CFE 2019: Start Registration
View Submission - CMStatistics
B0687
Title: Comparative intervention scoring for assessing heterogeneity of long-term health system intervention effects Authors:  Jared Huling - The Ohio State University (United States) [presenting]
Menggang Yu - University of Wisconsin - Madison (United States)
Maureen Smith - University of Wisconsin-Madison (United States)
Abstract: With the growing cost of health care in the United States, the need to improve efficiency and efficacy of the delivery of care has become increasingly urgent. To this end, there have been widespread efforts to design and implement interventions which coordinate the typically fragmented care of complex patients, yet the effectiveness of such interventions in practice has been mixed. A common thread among successful care coordination interventions is the targeting of patients likely to benefit for enrollment, however, there is little guidance toward effectively doing so. We seek to fill this gap by introducing a procedure to estimate personalized scores which characterize differential benefit of long-term health system interventions. As patients tend to respond differently over time, our approach allows the differential effects of an intervention to vary with time and encourage these effects to be more similar for closer time points. We utilize our approach to construct personalized enrollment decision rules for a complex case management intervention in a large health system and demonstrate that the enrollment decision rules result in improvement in health outcomes and care costs.