In August 2016, the Allegheny County Department of Human Services (DHS) implemented the Allegheny Family Screening Tool (AFST), a predictive risk model designed to improve call screening decision-making in the county’s child welfare system. The AFST is the result of a two-year process of exploration, research, ethical analysis and training.
The AFST calculates a score by integrating and analyzing hundreds of data elements; the score predicts the long-term likelihood of re-referral, if the referral is screened out without an investigation, or home removal, if the referral is screened in for investigation. The Family Screening Score provides additional information – in conjunction with clinical judgement – to assist child welfare workers make a call screening decision.
The following publications provide a look at the development and implementation of the AFST:
- Developing Predictive Risk Models to Support Child Maltreatment Hotline Screening Decisions
This publication consists of three sections:
1) Developing Predictive Risk Models to Support Child Maltreatment Hotline Screening Decisions: Allegheny County Methodology and Implementation
2) Ethical Analysis: Predictive Risk Models at Call Screening for Allegheny County
3) DHS’s response to the Ethical Analysis
- Allegheny Family Screening Tool: Frequently-Asked Questions
- Allegheny County Predictive Risk Modeling Tool Implementation: Process Evaluation
Below, you’ll find several news items about the AFST:
DHS Response to Automated Inequality by Virginia Eubanks
Ms. Eubanks set out to examine the development and use of the AFST. Consistent with other decisions we have made to promote rigor, transparency and accountability in our implementation of this new tool, we invited the author into our agency. Unfortunately, her piece has numerous inaccuracies and several key points require correction.
This video, produced by University of Pennsylvania’s Actionable Intelligence for Social Policy, highlights the Allegheny Family Screening Tool as one of the projects across the country that use integrated data systems (IDS) to improve social programs.
Can Big Data Help Save Abused Kids?
This Reason article discusses efforts to use predictive analytics in preventing child abuse.
How Machine Learning Can Improve Public Sector Services
Published by The Regulatory Review in October 2017, this article discusses how Allegheny County government digitized its records and uses big data analysis to improve health and human services.
‘Less Bad’ Bias: An Analysis of the Allegheny Family Screening Tool
Published in February 2019, this paper provides analysis of the Allegheny County Family Screening Tool within the context of increasing algorithmic decision-making.
Predictive Analytics in Child Welfare
Published by the U.S. Department of Health and Human Services Office of the Assistance Secretary for Planning and Evaluation in November 2017, this report examines the potential benefits and pitfalls of predictive analytics and provides advice for progress.
Predictive Analytics in the Child Welfare System, Starting with the Basics
Hosted by the Alliance for Racial Equity in Child Welfare and the Center for the Study of Social Policy. This webinar discuss the development and use of predictive analytics in child welfare.
Using Integrated Data Systems (IDS) in County Government
Four Annie E. Casey Foundation reports explore the value of using Integrated Data Systems to improve outcomes for individuals and families.
Want Less-Biased Decisions? Use Algorithms.
Published in the Harvard Business Review, this article examines algorithmic decision-making.