Key result
A predictive model using remotely collected personal emergency response system data reliably identified patients at high risk for 30-day emergency hospital transport with an AUC of 0.779.
Why the study?
Telehealth programs often focus on high-cost patients and are limited to 30-60 days postdischarge, creating a need for inexpensive monitoring via personal emergency response systems to predict emergency hospital transport and target interventions.
Can patient data collected remotely via a personal emergency response system (PERS) reliably predict 30-day emergency hospital transport in elderly subscribers?
Population
290,434 development, 289,426 validation, and 1815 home health care PERS subscribers
Design
Prognostic retrospective cohort study
Follow-up
30 days
Authors
Loading...
May support remote risk stratification in elderly PERS users; leaves open whether predictions enable effective preventive interventions.
Observational (n=581,675)
Can patient data collected remotely via a personal emergency response system (PERS) reliably predict 30-day emergency hospital transport in elderly subscribers?
Effect estimate: AUC 0.779 (95% CI 0.774-0.785)
A predictive model using personal emergency response system (PERS) data can reliably identify elderly patients at high risk for 30-day emergency hospital transport, enabling targeted preventive interventions.
Buijs et al. (2018) conducted an observational in Elderly patients using a personal emergency response system (PERS) (n=581,675). Predictive model based on PERS data was evaluated on Performance of the predictive model of 30-day emergency hospital transport (AUC 0.779, 95% CI 0.774-0.785). A predictive model using remotely collected personal emergency response system data reliably identified patients at high risk for 30-day emergency hospital transport with an AUC of 0.779.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: