@Article{info:doi/10.2196/63700,
author="Havreng-Th{\'e}ry, Charlotte
and Fouchard, Arnaud
and Denis, Fabrice
and Veyron, Jacques-Henri
and Belmin, Jo{\"e}l",
title="Cost-Effectiveness Analysis of a Machine Learning--Based eHealth System to Predict and Reduce Emergency Department Visits and Unscheduled Hospitalizations of Older People Living at Home: Retrospective Study",
journal="JMIR Form Res",
year="2025",
month="Apr",
day="11",
volume="9",
pages="e63700",
keywords="monitoring; older adult; predictive tool; home care aide; emergency department visit; cost-effectiveness; artificial intelligence; electronic health; eHealth; emergency department; unscheduled hospitalization; aging; retrospective study; medico-economic; living at home; nursing home; emergency visit; Brittany; France; machine learning; remote monitoring; digital health; health informatics",
abstract="Background: Dependent older people or those losing their autonomy are at risk of emergency hospitalization. Digital systems that monitor health remotely could be useful in reducing these visits by detecting worsening health conditions earlier. However, few studies have assessed the medico-economic impact of these systems, particularly for older people. Objective: The objective of this study was to compare the clinical and economic impacts of an eHealth device in real life compared with the usual monitoring of older people living at home. Methods: This study was a comparative, retrospective, and controlled trial on data collected between May 31, 2021, and May 31, 2022, in one health care and home nursing center located in Brittany, France. Participants had to be aged >75 years, living at home, and receiving assistance from the home care service for at least 1 month. We implemented among the intervention group an eHealth system that produces an alert for a high risk of emergency department visits or hospitalizations. After each home visit, the home care aides completed a questionnaire on participants' functional status using a smartphone app, and the information was processed in real time by a previously developed machine learning algorithm that identifies patients at risk of an emergency visit within 7 to 14 days. In the case of predicted risk, the eHealth system alerted a coordinating nurse who could then inform the family carer and the patient's nurses or general practitioner. Results: A total of 120 patients were included in the study, with 60 in the control group and 60 in the intervention group. Among the 726 visits from the intervention group that were not followed by an alert, only 4 (0.6{\%}) resulted in hospitalizations (P<.001), confirming the relevance of the system's alerts. Over the course of the study, 37 hospitalizations were recorded for 25 (20.8{\%}) of the 120 patients. Additionally, of the 120 patients, 9 (7.5{\%}) were admitted to a nursing home, and 7 (5.8{\%}) died. Patients in the intervention group (56/60, 93{\%}) remained at home significantly more often than those in the control group (48/60, 80{\%}; P=.03). The total cost of primary care and hospitalization during the study was {\texteuro}167,000 ({\texteuro}1=US {\$}1.09), with {\texteuro}108,000 (64.81{\%}) attributed to the intervention group (P=.20). Conclusions: This study presents encouraging results on the impact of a remote medical monitoring system for older adults, demonstrating a reduction in both emergency department visits and hospitalization costs. Trial Registration: ClinicalTrials.gov NCT05221697; https://clinicaltrials.gov/study/NCT05221697 ",
issn="2561-326X",
doi="10.2196/63700",
url="https://formative.jmir.org/2025/1/e63700",
url="https://doi.org/10.2196/63700",
url="http://www.ncbi.nlm.nih.gov/pubmed/40215100"
}