Development and application of pharmacological statin-associated muscle symptoms phenotyping algorithms using structured and unstructured electronic health records data

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

Objective

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 statin-associated 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, including logistic regression, naive Bayes, decision tree, random forest, and gradient boosting decision tree, were used to construct the predictive models. Ten-fold cross-validation and bootstrapping sampling were performed for internal and external validation. Additionally, SHAP (SHapley Additive exPlanations) 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.

Conclusion

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.

Development and Validation of the Pharmacological Statin-Associated Muscle Symptoms Risk Stratification Score Using Electronic Health Record Data

Statin-associated muscle symptoms (SAMS) can lead to statin nonadherence. This paper aims to develop a pharmacological SAMS risk stratification (PSAMS-RS) score using a previously developed PSAMS phenotyping algorithm that distinguishes objective vs. nocebo SAMS using electronic health record (EHR) data. Using our PSAMS phenotyping algorithm, SAMS cases and controls were identified from Minnesota Fairview EHR, with the statin user cohort divided into derivation (January 1, 2010, to December 31, 2018) and validation (January 1, 2019, to December 31, 2020) cohorts. A Least Absolute Shrinkage and Selection Operator regression model was applied to identify significant features for PSAMS. PSAMS-RS scores were calculated and the clinical utility of stratifying PSAMS risk was assessed by comparing hazard ratios (HRs) between fourth vs. first score quartiles. PSAMS cases were identified in 1.9% (310/16,128) of the derivation and 1.5% (64/4,182) of the validation cohorts. Sixteen out of 38 clinical features were determined to be significant predictors for PSAMS risk. Patients within the fourth quartile of the PSAMS scores had an over sevenfold (HR: 7.1, 95% confidence interval (CI): 4.03-12.45, derivation cohort) or sixfold (HR: 6.1, 95% CI: 2.15-17.45, validation cohort) higher hazard of developing PSAMS vs. those in their respective first quartile. The PSAMS-RS score is a simple tool to stratify patients' risk of developing PSAMS after statin initiation which could inform clinician-guided pre-emptive measures to prevent PSAMS-related statin nonadherence.