Predictive Modeling for Population Health Management: A Practical Guide (Issue Brief)

Publisher: Chicago, IL: Mathematica Policy Research
Feb 24, 2017
Lindsey Leininger and Thomas DeLeire

Key Findings:

A successful predictive modeling strategy depends upon identifying (1) a precisely defined health care problem, (2) a promising intervention, (3) the appropriateness of a targeted approach in implementing the intervention, and (4) sufficient data and analytic capacity to develop and validate a predictive model. Importantly, only one of these four steps is statistical in nature. Once the decision has been made to build a predictive model, it is critical to remember that (1) the resulting stratification is akin to a screening—not a diagnostic—test, often requiring further risk assessment and/or monitoring; (2) there is a always a trade-off between false positives and false negatives when deciding where in the predicted risk distribution to intervene; and (3) underlying risk of elevated health care need is dynamic, as such it is important to reassess risk at clinically relevant intervals and avoid evaluating interventions based on simple pre-post comparisons of the high-risk intervention group.

The proliferation of predictive modeling in health care has led to an environment in which the opportunities for (and the pressures on) public payers adopting such methods are growing rapidly. There are vast academic literatures regarding the use of predictive modeling; however, there are few if any practical tools available to health policy leaders to assist them in making their own judgements regarding the suitability and effectiveness of predictive methods. The overarching goal of this brief is to provide the requisite translational bridge. Specifically, this brief provides practical guidance for public payers interested in pursuing predictive modeling for population health management initiatives, outlining scenarios for when a predictive modeling application is likely to be appropriate and describing key implementation considerations.
Senior Staff

Lindsey Leininger
Read More