Why Predict Align Prevent?
For the PAP Protocol, data sources, and methodology
In the United States, between 1500 and 3000 infants and children die due to abuse and neglect each year. Children age 0-3 years are at the greatest risk for maltreatment and related fatality. The children who survive abuse, neglect, and chronic adversity in early childhood often suffer a lifetime of well-documented physical, mental, educational, and social health problems. The cost of child maltreatment to American society is estimated at $124 - 585 billion annually.
A distinctive characteristic of the infants and young children most vulnerable to maltreatment is their potential lack of visibility to the most common types of mandatory reporters such as teachers, medical professionals, and law enforcement before they sustain harm. Indeed, approximately half of infants and children who die from child maltreatment are not known to child protection agencies before their deaths occur.
Currently, most programs designed to prevent child abuse and neglect or mitigate associated risks are deployed after suspicion for maltreatment is present. Predict Align Prevent (PAP) focuses on identifying risk and providing prevention resources before child maltreatment has occurred.
PAP’s unique approach in preventing child maltreatment begins with its use of location-based predictive analytics instead of the more common approach of person-specific predictive analytics. Person-based predictive analytics for child maltreatment can be beneficial in their ability to guide interventions to specific people, potentially preempting a maltreatment event, but person-specific predictive resolution comes at a cost. Person-level predictions require person-level data, often necessitating a jurisdiction to overcome the significant legal, bureaucratic and financial costs required to integrate or link highly private, cross-agency administrative data. Person-specific algorithms also require a report of suspicion of maltreatment, relegating further action into the realm of secondary prevention.
Predict Align Prevent delivers an innovative solution with a three-phase program:
First, the Predict phase utilizes geospatial machine learning to identify 500 X 500 square foot areas where child maltreatment is likely to occur in the future based on environmental risk and protective features. A geographic risk and protective factor analysis determines which risk factors are most harmful and which protective factors are most helpful in each unique community. The resulting maps show where and what prevention efforts are likely to have the greatest prevention impact.
In the next phase, Align, PAP utilizes the predictive maps overlaid with public health and community asset locations. We work with existing community leaders, stakeholders, and coalitions to align and augment existing prevention efforts. Our services are designed to:
● Optimize access to critical supports
● Develop capacity for vital services
● Develop supportive infrastructure
● Improve professional response
● Standardize cross-sector prevention messaging
● Strengthen and build community resilience
● Match employment opportunities with populations using psychographics
● Develop new social norms
Once a community has rallied around high-risk locations by aligning prevention services, supports, resources, and initiatives, we move into our Prevent phase where collaborators can learn what combination results in the most effective maltreatment prevention.
Repeated population-level measurement of the impact of aligned services and supports will demonstrate if there is a reduction of child maltreatment and related risk factors over time. We are also seeking locations demonstrating positive deviance, or “bright spots” where the wisdom of community members can benefit others. The purpose of these measurements is to clarify the need for new or different strategies, to expand effective programs, and continue to improve the allocation of resources.
We expect an effective prevention bundle to offer communities and states benefits beyond the reduction of child maltreatment, including improved allocation of resources, quality improvement in prevention services, accountability to objective effectiveness measures, and a reduction in redundant or conflicting efforts.