The Big Picture

Traditional forensic risk assessments often struggle with subjectivity and potential biases, particularly those that rely on static factors or self-reporting. This study introduces a novel mobile neurocognitive assessment software designed to predict reoffense among correctional community probation populations. The tool measures decision-making traits through neurocognitive tests administered on a tablet, providing a bias-resistant, self-scoring approach to assess reoffense risk.
What We Did

Researchers conducted a study with 730 probationers in Houston, TX, using mobile neurocognitive assessment software that included tests for impulsivity, empathy, aggression, and other traits linked to reoffending. Data was collected between 2017 and 2019. Machine learning models were applied to the results to validate the tool’s predictive accuracy, focusing on its ability to predict recidivism using receiver-operator characteristic curves.

1

Predictive Validity Comparable to Traditional Assessments:

The neurocognitive assessment tool achieved a recidivism prediction value (AUC) of 0.70, which is similar to commonly used risk assessments. This suggests that the tool’s predictive accuracy is on par with traditional methods, but without the drawbacks of subjective biases.

2

Reduction of Bias and Subjectivity:

Unlike conventional tools that often depend on self-reports or static factors like past criminal history, this neurocognitive assessment reduces bias by focusing solely on dynamic cognitive traits, thereby eliminating race, socioeconomic status, and other demographic factors from influencing risk scores.

3

Efficiency and Accessibility:

The tool’s self-administered, mobile format reduces administrative burdens and allows for rapid, scalable deployment in diverse settings, making it accessible for widespread use in the criminal justice system.

The study underscores the potential of neurocognitive assessments in reforming risk prediction within the criminal justice system. By focusing on cognitive traits and removing bias-laden variables, this tool provides a more equitable method for predicting reoffense, which could significantly impact sentencing, probation decisions, and the allocation of rehabilitative resources.

1

Incorporate Neurocognitive Tools in Risk Assessments:

Expand the use of neurocognitive assessments in probation and parole settings to enhance predictive accuracy and reduce biases inherent in traditional tools.

2

Continuous Data Collection and Refinement:

Ongoing data collection and analysis will further validate and refine the tool, potentially allowing for more specific risk assessments based on crime type and individual profiles.

3

Training for Justice Professionals:

Equip criminal justice professionals with training on using neurocognitive assessments to inform decisions, focusing on interpreting results and integrating these tools into existing risk management frameworks.

About the Study

This study was conducted by researchers from The Center for Science and Law, Texas Southern University, and Stanford University School of Medicine, demonstrating a pioneering approach to risk assessment in the criminal justice system. The full APA citation is: Haarsma, G., Davenport, S., White, D. C., Ormachea, P. A., Sheena, E., & Eagleman, D. M. (2020). Assessing risk among correctional community probation populations: Predicting reoffense with mobile neurocognitive assessment software. Frontiers in Psychology, 10, 2926. https://doi.org/10.3389/fpsyg.2019.02926