Peer grounded planning breaks chronic health goals into doable steps
Peer-Grounded Counterfactual Path Planning for Chronic Health Management
Machine Learning
Summary
Managing chronic diseases like diabetes is hard because it requires many small changes in behavior that add up over time. The authors offer a new way to create step-by-step plans for patients, based on what similar people have actually done and improved. Their method builds a map of achievable health states and suggests a path through these states that gradually improves health, making goals easier and more realistic to reach. They tested this on diabetic patient data and found it breaks big goals into smaller, manageable steps grounded in real peer experiences.
What this means in practice
- •For healthcare providers: Create personalized incremental health plans for chronic patients based on achievable peer behaviors in real-world data.
- •For chronic care management platforms: Design software to generate peer-grounded step-by-step behavior improvement routes that improve patient adherence and outcomes.$Commercial implications: Enables platforms to offer individualized intervention plans that reflect realistic, achievable behavior changes demonstrated by similar patients.
Authors
Saman Khamesian, Hassan Ghasemzadeh
Abstract
Effective behavioral intervention in chronic disease management requires not a single prescription but a sequence of incremental steps, each grounded in what real, similar individuals have demonstrably achieved. Counterfactual explanation offers a natural computational route to such guidance, answering what change in behavior would have produced a better outcome. But existing methods return a target state without a route to it, guarantee no monotone health improvement along the way, and draw no evidence from peer behavior -- asking a patient to close a wide gap in one move, which is precisely the recommendation structure least likely to be attempted. We propose POROS (Peer-Grounded Optimal Routes Over States), a domain-agnostic framework rooted in Bandura's self-efficacy theory and Festinger's social comparison theory that constructs a Behavioral Progression Graph -- a directed acyclic graph over observed patient states in which every edge requires both peer-grounded behavioral proximity and strict health outcome improvement. Every edge is therefore a behavioral change that individuals in the cohort have demonstrated is achievable within a single period. Minimum-cost paths through this graph decompose otherwise inactionable behavioral gaps into incremental, peer-grounded steps. We evaluate POROS on two independent longitudinal cohorts of patients with diabetes. For patients below the 70% clinical threshold for time in range (TIR, blood glucose within 70-180 mg/dL), it reduces the mean gain required per step from 26.3 percentage points (pp) to 5.5 pp on one cohort and from 31.1 pp to 5.7 pp on the other, decomposing large behavioral jumps into the incremental steps that self-efficacy requires. Across both cohorts, 97-98% of multi-hop paths cross patient boundaries, embedding social comparison by construction.