Development and Application of Pharmacological Statin-Associated Muscle Symptoms Phenotyping Algorithms Using Structured and Unstructured Electronic Health Records Data

ABSTRACT Background Statins are widely prescribed cholesterol-lowering medications in the US, but their clinical benefits can be diminished by statin-associated muscle symptoms (SAMS), leading to discontinuation. In this study, we aimed to develop and validate a pharmacological SAMS clinical phenotyping algorithm using electronic health records (EHRs) data from Minnesota Fairview. Methods We retrieved structured and unstructured EHR data of statin users and manually ascertained a gold standard set of SAMS cases and controls using the SAMS-CI tool from clinical notes in 200 patients. We developed machine learning algorithms and rule-based algorithms that incorporated various criteria, including ICD codes, statin allergy, creatine kinase elevation, and keyword mentions in clinical notes. We applied the best performing algorithm to the statin cohort to identify SAMS. Results We identified 16,889 patients who started statins in the Fairview EHR system from 2010-2020. The combined rule-based (CRB) algorithm, which utilized both clinical notes and structured data criteria, achieved similar performance compared to machine learning algorithms with a precision of 0.85, recall of 0.71, and F1 score of 0.77 against the gold standard set. Applying the CRB algorithm to the statin cohort, we identified the pharmacological SAMS prevalence to be 1.9% and selective risk factors which included female gender, coronary artery disease, hypothyroidism, use of immunosuppressants or fibrates. Conclusion Our study developed and validated a simple pharmacological SAMS phenotyping algorithm that can be used to create SAMS case/control cohort for further analysis such as developing SAMS risk prediction model. LAY SUMMARY Statins are commonly prescribed cholesterol-lowering medications in the US, but some patients may experience statin-associated muscle symptoms (SAMS) that can reduce their benefits. In this study, we developed and tested a simple algorithm using electronic health records (EHRs) to identify cases of SAMS. We retrieved data from statin users in the Minnesota Fairview EHR system and manually identified a gold standard set of SAMS cases and controls using a clinical tool. We developed machine learning and rule-based algorithms that considered various criteria, such as ICD codes, statin allergy, creatine kinase elevation, and keyword mentions in clinical notes. The best performing algorithm, called the combined rule-based (CRB) algorithm, achieved similar performance to machine learning algorithms in identifying SAMS cases. When applied to the larger statin cohort, the CRB algorithm identified a prevalence of 1.9% for pharmacological SAMS, and identified selective risk factors such as female gender, coronary artery disease, hypothyroidism, and use of immunosuppressants or fibrates. The developed algorithm has the potential to help create SAMS case/control cohorts for future studies such as building models to predict SAMS risks for patients.