2023
Sükei, Emese; Romero-Medrano, Lorena; Leon-Martinez, Santiago; López, Jesús Herrera; Campaña-Montes, Juan José; Olmos, Pablo M; Baca-Garcia, Enrique; Artés-Rodríguez, Antonio
Continuous Assessment of Function and Disability via Mobile Sensing: Real-World Data-Driven Feasibility Study Artículo de revista
En: JMIR Form Res, vol. 7, pp. e47167, 2023, ISSN: 2561-326X.
Resumen | Enlaces | BibTeX | Etiquetas: WHODAS; functional limitations; mobile sensing; passive ecological momentary assessment; predictive modeling; interpretable machine learning; machine learning; disability; clinical outcome
@article{info:doi/10.2196/47167,
title = {Continuous Assessment of Function and Disability via Mobile Sensing: Real-World Data-Driven Feasibility Study},
author = {Emese S\"{u}kei and Lorena Romero-Medrano and Santiago Leon-Martinez and Jes\'{u}s Herrera L\'{o}pez and Juan Jos\'{e} Campa\~{n}a-Montes and Pablo M Olmos and Enrique Baca-Garcia and Antonio Art\'{e}s-Rodr\'{i}guez},
url = {http://www.ncbi.nlm.nih.gov/pubmed/37902823},
doi = {10.2196/47167},
issn = {2561-326X},
year = {2023},
date = {2023-10-30},
journal = {JMIR Form Res},
volume = {7},
pages = {e47167},
abstract = {Background: Functional limitations are associated with poor clinical outcomes, higher mortality, and disability rates, especially in older adults. Continuous assessment of patients' functionality is important for clinical practice; however, traditional questionnaire-based assessment methods are very time-consuming and infrequently used. Mobile sensing offers a great range of sources that can assess function and disability daily. Objective: This work aims to prove the feasibility of an interpretable machine learning pipeline for predicting function and disability based on the World Health Organization Disability Assessment Schedule (WHODAS) 2.0 outcomes of clinical outpatients, using passively collected digital biomarkers. Methods: One-month-long behavioral time-series data consisting of physical and digital activity descriptor variables were summarized using statistical measures (minimum, maximum, mean, median, SD, and IQR), creating 64 features that were used for prediction. We then applied a sequential feature selection to each WHODAS 2.0 domain (cognition, mobility, self-care, getting along, life activities, and participation) in order to find the most descriptive features for each domain. Finally, we predicted the WHODAS 2.0 functional domain scores using linear regression using the best feature subsets. We reported the mean absolute errors and the mean absolute percentage errors over 4 folds as goodness-of-fit statistics to evaluate the model and allow for between-domain performance comparison. Results: Our machine learning\textendashbased models for predicting patients' WHODAS functionality scores per domain achieved an average (across the 6 domains) mean absolute percentage error of 19.5%, varying between 14.86% (self-care domain) and 27.21% (life activities domain). We found that 5-19 features were sufficient for each domain, and the most relevant being the distance traveled, time spent at home, time spent walking, exercise time, and vehicle time. Conclusions: Our findings show the feasibility of using machine learning\textendashbased methods to assess functional health solely from passively sensed mobile data. The feature selection step provides a set of interpretable features for each domain, ensuring better explainability to the models' decisions\textemdashan important aspect in clinical practice.},
keywords = {WHODAS; functional limitations; mobile sensing; passive ecological momentary assessment; predictive modeling; interpretable machine learning; machine learning; disability; clinical outcome},
pubstate = {published},
tppubtype = {article}
}
Background: Functional limitations are associated with poor clinical outcomes, higher mortality, and disability rates, especially in older adults. Continuous assessment of patients' functionality is important for clinical practice; however, traditional questionnaire-based assessment methods are very time-consuming and infrequently used. Mobile sensing offers a great range of sources that can assess function and disability daily. Objective: This work aims to prove the feasibility of an interpretable machine learning pipeline for predicting function and disability based on the World Health Organization Disability Assessment Schedule (WHODAS) 2.0 outcomes of clinical outpatients, using passively collected digital biomarkers. Methods: One-month-long behavioral time-series data consisting of physical and digital activity descriptor variables were summarized using statistical measures (minimum, maximum, mean, median, SD, and IQR), creating 64 features that were used for prediction. We then applied a sequential feature selection to each WHODAS 2.0 domain (cognition, mobility, self-care, getting along, life activities, and participation) in order to find the most descriptive features for each domain. Finally, we predicted the WHODAS 2.0 functional domain scores using linear regression using the best feature subsets. We reported the mean absolute errors and the mean absolute percentage errors over 4 folds as goodness-of-fit statistics to evaluate the model and allow for between-domain performance comparison. Results: Our machine learning–based models for predicting patients' WHODAS functionality scores per domain achieved an average (across the 6 domains) mean absolute percentage error of 19.5%, varying between 14.86% (self-care domain) and 27.21% (life activities domain). We found that 5-19 features were sufficient for each domain, and the most relevant being the distance traveled, time spent at home, time spent walking, exercise time, and vehicle time. Conclusions: Our findings show the feasibility of using machine learning–based methods to assess functional health solely from passively sensed mobile data. The feature selection step provides a set of interpretable features for each domain, ensuring better explainability to the models' decisions—an important aspect in clinical practice.