Estimating Heart Failure Health Status From Multimodal Wearables: Implementation of a Feature-Engineering Framework for KCCQ-12 Prediction

Routine monitoring of symptom burden and quality of life in heart failure (HF) patients is limited by intermittent sampling of validated instruments, such as the Kansas City Cardiomyopathy Questionnaire (KCCQ-12). As more wearable devices track physiological measures in real-world settings than ever before, we propose an exploratory implementation of a feature-engineering framework to bridge this sampling gap, approximating KCCQ-12 scores and patient health status from wearable features. In this narrative, we processed data from the 8-week multicenter observational study of HF patients (NYHA class I-III) wearing Everion® multisensor smartwatches: "Evaluating Mobile Health Tool Use for Capturing Patient-centered Outcomes Measures in HF Patients" (NCT04191356). Then, LASSO logistic regression was applied for feature selection, followed by binary classification and linear mixed-effects modeling to predict KCCQ-12 scores. Among patients generating sufficient data (n = 59), there were 173 unique KCCQ-12 observations. From 7,235 candidate features, LASSO retained 88 predictors (Supplementary Table 1), including the top predictors: p6MWD (positive), daily steps/walking time (positive), nocturnal respiratory variability (negative), and patient-reported dyspnea (negative). Binary classification models achieved test AUC=0.77 (sensitivity 91%, specificity 63%) and linear mixed-effects models produced a RMSE of 14.7 (R 2 = 0.58) for predicting patient health status and continuous KCCQ-12 scores, respectively. A patient-level split analysis revealed decreased model performance (RMSE = 18.9; R 2 =0.33), suggesting limited generalizability to new individuals. This exploratory implementation with small sample size outlines wearable features that warrant future investigation for KCCQ-12 score monitoring and offers early-stage lessons for assessing such features as proxies of KCCQ-12 scores in real-world settings.