Medicaid claims alone have high sensitivity but low specificity in identifying child abuse and neglect

TL;DR

Medicaid claims can identify most children with abuse or neglect but also wrongly flag many others due to low specificity.

Contribution

Developed and validated a Medicaid claims-based predictive model for identifying child abuse and neglect.

Findings

The model achieved 98.5% sensitivity but only 9.5% specificity in identifying child abuse and neglect.

Children with a CAN indicator had more high-expenditure medical encounters and injury-related ED visits.

Linking Medicaid claims with child protective services reports is suggested to improve accuracy.

Abstract

Decision support tools, such as predictive risk models (PRMs), may assist medical personnel identify child abuse and neglect (CAN). However, no prior work has established whether Medicaid claims alone are sufficient for accurate prediction. We developed a Medicaid claims-based PRM to predict CAN, validating against medical encounters and clinical diagnoses that precede and follow a CAN-related diagnosis code.

We conducted a case–control study of Medicaid-enrolled children born in New York State between 2006 and 2008. Children with a CAN indicator in the first 10 years of life (case) were matched to children without (control) based on sex, race/ethnicity, county, low birthweight (<2,500 g), birth year, and months enrolled in Medicaid. Outcomes in 1 year included medical encounters, ED visits by injury intent, number of providers, and expenditures, as well as death within 5 years.

Of the 50,515 children in the matched sample, 13,109 (26%) were Black, 24,298 (48%) were female, 31,917 (63%) resided in New York City, and by design, 13,429 (26.5%) were diagnosed with CAN before age 10. The final PRM achieved an area under the receiver operating curve of 62%, an accuracy of 75%, a sensitivity of 98.5%, and a specificity of 9.5%. Children with a CAN indicator and those with a high probability of CAN had more high-expenditure medical encounters, particularly injury-related ED visits, compared with those without in the year following the index date.

This claims-based tool demonstrated high sensitivity, identifying nearly all children with a CAN indicator; however, it had very low specificity. Future work should link Medicaid claims to child protective services reports to increase predictive accuracy.