by Marie K. Cohen, ChronicleOfSocialChange.org
As The Chronicle of Social Change has been reporting over the past two years, various jurisdictions have been exploring new tools to focus the attention of child welfare systems on the children most at risk of subsequent abuse or neglect. The mainstream media has begun to notice, as demonstrated by CNBC’s recent report on Los Angeles’ contract with software company SAS to develop such a tool for its child welfare system.
These new approaches generally rely on predictive analytics, which means using patterns in data to predict future outcomes. Despite the recent media coverage, there is still some confusion about what is
meant by this term, how it differs from current approaches like Structured Decision Making (SDM), and the distinctions between the various new approaches.
To understand these new approaches, it is important to understand how child protective services (CPS) works now. I can describe the process in the District of Columbia, where I once served as a caseworker.
CPS workers in the District use checklists to interview children, parents, teachers, and others about an allegation of abuse and neglect. They generally rely on the verbal answers to these questions, although they do receive access to data from schools and public assistance agencies.
The District of Columbia, like jurisdictions in over 20 states, uses an SDM tool to help social workers decide how to proceed at the conclusion of an investigation. Social workers fill out checklists on the computer. SDM assigns points to each risk factor, such as “primary caregiver has historic or current drug or alcohol problem.”
Based on the worker’s checkoffs, the software spits out a recommendation to remove the child or keep her at home.
SDM has at least two major flaws. First, it can be manipulated to recommend the action that the social worker wants to take. Second, it does not obtain any new data but simply uses what the social worker plugs in. That’s why in my experience in D.C., SDM was treated as a meaningless form to be filled out, not as a tool for making decisions.
A new set of predictive tools, known as predictive analytics, is being developed for governments in Los Angeles, Allegheny County, Pennsylvania, and New Zealand. These tools are designed to produce a numeric risk score for each child assessed. A high risk score would target the child and family for special attention, which might include intensive services and monitoring.
Unlike SDM, predictive analytics tools access data directly from other systems rather than relying on self-report from parents and caregivers. These systems might include mental health, substance abuse treatment and criminal justice, among others. Clearly, the information obtained this way would be more accurate than simply asking the parent or caregiver, who has to rely on memory and might have an incentive to withhold information.
Los Angeles County’s Department of Child and Family Services has contracted with software giant SAS to develop a risk assessment tool called AURA. As described by The Chronicle, SAS identified child deaths, near fatalities and severe injuries (called “AURA events”) in 2011-2012 among children referred to CPS within six months of these events.
Programmers then developed an algorithm that calculated the risk of an AURA event in the six months following a referral based on the characteristics of the children and their families. The predictive power of the algorithm was tested against child abuse reports in 2013 (data that was not used to develop the algorithm.)
AURA proved to be a powerful tool for predicting deaths and serious injuries to children. Among those cases that had at least one referral before the current one, the 1 percent of referrals with the highest AURA scores experienced 57 percent of the AURA events. The 20 percent of referrals with the highest risk accounted for 83 percent of total AURA events.
Florida has chosen to use a different approach. It is using a tool called Rapid Safety Feedback (RSF), developed by a nonprofit called Eckerd Kids for Hillsborough County, which had experienced nine deaths among children in open cases receiving services at home over three years.
Rather than a risk assessment algorithm, RSF is a quality assurance tool that is used to target a set of high-risk cases for special treatment and review. RSF targets cases with characteristics associated with a high probability of serious injury or death to a child.
In Florida, RSF is used only for families with in-home cases. Cases designated high-risk are reviewed quarterly to make sure workers are using specific practices that have been shown to increase child safety.
According to Eckerd, there have been no maltreatment-related deaths of children in open cases in Hillsborough County since implementation of RSF in January 2013. Several states are working with Eckerd to adapt and implement RSF in their child welfare investigations.
The new tools discussed above are in their infancy in child welfare. It is important for policymakers and advocates to understand the nature of the tools that are available and the differences between them before making decisions about which if any to support.
Marie K. Cohen is a writer and child advocate and a mentor to a foster youth. She is a former social worker in the District of Columbia’s child welfare system. She has a Masters in Social Work from the University of Maryland and a Masters in Public Affairs from Princeton. Find her on Facebook at Fostering Reform or on Twitter @fosteringreform.
This article first appeared on ChronicleofSocialChange.org.
Thanks so much for posting my article. You may want to see the followup column, which is at https://chronicleofsocialchange.org/blogger-co-op/no-risk-trying-new-approaches-find-children-danger/15564
On Tue, Feb 9, 2016 at 10:32 PM, ACEs Too High wrote:
> The Chronicle of Social Change posted: ” by Marie K. > Cohen, ChronicleOfSocialChange.org As The Chronicle of Social Change has > been reporting over the past two years, various jurisdictions have been > exploring new tools to focus the attention of child welfare systems on the > children most a” >