Construction and validation of a machine learning-based model for predicting the risk of intravenous medication

Yang Yang; Wang Hongmei; Shan Xuefeng; Xiao Mingzhao

doi:10.13406/j.cnki.cyxb.003572

您当前的位置：

首页 >

文章列表页 >

Construction and validation of a machine learning-based model for predicting the risk of intravenous medication

Clinical research | 更新时间：2025-10-23

- Construction and validation of a machine learning-based model for predicting the risk of intravenous medication
- Journal of Chongqing Medical University Vol. 49, Issue 10, Pages: 1132-1137(2024)
- 作者机构：
  
  1.重庆医科大学附属第一医院麻醉科,重庆 400016
  2.重庆医科大学附属第一医院药学部,重庆 400016
  3.重庆医科大学附属璧山医院药学部,重庆 402760
  4.重庆医科大学附属第一医院泌尿外科,重庆 400016
- 作者简介：
- 基金信息：
- DOI：10.13406/j.cnki.cyxb.003572
  CLC： R979.9
- Received：05 March 2024，
  
  Revised：2024-04-20，
  
  Accepted：23 April 2024，
  
  Published：28 October 2024
- 稿件说明：
移动端阅览
杨洋,王红梅,单雪峰,等.基于机器学习算法的静脉用药风险预测模型构建及验证[J].重庆医科大学学报,2024,49(10):1132-1137.

Yang Yang,Wang Hongmei,Shan Xuefeng,et al.Construction and validation of a machine learning-based model for predicting the risk of intravenous medication[J].Journal of Chongqing Medical University,2024,49(10):1132-1137.
杨洋,王红梅,单雪峰,等.基于机器学习算法的静脉用药风险预测模型构建及验证[J].重庆医科大学学报,2024,49(10):1132-1137. DOI： 10.13406/j.cnki.cyxb.003572.

Yang Yang,Wang Hongmei,Shan Xuefeng,et al.Construction and validation of a machine learning-based model for predicting the risk of intravenous medication[J].Journal of Chongqing Medical University,2024,49(10):1132-1137. DOI： 10.13406/j.cnki.cyxb.003572.

摘要

目的

收集患者临床信息，采用机器学习算法构建患者静脉用药风险预测模型。

方法

回顾性纳入静脉用药患者（建模组1 302例和验证组281例），采用药学监护联盟协会提出的药物相关问题V 9.09分类标准分析患者存在的药物相关问题，采用logistics回归、神经网络、CHAID决策树、贝叶斯网络、支持向量机等机器学习算法构建静脉用药风险预测模型，并采用混淆矩阵格式对各预测模型进行评价。通过准确率、召回率、精确率、F1值以及生成验证受试者工作特征曲线下面积（area under curve，AUC）评价模型的预测性能。

结果

患者药物相关问题发生率为26.9%。患者药物相关问题主要集中在治疗安全性方面（

=556，94.9%），其次是治疗有效性方面（

=30，5.1%）。构建的模型中支持向量机的预测效能最好，AUC为0.826。

结论

机器学习算法构建的静脉用药风险预测模型预测效能良好，可为静脉用药安全管理提供新思路和新方法。

Abstract

Objective

To construct a predictive model for the risk of intravenous medication using machine learning algorithms based on the clinical information of patients.

Methods

A retrospective analysis was performed for the patients receiving intravenous medication，with 1302 patients in the modeling group and 281 in the validation group. The drug-related problem classification system V9.09 proposed by the European Society of Clinical Pharmacy was used to analyze the drug-related problems in patients. Machine learning algorithms，including logistic regression，neural network，CHAID decision tree，Bayesian network，and support vector machine，were used to construct risk predictive models for intravenous medication，and confusion matrices were used to evaluate the performance of each predictive model. Accuracy，recall rate，precision，and the area under the ROC curve（AUC） for the subjects in the validation group were used to evaluate the predictive performance of the model.

Results

The incidence rate of drug-related problems was 26.9% among these patients. These drug-related problems mainly involved treatment safety（

=556，94.9%），followed by treatment effectiveness（

=30，5.1%）. Among the models constructed，support vector machine algorithm showed the best predictive performance，with an AUC of 0.826.

Conclusion

The predictive model for the risk of intravenous medication constructed using machine learning algorithms has good predictive performance，which can provide new insights and methods for the management of intravenous medication safety.

关键词

Keywords

references

国家药品监督管理总局药品评价中心，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）[EB/OL ] . （ 2023-01-12 ）[ 2024-03-03 ] . https://www.cdr-adr.org.cn/drug_1/aqjs_1/drug_aqjs_sjbg/202303/t20230324_50019.html https://www.cdr-adr.org.cn/drug_1/aqjs_1/drug_aqjs_sjbg/202303/t20230324_50019.html .

Center for drug reevaluation ， National center for ADR nonitoring ， China . National adverse drug reaction monitoring annual report （ 2022 ）[EB/OL ] . （ 2023-01-12 ）[ 2024-03-03 ] . https://www.cdr-adr.org.cn/drug_1/aqjs_1/drug_aqjs_sjbg/202303/t20230324_50019.html https://www.cdr-adr.org.cn/drug_1/aqjs_1/drug_aqjs_sjbg/202303/t20230324_50019.html .

国家药品监督管理总局药品评价中心，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（ 2021 年）[EB/OL ] . （ 2022-01-10 ）[ 2023-02-03 ] . https://www.cdr-adr.org.cn/drug_1/aqjs_1/drug_aqjs_sjbg/202203/t20220330_49586.html https://www.cdr-adr.org.cn/drug_1/aqjs_1/drug_aqjs_sjbg/202203/t20220330_49586.html .

Center for drug reevaluation ， National center for ADR nonitoring ， China . National adverse drug reaction monitoring annual report （ 2021 ）[EB/OL ] . （ 2022-01-10 ）[ 2023-02-03 ] . https://www.cdr-adr.org.cn/drug_1/aqjs_1/drug_aqjs_sjbg/202203/t20220330_49586.html https://www.cdr-adr.org.cn/drug_1/aqjs_1/drug_aqjs_sjbg/202203/t20220330_49586.html .

Li HN ， Deng JX ， Yu PM ， et al . Drug-related deaths in China：an analysis of a spontaneous reporting system [J ] . Front Pharmacol ， 2022 ， 13 ： 771953 .

Wu YF ， Fang Y . Stroke prediction with machine learning methods among older Chinese [J ] . Int J Environ Res Public Health ， 2020 ， 17 （ 6 ）： 1828 .

Chicco D ， Jurman G . Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone [J ] . BMC Med Inform Decis Mak ， 2020 ， 20 （ 1 ）： 16 .

Zhang JL ， Tang WM . Building a prediction model for iron deficiency anemia among infants in Shanghai，China [J ] . Food Sci Nutr ， 2019 ， 8 （ 1 ）： 265 - 272 .

Pharmaceutical Care Network Europe Association Classification for drug related problems V 9.1 . The PCNE Classification V 9.1 2020

Ma Z ， Sun SS ， Zhang CX ， et al . Characteristics of drug-related problems and pharmacists' interventions in a geriatric unit in China [J ] . Int J Clin Pharm ， 2021 ， 43 （ 1 ）： 270 - 274 .

谢雅琼，林孝怡 . 血清游离轻链在鉴别诊断不同病因肾病的应用价值及其与患者肾功能分期的相关性分析 [J ] . 诊断学理论与实践， 2023 ， 22 （ 2 ）： 166 - 171 ．

Xie YQ ， Lin XY . Value of serum-free light chain assay in differential diagnosis and staging of nephropathy of various etiologies [J ] . J Diagn Concepts Pract ， 2023 ， 22 （ 2 ）： 166 - 171 ．

Liu PP ， Li GY ， Han M ， et al . Identification and solution of drug-related problems in the neurology unit of a tertiary hospital in China [J ] . BMC Pharmacol Toxicol ， 2021 ， 22 （ 1 ）： 65 .

Garin N ， Sole N ， Lucas B ， et al . Drug related problems in clinical practice：a cross-sectional study on their prevalence，risk factors and associated pharmaceutical interventions [J ] . Sci Rep ， 2021 ， 11 （ 1 ）： 883 .

张咪雪，刘　莎 . 抑郁症的药物治疗新进展 [J ] . 重庆医科大学学报， 2024 ， 49 （ 5 ）： 631 - 637 .

Zhang MX ， Liu S . New progress in drug therapy for depression [J ] . Journal of Chongqing Medical University ， 2024 ， 49 （ 5 ）： 631 - 637 .

Viktil KK ， Blix HS ， Moger TA ， et al . Polypharmacy as commonly defined is an indicator of limited value in the assessment of drug-related problems [J ] . Br J Clin Pharmacol ， 2007 ， 63 （ 2 ）： 187 - 195 .

幸晓琼，王红梅，杨佳丹，等 . 某院心内科住院患者严重和禁忌的潜在药物相互作用横断面研究 [J ] . 中国药学杂志， 2021 ， 56 （ 8 ）： 694 - 698 .

Xing XQ ， Wang HM ， Yang JD ， et al . Cross-sectional study of major and contraindicated potential drug-drug interactions in hospitalized cardiac patients in our hospital [J ] . Chin Pharm J ， 2021 ， 56 （ 8 ）： 694 - 698 .

席田兰，幸晓琼，杨佳丹，等 . 基于潜在药物相互作用的心血管疾病患者住院时间延长风险预测模型的构建 [J ] . 中国医院用药评价与分析， 2023 ， 23 （ 4 ）： 400 - 403 .

Xi TL ， Xing XQ ， Yang JD ， et al . Construction of prediction model for prolonged length of stay in patients with cardiovascular disease based on potential drug interactions [J ] . Eval Anal Drug Use Hosp China ， 2023 ， 23 （ 4 ）： 400 - 403 .

Chung AY ， Anand S ， Wong IC ， et al . Improving medication safety and diabetes management inHong Kong：a multidisciplinary approach [J ] . Xianggang Yi Xue Za Zhi ， 2017 ， 23 （ 2 ）： 158 - 167 .

Onder G ， Petrovic M ， Tangiisuran B ， et al . Development and validation of a score to assess risk of adverse drug reactions among in-hospital patients 65 years or older：the GerontoNet ADR risk score [J ] . Arch Intern Med ， 2010 ， 170 （ 13 ）： 1142 - 1148 .

Geeson C ， Wei L ， Franklin BD . Development and performance evaluation of the Medicines Optimisation Assessment Tool（MOAT）：a prognostic model to target hospital pharmacists' input to prevent medication-related problems [J ] . BMJ Qual Saf ， 2019 ， 28 （ 8 ）： 645 - 656 .

Urbina O ， Ferrández O ， Grau S ， et al . Design of a score to identify hospitalized patients at risk of drug-related problems [J ] . Pharmacoepidemiol Drug Saf ， 2014 ， 23 （ 9 ）： 923 - 932 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Influencing factors for sarcopenia in elderly hospitalized patients and construction and validation of a risk prediction model

Research advances in artificial intelligence for difficult airway prediction

Application of machine learning models in predicting renal function decline following robot-assisted partial nephrectomy

Influencing factors for dysphagia in the elderly and establishment of a predictive model

Related Author

Zhou Guilin

Shao Jianlin

Deng Dan

He Pingfeng

Jiang Hong

Liu Xintong

Peng Peng

Fan Qingqing

Related Institution

Department of Anesthesiology，The First Affiliated Hospital of Kunming Medical University

Department of General Practice，Chongqing University Central Hospital

Department of Geriatrics，The First Affiliated Hospital of Chongqing Medical University

Department of Health Statistics，College of Public Health，Chongqing Medical University

Department of Clinical Laboratory， Banan Hospital Affiliated to Chongqing Medical University

⁰