Using machine learning to predict future foster care admission.

Area of Science:

• Public Health
• Health Informatics
• Social Science

Background:

• Foster care admissions are a significant source of trauma for children and families, leading to adverse outcomes.
• Identifying at-risk children early is crucial for implementing preventative measures and diversion strategies.

Purpose of the Study:

• To assess the effectiveness of machine learning (ML) methods in predicting children at high risk for future foster care admission.
• To evaluate the impact of social determinants of health (SDOH) data on prediction accuracy.

Main Methods:

• Utilized claims data from children and linked adults in an Ohio Medicaid health plan.
• Incorporated individual and geographic social determinants of health (SDOH) factors.
• Compared a gradient-boosted tree ML algorithm against logistic regression for predictive performance.

Main Results:

• The ML model identified 2408 children (1.32%) at risk, with 1599 entering foster care within a year (PPV 66.4%).
• Models incorporating SDOH data demonstrated substantially higher accuracy (PPV 84.72%) compared to those without (PPV 27.44%).
• The gradient-boosted tree model outperformed logistic regression in predicting foster care admissions.

Conclusions:

• Social determinants of health (SDOH) are critical factors in predicting foster care admission.
• Machine learning holds significant potential for facilitating early interventions to prevent unnecessary foster care placements.
• Integrating ML and SDOH data can enhance child welfare services and support family stability.