Accepted for/Published in: JMIR Research Protocols
Date Submitted: May 10, 2024
Date Accepted: Jan 30, 2025
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Federated Approach to Integrating Ambient In-Home Sensor Data and EMR Data for the Prediction of Outcomes in ALS
ABSTRACT
Background:
Amyotrophic Lateral Sclerosis leads to rapid physiological and functional before causing untimely death. Current best-practices approaches to interdisciplinary care are unable to provide adequate monitoring of patients’ health. Passive in-home sensor systems enable 24x7 health monitoring. Combining sensor data with outcomes extracted from the electronic health record through a supervised machine learning algorithm may enable healthcare providers to predict and ultimately retard decline among people living with ALS.
Objective:
The objective of this manuscript is to describe a federated approach to the assimilation of sensor and EHR data in a machine learning algorithm to predict decline among people living with ALS.
Methods:
Sensor systems have been continuously deployed in the homes of four participants for up to 330 days. Sensors include bed, gait, and motion sensors. Sensor data are subjected to a multi-dimensional streaming clustering algorithm to detect changes in health status. Specific health outcomes are identified in the Electronic Health Record and extracted via the REDCap Fast Healthcare Interoperability Resource directly into a secure database. Machine learning algorithms are currently in development to predict those health outcomes from sensor-detected changes in health status.
Results:
This methodology manuscript presents preliminary results from one participant as proof-of-concept. The participant experienced several notable changes in activity, fluctuations in heart rate and respiration rate, and reductions in gait speed. Data collection is ongoing with a growing sample.
Conclusions:
The system described in this manuscript enables tracking the health status of people living with ALS at unprecedented levels of granularity. Combined with tightly integrated EHR data, we anticipate building predictive models that can identify opportunities for health care services before declines in function are detected. We anticipate that this system will improve and extend the lives of people living with ALS.
Citation
