Ir arriba
Información del artículo en conferencia

Analyzing mobility patterns of complex chronic patients using wearable activity trackers: a machine learning approach

A. Polo-Molina, E.F. Sánchez-Úbeda, J. Portela, R. Palacios, C. Rodríguez-Morcillo, A. Muñoz, C. Álvarez-Romero, C. Hernández-Quiles

9th International Conference on Time Series and Forecasting - ITISE 2023, Las Palmas de Gran Canaria (España). 12-14 julio 2023


Resumen:

This study suggests using wearable activity trackers to identify mobility patterns in Chronic Complex Patients (CCP) and investigate their relation with the Barthel Index (BI) for assessing functional decline. CCP are individuals who suffer from multiple, chronic health conditions that often lead to a progressive decline in their functional capacity. As a result, CCP frequently require the use of healthcare and social resources, which can place a significant challenge on the healthcare system. Evaluating mobility patterns is critical for determining CCP’s functional capacity and prognosis. In order to monitor the overall activity levels of CCP, wearables activity trackers are proposed. Utilizing the data gathered by the wearables, time series clustering with Dynamic Time Warping (DTW) is employed to generate synchronized mobility patterns of mean activity and coefficient of variation profiles. The research has revealed distinct patterns in individuals’ walking habits, including the time of day they walk, whether they walk continuously or intermittently, and their relation to BI. These findings could significantly enhance CCP’s quality of care by providing a valuable tool for personalizing treatment and care plans.


Resumen divulgativo:

Este estudio sugiere la utilización de pulseras de actividad para recopilar datos de pasos con el fin de identificar patrones de movilidad en pacientes crónicos complejos y examinar la relación entre estos patrones y el índice de Barthel como medio para evaluar el deterioro funcional.


Palabras clave: Barthel Index · Chronic Complex Patients · Dynamic Time Warping · Functional Decline · Mobility Patterns · Time Series Clustering


DOI: DOI icon https://doi.org/10.3390/engproc2023039092

Publicado en Engineering Proceedings, vol: 39, pp: 92-1/92-11

Fecha de publicación: 2023-12-31.



Cita:
A. Polo-Molina, E.F. Sánchez-Úbeda, J. Portela, R. Palacios, C. Rodríguez-Morcillo, A. Muñoz, C. Álvarez-Romero, C. Hernández-Quiles, Analyzing mobility patterns of complex chronic patients using wearable activity trackers: a machine learning approach, 9th International Conference on Time Series and Forecasting - ITISE 2023, Las Palmas de Gran Canaria (España). 12-14 julio 2023. En: Engineering Proceedings, vol. 39, nº. 1, e-ISSN: 2673-4591


    Líneas de investigación:
  • Análisis de datos
  • Modelos matemáticos e Inteligencia Artificial aplicados al sector de la salud