JMIR Publications

ABSTRACT

Background:

A small proportion of high-need patients persistently use the bulk of healthcare services and incur disproportionate costs. Population health management (PHM) programs often refer to these patients as persistent high users/utilizers (PHUs). Accurate PHU prediction enables PHM programs to better align scarce healthcare resources with high-need PHUs while generally improving outcomes. While prior research in PHU prediction has shown promise, traditional regression methods used in these studies have yielded limited accuracy.

Objective:

We sought to improve PHU predictions with an ensemble approach in a retrospective observational study design using insurance claim records.

Methods:

We defined a PHU as a patient with healthcare costs in the top 20% of all patients for four consecutive 6-month periods. We used 2013 claims data to predict PHU status in next 24 months. Our study population included 165,595 patients in the Johns Hopkins Health Care plan, with 8359 (5.1%) patients identified as PHUs in 2014 and 2015. We assessed the performance of several standalone machine learning methods and then an ensemble approach combining multiple models.

Results:

The candidate ensemble with Complement Naïve Bayes and Random Forest layers produced increased sensitivity and PPV (49.0% and 50.3%, respectively) compared to logistic regression (46.8% and 46.1%).

Conclusions:

Our results suggest that ensemble machine learning can improve prediction of care management needs. Improved PPV implies reduced incorrect referral of low-risk patients. With the improved sensitivity/PPV balance of this approach, resources may be directed more efficiently to patients needing them most.