Background
Cardiac Resynchronization Therapy (CRT) is a widely used, device-based therapy for patients with left ventricle (LV) failure. Unfortunately, many patients do not benefit from CRT, so there is potential value in identifying this group of non-responders before CRT implementation. Past studies suggest that predicting CRT response will require diverse variables, including demographic, biomarker, and LV function data. Accordingly, the objective of this study was to integrate diverse variable types into a machine learning algorithm for predicting individual patient responses to CRT.
Methods
We built an ensemble classification algorithm using previously acquired data from the SMART-AV CRT clinical trial (n = 794 patients). We used five-fold stratified cross-validation on 80% of the patients (n = 635) to train the model with variables collected at 0 months (before initiating CRT), and the remaining 20% of the patients (n = 159) were used as a hold-out test set for model validation. To improve model interpretability, we quantified feature importance values using SHapley Additive exPlanations (SHAP) analysis and used Local Interpretable Model-agnostic Explanations (LIME) to explain patient-specific predictions.
Results
Our classification algorithm incorporated 26 patient demographic and medical history variables, 12 biomarker variables, and 18 LV functional variables, which yielded correct prediction of CRT response in 71% of patients. Additional patient stratification to identify the subgroups with the highest or lowest likelihood of response showed 96% accuracy with 22 correct predictions out of 23 patients in the highest and lowest responder groups.
Conclusion
Computationally integrating general patient characteristics, comorbidities, therapy history, circulating biomarkers, and LV function data available before CRT intervention can improve the prediction of individual patient responses.
Purpose: As polygenic risk scores (PRS) enter clinical practice, healthcare providers' and the publics' comprehension of PRS results are of great importance, yet poorly understood. We present the Vanderbilt Polygenic Risk Scores Knowledge Score (Vanderbilt PRS-KS), a tool to quantify PRS knowledge.Methods: The Vanderbilt PRS-KS was developed by a team of genetic counselors and physicians to cover key conceptual facts pertaining to PRSs. We recruited (n=500) individuals with demographics representative of a U.S. sample and graduate-level healthcare students (n=74) at a large academic medical center to participate in this validation study. We evaluated the Vanderbilt PRS-KS's psychometric properties using confirmatory factor analysis (CFA) and item response theory (IRT).Results: The 7-item Vanderbilt PRS-KS correlated to a single latent construct on CFA (λ=0.31-0.61). The scale showed promising reliability (Cronbach's α=0.66) with IRT summed scores of ≥2 to ≤5, demonstrating reliability > 0.70. The Vanderbilt PRS-KS significantly correlated with genetic knowledge and applied PRS knowledge (r=0.55, r=0.29), and graduate-level healthcare students had significantly higher scores compared to the representative sample (p<0.01).Conclusions: The Vanderbilt PRS-KS is a rigorously validated measure to quantify PRS knowledge.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.