Validating a Predictive Risk Model for Child Abuse and Neglect With Adolescent Outcomes
Journal of Adolescence · 2026-08 · 98 (6) · 2150-2154
DOI: 10.1002/jad.70195 ↗At a glance
Validierungsstudie in Journal of Adolescence, published online on 2026-06-01. Written by John Prindle and 4 co-authors. Institution: University of Southern California, Los Angeles, California, USA. Major MEDLINE topics: Child Abuse. 16 references. The full text is freely available in PubMed Central. Funded by: Reissa Foundation, Conrad N. Hilton Foundation.
Abstract (original language)
Introduction
A predictive risk model (PRM) was trained to stratify risk among children investigated for alleged maltreatment based on the likelihood of future child protection involvement. In the current brief, we assess the model's ability to differentiate risk of adverse events not used to build the model (i.e., arrest, death) among adolescent populations investigated following reported maltreatment to guide prevention‐oriented services.
Methods
Child welfare and vital statistics records were obtained through a data use agreement. Among adolescents born in 2000 and 2001 and investigated for alleged maltreatment between ages 11 and 17 ( n = 72,340), risk scores were calculated using a random forest algorithm based on information available at the time of maltreatment report. The records of these adolescents were then linked to arrest and death records.
Results
Among adolescents investigated for maltreatment, 5.8% experienced a juvenile arrest or death before age 21. Of those who experienced an arrest or death, 43.9% fell in the highest risk decile.
Conclusions
A PRM trained to predict foster care placement had strong external validity in predicting both future arrests and deaths. The average time from investigation to adverse event indicates a meaningful window for interventions to be delivered focused on supporting and stabilizing adolescents and their families.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- University of Southern California, Los Angeles, California, USA.
- University of Wisconsin-Madison, Madison, Wisconsin, USA.
- University of Utah, Salt Lake City, Utah, USA.
- University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
ORCID profiles: John Prindle
Funding
- Reissa Foundation
- Conrad N. Hilton Foundation
Cite
APA
Prindle, J., Ahn, E., Palmer, L., Eastman, A. L., & Putnam-Hornstein, E. (2026). Validating a Predictive Risk Model for Child Abuse and Neglect With Adolescent Outcomes. Journal of Adolescence, 98(6), 2150-2154. https://doi.org/10.1002/jad.70195
Vancouver
Prindle J, Ahn E, Palmer L, Eastman AL, Putnam-Hornstein E. Validating a Predictive Risk Model for Child Abuse and Neglect With Adolescent Outcomes. Journal of Adolescence. 2026;98(6):2150-2154. doi:10.1002/jad.70195
BibTeX
@article{Prindle2026,
author = {Prindle, John and Ahn, Eunhye and Palmer, Lindsey and Eastman, Andrea Lane and Putnam-Hornstein, Emily},
title = {Validating a Predictive Risk Model for Child Abuse and Neglect With Adolescent Outcomes},
journal = {Journal of Adolescence},
year = {2026},
volume = {98},
number = {6},
pages = {2150--2154},
doi = {10.1002/jad.70195}
}
EUVIMED