Allegheny County child neglect screening

The Allegheny Family Screening Tool (AFST) is a risk modelling tool used by Allegheny County, Pennsylvania, that aims to improve child safety by predicting the likelihood that a child referred for abuse or neglect will later experience a foster care placement in the two years after they are investigated.

The ASFT analyses personal data including birth, Medicaid, substance abuse, mental health, jail and probation records for each person reputedly involved in an allegation of child maltreatment and generates a ‘Family Screening Score’ that predicts the long-term likelihood of a child requiring protection.

The ASFT was developed by a team from Auckland University of Technology, University of Auckland, University of Southern California, and the University of California. ASFT Version 1 was released in 2016, followed by a second version in December 2018.

Operator: Allegheny County Children and Youth Services
Developer: Rhema Vaithianathan; Emily Putnam-Hornstein; Irene de Haan; Marianne Bitler; Tim Maloney; Nan Jiang

Country: USA

Sector: Govt - welfare

Purpose: Predict child neglect/abuse

Technology: Prediction algorithm  
Issue: Accuracy/reliability; Bias/disrimination - race, ethnicity, disability

Transparency: Black box; Marketing

Risks and harms 🛑

The Allegheny Family Screening Tool has been criticised for perpetuating historical biases and inequalities due to its reliance on potentially skewed data, and for inadequate transparency.

Bias/discrimination

Transparency 🙈

Allegheny County has been praised for making a significant effort to be transparent and open with the public and other stakeholders about the ASFT, notably concerning its implementation and the release of the list of predictive variables that make up the model.

However, the County has also been reluctant to release the model weights, or to provide the Family Screening Score to the families being investigated, or to judges - partly as it is seen as too difficult to explain.

Page info
Type: System
Published: December 2022
Last updated: May 2024