Predicting quality measure completion among 14 million low-income patients enrolled in medicaid
Authors:
Open Access
- 2 July 2025
- journal article
- research article
- Published by Springer Nature in npj Digital Medicine
- Vol. 8 (1) , 1-11
Abstract
Low-income populations have disproportionately low completion of recommended healthcare services, from missed vaccinations to cancer screenings. While machine learning models help identify high-risk patients for targeted treatment, they have rarely been evaluated for quality measure gap completion—or among low-income populations underrepresented in typical datasets. Analyzing 14.2 million Medicaid recipients—including those excluded from electronic health records and without prior utilization—we developed models to predict gaps in nine nationally adopted quality measures, including preventive care and chronic disease management. Using clinical data to prioritize outreach, the clinical-only model improved accuracy by 32.5 percentage points (pp) over non-predictive methods such as alphabetical calling or birthday reminders (AUROC: 0.88, F1-score: 0.69). Incorporating social determinants of health data further improved performance by 2.0pp in accuracy (to 84.5%) and increased F1-score by 5.0pp (to 0.74), with no change in AUROC (area under the receiver operating characteristic curve). Compared to the clinical-only model, the SDoH model also reduced pre-existing Black–White disparities in prediction accuracy. Model performance was especially sensitive to SDoH factors like healthcare workforce and facility availability.Keywords
This publication has 27 references indexed in Scilit:
- Prediction of non emergent acute care utilization and cost among patients receiving MedicaidScientific Reports, 2024
- Residential Structural Racism and Prevalence of Chronic Health ConditionsJAMA Network Open, 2023
- Addressing Social Needs in Clinical Settings: Early Lessons from Accountable Health CommunitiesPopulation Health Management, 2023
- Factors Associated With Disparities in Hospital Readmission Rates Among US Adults Dually Eligible for Medicare and MedicaidJAMA Health Forum, 2022
- Randomized Controlled Trial of Advance Notification Phone Calls vs Text Messages Prior to Mailed Fecal Test OutreachClinical Gastroenterology and Hepatology, 2021
- Comparative Effectiveness of Machine Learning Approaches for Predicting Gastrointestinal Bleeds in Patients Receiving Antithrombotic TreatmentJAMA Network Open, 2021
- Reducing Readmissions by Addressing the Social Determinants of HealthAmerican Journal of Health Economics, 2021
- XGBoost, a Machine Learning Method, Predicts Neurological Recovery in Patients with Cervical Spinal Cord InjuryNeurotrauma Reports, 2020
- Deaths Preventable in the U.S. by Improvements in Use of Clinical Preventive ServicesAmerican Journal of Preventive Medicine, 2010
- Social Determinants of Health2005