Skip to main content

ORIGINAL RESEARCH article

Front. Pharmacol.
Sec. Experimental Pharmacology and Drug Discovery
Volume 15 - 2024 | doi: 10.3389/fphar.2024.1334929
This article is part of the Research Topic Machine Learning and Pharmacotherapy View all 7 articles

Machine learning-based prediction model for the efficacy and safety of statins

Provisionally accepted
Yu Xiong Yu Xiong 1,2*Xiaoyang Liu Xiaoyang Liu 2,3Qing Wang Qing Wang 4*Li Zhao Li Zhao 2Xudong Kong Xudong Kong 2*Chunhe Da Chunhe Da 5*Zuohuan Meng Zuohuan Meng 6*Leilei Qu Leilei Qu 7*Qinfang Xia Qinfang Xia 8*Pengmei Li Pengmei Li 2*Lihong Liu Lihong Liu 2*
  • 1 Institute of Materia Medica, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
  • 2 Department of Pharmacy, China-Japan Friendship Hospital, Beijing, China
  • 3 Department of Pharmacy Administration and Clinical Pharmacy, School of Pharmaceutical Sciences, Health Science Centre, Peking University, Beijing, Beijing Municipality, China
  • 4 Department of Automation, Tsinghua University, Beijing, China
  • 5 Respiratory Center of the Third Affiliated Hospital of Gansu University of Traditional Chinese Medicine, Gansu, China
  • 6 Institute of Traditional Chinese Medicine, The Third Affiliated Hospital of Gansu University of Chinese Medicine, Gansu, China
  • 7 Respiratory and Critical Care Medical Center, Baiyin First People's Hospital, Gansu, China
  • 8 Department of Information center, China-Japan Friendship Hospital, Beijing, China

The final, formatted version of the article will be published soon.

    The appropriate use of statins plays a vital role in reducing the risk of atherosclerotic cardiovascular disease (ASCVD). However, due to changes in diet and lifestyle, there has been a significant increase in the number of individuals with high cholesterol levels. Therefore, it is crucial to ensure the rational use of statins. Adverse reactions associated with statins, including liver enzyme abnormalities and statinassociated muscle symptoms (SAMS), have impacted their widespread utilization. In this study, we aimed to develop a predictive model for statin efficacy and safety based on real-world clinical data using machine learning techniques. Methods: We employed various data preprocessing techniques, such as improved random forest imputation and Borderline SMOTE oversampling, to handle the dataset. Boruta method was utilized for feature selection, and the dataset was divided into training and testing sets in a 7:3 ratio. Five algorithms were used to construct the predictive models. Ten-fold cross-validation and bootstrapping sampling were performed for internal and external validation. Additionally, SHAP was employed for feature interpretability. Ultimately, an accessible web-based platform for predicting statin efficacy and safety was established based on the optimal predictive model. Results: The random forest algorithm exhibited the best performance among the five algorithms. The predictive models for LDL-C target attainment (AUC=0. 883, Accuracy=0.868, Precision=0.858, Recall=0.863, F1=0.860, AUPRC=0.906, MCC=0.761), liver enzyme abnormalities (AUC=0. 964, Accuracy=0.964, Precision=0.967, Recall=0.963, F1=0.965, AUPRC=0.978, MCC=0.938), and muscle pain/ Creatine kinase (CK) abnormalities (AUC=0.981, Accuracy=0.980, Precision=0.987, Recall=0.975, F1=0.981, AUPRC=0.987, MCC=0.965) demonstrated favorable performance. The most important features of LDL-C target attainment prediction model was cerebral infarction, TG, PLT, and HDL. The most important features of liver enzyme abnormalities model was CRP, CK and number of oral medications. Similarly, AST, ALT, PLT and number of oral medications were found to be important features for muscle pain/CK abnormalities. Based on the best-performing predictive model, a user-friendly web application was designed and implemented.This study presented a machine learning-based predictive model for statin efficacy and safety. The platform developed can assist in guiding statin therapy decisions and optimizing treatment strategies. Further research and application of the model are warranted to improve the utilization of statin therapy.

    Keywords: Statins, machine learning, predictive model, random forest, efficacy, Safety

    Received: 08 Nov 2023; Accepted: 12 Jul 2024.

    Copyright: © 2024 Xiong, Liu, Wang, Zhao, Kong, Da, Meng, Qu, Xia, Li and Liu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Yu Xiong, Institute of Materia Medica, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Qing Wang, Department of Automation, Tsinghua University, Beijing, China
    Xudong Kong, Department of Pharmacy, China-Japan Friendship Hospital, Beijing, China
    Chunhe Da, Respiratory Center of the Third Affiliated Hospital of Gansu University of Traditional Chinese Medicine, Gansu, China
    Zuohuan Meng, Institute of Traditional Chinese Medicine, The Third Affiliated Hospital of Gansu University of Chinese Medicine, Gansu, China
    Leilei Qu, Respiratory and Critical Care Medical Center, Baiyin First People's Hospital, Gansu, China
    Qinfang Xia, Department of Information center, China-Japan Friendship Hospital, Beijing, China
    Pengmei Li, Department of Pharmacy, China-Japan Friendship Hospital, Beijing, China
    Lihong Liu, Department of Pharmacy, China-Japan Friendship Hospital, Beijing, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.