Graphical Structure Learning Identifies Hypothesized Mechanisms for Heterogeneous Treatment Effects in Medicaid Population Health Programs

Sanjay Basu

Abstract: Heterogeneous treatment effect models identify Medicaid beneficiaries who benefit most from population health programs but provide limited mechanistic insight. We combined graphical structure learning with regression-based effect estimation to generate hypotheses about intervention-specific mechanisms in a program serving 6396 Medicaid managed care enrollees (2023-2025). The Peter-Clark algorithm and Greedy Equivalence Search identified conditional dependencies between baseline characteristics, intervention exposures (behavioral health therapy, n=434; clinical pharmacy, n=632; community health workers, n=2169; care coordination, n=1042), and acute care outcomes. Four associations warranted investigation: behavioral health therapy was associated with reduced psychiatric admissions (risk ratio, 0.27; 95% confidence interval, 0.19-0.37; E-value, 7.6); clinical pharmacy showed dose-dependent associations with reduced costs; community health workers were associated with emergency department reduction (risk ratio, 0.62; 95% confidence interval, 0.51-0.74; E-value, 4.5); and care coordination was associated with emergency department reduction among women (risk ratio, 0.38; 95% confidence interval, 0.27-0.52; E-value, 9.1). False coverage rate correction for post-selection inference yielded 98.44% confidence intervals that continued to exclude the null for all reported associations. Graphical methods can complement heterogeneous treatment effect models by generating mechanistic hypotheses for confirmation through future trials.