by A. Cakmak, E. Alday, S. Densen, G. Najarro, P. Rout, C. J. Rozell, O.T. Inan, A.J. Shah and G.D. Clifford
Abstract:
Background: Heart failure (HF) is a major cause of frequent hospitalization and death. Early detection of HF symptoms using smartphone-based monitoring may reduce adverse events in a low-cost, scalable way. Objective: We examined the relationship of heart failure decompensation events with smartphone-based features derived from passively and actively acquired data. Methods: This was a prospective cohort study in which we monitored HF participants’ social and movement activities using a smartphone app and followed them for clinical events via phone and chart review and classified the encounters as compensated or decompensated by reviewing the provider notes in detail. We extracted motion, location, and social interaction passive features and self-reported quality of life weekly (active) with the short Kansas City Cardiomyopathy Questionnaire (KCCQ-12) survey. We developed and validated an algorithm for classifying decompensated versus compensated clinical encounters (hospitalizations or clinic visits). We evaluated models based on single modality as well as early and late fusion approaches combining patient-reported outcomes and passive smartphone data . We used Shapley Additive exPlanation (SHAP) values to quantify the contribution and impact of each feature to the model. Results: We evaluated 28 participants with mean (SD) age 67(8) years, 10% female sex, and 47% Black race. We identified 62 compensated and 48 decompensated clinical events from 24 and 22 participants respectively. The highest area under the precision-recall curve (AUCPr) for classifying decompensation was with a late fusion approach combining KCCQ-12, motion, and social contact features using leave one subject out cross-validation for a two-day prediction window. It had a AUCPr of 0.80, with an area under the receiver operator curve (AUC) of 0.83, a positive predictive value (PPV) of 0.73, a sensitivity of 0.77, and a specificity of 0.88 for a two-day prediction window. Similarly, the four-day window model had AUC of 0.82, AUCPr of 0.69, a PPV of 0.62, sensitivity of 0.68, and specificity of 0.87. Passive social data provided some of the most informative features with fewer calls of longer duration associating with a higher probability of future HF decompensation. Conclusions: Smartphone-based data that includes both passive monitoring and actively collected surveys may provide important behavioral and functional health information on HF status in advance of clinical visits. This proof-of-concept study, although small, offers important insight on the social and behavioral determinants of health and feasibility of using smartphone-based monitoring in this population. Our strong results are comparable to more active and expensive monitoring approaches, and underscore the need for larger studies to understand the clinical significance of this monitoring method.
Reference:
Passively Captured Interpersonal Social Interactions and Motion from Smartphones Predicts Decompensation in Heart Failure: An Observational Cohort StudyA. Cakmak, E. Alday, S. Densen, G. Najarro, P. Rout, C. J. Rozell, O.T. Inan, A.J. Shah and G.D. Clifford. JMIR Formative Research, 6(8), pp. e36972, August 2022.
Bibtex Entry:
@article{cakmak.22,
author = {Cakmak, A. and Alday, E. and Densen, S. and Najarro, G. and Rout, P. and Rozell, C. J. and Inan, O.T. and Shah, A.J. and Clifford, G.D.},
title = {Passively Captured Interpersonal Social Interactions and Motion from Smartphones Predicts Decompensation in Heart Failure: An Observational Cohort Study},
year = 2022,
month = aug,
volume={6},
number={8},
pages={e36972},
journal = {JMIR Formative Research},
abstract = {Background: Heart failure (HF) is a major cause of frequent hospitalization and death. Early detection of HF symptoms using smartphone-based monitoring may reduce adverse events in a low-cost, scalable way. Objective: We examined the relationship of heart failure decompensation events with smartphone-based features derived from passively and actively acquired data. Methods: This was a prospective cohort study in which we monitored HF participants’ social and movement activities using a smartphone app and followed them for clinical events via phone and chart review and classified the encounters as compensated or decompensated by reviewing the provider notes in detail. We extracted motion, location, and social interaction passive features and self-reported quality of life weekly (active) with the short Kansas City Cardiomyopathy Questionnaire (KCCQ-12) survey. We developed and validated an algorithm for classifying decompensated versus compensated clinical encounters (hospitalizations or clinic visits). We evaluated models based on single modality as well as early and late fusion approaches combining patient-reported outcomes and passive smartphone data . We used Shapley Additive exPlanation (SHAP) values to quantify the contribution and impact of each feature to the model. Results: We evaluated 28 participants with mean (SD) age 67(8) years, 10\% female sex, and 47\% Black race. We identified 62 compensated and 48 decompensated clinical events from 24 and 22 participants respectively. The highest area under the precision-recall curve (AUCPr) for classifying decompensation was with a late fusion approach combining KCCQ-12, motion, and social contact features using leave one subject out cross-validation for a two-day prediction window. It had a AUCPr of 0.80, with an area under the receiver operator curve (AUC) of 0.83, a positive predictive value (PPV) of 0.73, a sensitivity of 0.77, and a specificity of 0.88 for a two-day prediction window. Similarly, the four-day window model had AUC of 0.82, AUCPr of 0.69, a PPV of 0.62, sensitivity of 0.68, and specificity of 0.87. Passive social data provided some of the most informative features with fewer calls of longer duration associating with a higher probability of future HF decompensation. Conclusions: Smartphone-based data that includes both passive monitoring and actively collected surveys may provide important behavioral and functional health information on HF status in advance of clinical visits. This proof-of-concept study, although small, offers important insight on the social and behavioral determinants of health and feasibility of using smartphone-based monitoring in this population. Our strong results are comparable to more active and expensive monitoring approaches, and underscore the need for larger studies to understand the clinical significance of this monitoring method.}
}