Fig. 2: SDoH variable importance in prediction of quality care gaps.
From: Predicting quality measure completion among 14 million low-income patients enrolled in medicaid
APRN (advanced practice registered nurse), TANF (Temporary Assistance for Needy Families), SSI (Supplement Security Income), SSDI (Social Security Disability Insurance), AMM (antidepressant medication management), PBH (persistence of beta-blocker treatment after a heart attack), SPC (statin therapy for patients with cardiovascular disease), SPD (statin therapy for patients with diabetes), PCR (all-cause hospital readmissions), LBP (avoidance of unnecessary imaging for routine lower back pain), FUM30 (follow-up after emergency department visits for mental illness), PPC (prenatal and postpartum care visits), WCV (child and adolescent well-care visits). Variable importance for predicting quality care gaps: individual-level SDoH (panel a), healthcare access SDoH (panel b), and area-level SDoH (panel c).Variable importance values range from 0 to 1, with higher values indicating greater contribution to model predictions.
