JMIR Publications

ABSTRACT

Background:

Predictive analytics based on data from remote monitoring of elderly via a Personal Emergency Response System (PERS) in the United States (US) can identify subscribers at high risk for emergency hospital transport. These risk predictions can subsequently be used to proactively target interventions and prevent avoidable, costly healthcare utilization. It is, however, unknown if PERS-based risk prediction with targeted interventions could also be applied in the German healthcare setting.

Objective:

The objectives were to 1) develop and validate a predictive model of 30-day emergency hospital transport based on data from a German PERS provider, and 2) compare the model to another predictive model developed on data from a US PERS provider.

Methods:

Retrospective data of 5,805 subscribers to a German PERS service were used to develop and validate an extreme gradient boosting predictive model of 30-day hospital transport, including predictors derived from subscriber demographics, self-reported medical conditions and a two-year history of case data. Models were trained on 80% of the data and performance was evaluated on an independent test set of 20%. Results were compared to our previously published prediction model developed on a data set of PERS users in the US.

Results:

German PERS subscribers were on average 83.6 years old, with 64.0% females. 65.4% reported three or more chronic conditions. 1.4% of subscribers had one or more emergency transports in 30 days in the test set, which was significantly lower compared to the US data set (2.2%). Performance of the predictive model of emergency hospital transport, as evaluated by Area Under the receiver operator characteristic Curve (AUC), was 0.749 [95% CI: 0.721-0.777], which was similar to the US prediction model (AUC = 0.779 [95% CI: 0.774-0.785]). The top 1% of predicted high-risk patients were 10.7 times more likely to experience an emergency hospital transport in 30 days than the overall German PERS population. This lift was comparable to a model lift of 11.7 obtained by the US predictive model.

Conclusions:

Despite differences in emergency care utilization, PERS-based collected subscriber data can be used to predict utilization outcomes in different international settings. These predictive analytic tools can be used by healthcare organizations to extend population health management into the home, by identifying and delivering timelier targeted interventions to high-risk patients. This could lead to overall improved patient experience, higher quality of care and more efficient resource utilization.