Breaking the Cycle of Incarceration With Targeted Mental Health Outreach: A Case Study in Machine Learning for Public Policy

2025-09-17

AI Summary

This study addresses racial disparities in recidivism among incarcerated individuals facing multiple disadvantages—namely, serious mental illness, substance use disorders, and homelessness. We propose a “predict–intervene” closed-loop framework grounded in multi-source administrative data. Using machine learning augmented with causal inference techniques, we develop a high-accuracy model to predict one-year reincarceration risk and systematically integrate it with community-based mental health outreach services. A randomized controlled trial conducted in Johnson County, Kansas, demonstrated that the model reliably identified individuals with >50% one-year reincarceration risk. Targeted psychological interventions for this high-risk cohort significantly reduced psychiatric crises, emergency medical service (EMS) utilization, and justice system involvement, while increasing engagement with healthcare services. The findings provide robust evidence that precision public health interventions can reduce recidivism and advance equity in criminal justice outcomes, offering a scalable, evidence-informed paradigm for correctional policy.

Technology Category

• Machine Learning: Causal Learning
• Humans and AI: Human-in-the-loop Machine Learning
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Many incarcerated individuals face significant and complex challenges, including mental illness, substance dependence, and homelessness, yet jails and prisons are often poorly equipped to address these needs. With little support from the existing criminal justice system, these needs can remain untreated and worsen, often leading to further offenses and a cycle of incarceration with adverse outcomes both for the individual and for public safety, with particularly large impacts on communities of color that continue to widen the already extensive racial disparities in criminal justice outcomes. Responding to these failures, a growing number of criminal justice stakeholders are seeking to break this cycle through innovative approaches such as community-driven and alternative approaches to policing, mentoring, community building, restorative justice, pretrial diversion, holistic defense, and social service connections. Here we report on a collaboration between Johnson County, Kansas, and Carnegie Mellon University to perform targeted, proactive mental health outreach in an effort to reduce reincarceration rates. This paper describes the data used, our predictive modeling approach and results, as well as the design and analysis of a field trial conducted to confirm our model's predictive power, evaluate the impact of this targeted outreach, and understand at what level of reincarceration risk outreach might be most effective. Through this trial, we find that our model is highly predictive of new jail bookings, with more than half of individuals in the trial's highest-risk group returning to jail in the following year. Outreach was most effective among these highest-risk individuals, with impacts on mental health utilization, EMS dispatches, and criminal justice involvement.

Problem

• Targeted mental health outreach to reduce reincarceration rates
• Predictive modeling identifies high-risk individuals for intervention
• Addressing mental illness and racial disparities in criminal justice

Innovation

• Machine learning for predictive modeling
• Targeted mental health outreach
• Field trial to evaluate effectiveness