medical-informed machine learning: integrating prior knowledge into medical  decision systems[J]. BMC Med Inform Decis Mak, 2024, 24(Suppl 4): 186. DOI: 10.1186/s12911-024-02582-4.

9.Tully MP, Buchan IE. Prescribing errors during hospital inpatient care: factors influencing identification by pharmacists[J]. Pharm World Sci, 2009, 31(6): 682-688. DOI: 10.1007/s11096-009-9332-x.

10.Teng X, Han K, Jin W, et al. Development and validation of an early diagnosis model for bone metastasis in non-small cell lung cancer based on serological characteristics of the bone  metastasis mechanism[J]. EClinicalMedicine, 2024, 72: 102617. DOI: 10.1016/j.eclinm.2024.102617.

11.Hu J, Xu J, Li M, et al. Identification and validation of an explainable prediction model of acute kidney  injury with prognostic implications in critically ill children: a prospective  multicenter cohort study[J]. EClinicalMedicine, 2024, 68: 102409. DOI: 10.1016/j.eclinm.2023.102409.

12.Haitovsky Y. Multicollinearity in regression analysis: comment[A]. The Review of Economics and Statistics[M]. Massachusetts, U.S.: MIT Press, 1969: 486-489. DOI: 10.2307/1926450.

13.Xiong Y, Liu YM, Hu JQ, et al. A personalized prediction model for urinary tract infections in type 2 diabetes mellitus using machine learning[J]. Front Pharmacol, 2023, 14: 1259596. DOI: 10.3389/fphar.2023.1259596.

14.王鑫, 廖彬, 李敏, 等. 融合LightGBM与SHAP的糖尿病预测及其特征分析方法[J]. 小型微型计算机系统, 2022, 43(9): 1877-1885. [Wang X, Liao B, Li M, et al. Combination of LightGBM and SHAP for diabetes prediction and feature analysis[J]. Journal of Chinese Computer Systems, 2022, 43(9): 1877-1885.] DOI: 10.20009/j.cnki.21-1106/TP.2021-0114.

15.Farrar DE, Glauber RR. Multicollinearity in regression analysis: the problem revisitedt[A]. The Review of Economics and Statistics[M]. Massachusetts, U.S.: MIT Press, 1969: 92-107. DOI: 10.2307/1937887.

16.Vatcheva KP, Lee M, McCormick JB, et al. Multicollinearity in regression analyses conducted in epidemiologic studies[J]. Epidemiology (Sunnyvale), 2016, 6(2): 227. DOI: 10.4172/2161-1165.1000227.

17.Wawruch M, Fialova D, Zikavska M, et al. Factors influencing the use of potentially inappropriate medication in older patients in Slovakia[J]. J Clin Pharm Ther, 2008, 33(4): 381-392. DOI: 10.1111/j.1365-2710.2008.00929.x.

18.倪清清, 王勇, 王娜, 等. 老年住院患者潜在不适当用药情况分析[J]. 中国临床保健杂志, 2024, 27(3): 394-398. [Ni QQ, Wang Y, Wang N, et al. Analysis of potential inappropriate medication use among elderly hospitalized patients[J]. Chinese Journal of Clinical Healthcare, 2024, 27(3): 394-398.] DOI: 10.3969/J.issn.1672-6790. 2024.03.025.