The Heterogeneous Effects of Remote Patient Monitoring on Patients with Chronic Heart Conditions

While prior research has provided evidence that, on average, Remote Patient Monitoring (RPM) use has a positive impact on patient outcomes, very few have examined the heterogeneous effects of RPM, and none have looked at how different hospital and county configurations fit different types of patients with chronic heart conditions. Using Resource Orchestration as our theoretical framework, we will leverage causal machine learning to find patterns of heterogeneity on the impact of RPM and describe how different combinations of hospital and county configurations facilitate RPM use for each type of patient with chronic heart conditions. We expect to find differences in treatment effects across patients with different ages, socioeconomic statuses, and payment sources. Hence, our research will contribute to the literature by providing insights that can help health care providers craft strategies to facilitate RPM use for different types of patients with chronic heart conditions.