Back

Health System Surveillance to Advance Mental Health Parity for Children

Beinenson, D.; Joyce, J.; Henderson, H.; Patel, J.; Frericks, G.; Constantino, J. N.

2025-10-02 health systems and quality improvement
10.1101/2025.09.25.25336447 medRxiv
Show abstract

ABSRACTO_ST_ABSObjectiveC_ST_ABSParity between physical and mental health for insured individuals is protected by federal law but unfulfilled, in part, because deficiencies are notoriously difficult to document. MethodsWe implemented real-time, systematic clinical documentation of gaps in access to mental health services for an outpatient cohort representing 2,149 children discharged from Childrens Healthcare of Atlanta emergency departments for behavioral crisis May-Dec 2024. ResultsSixty percent of patients discharged to the community with clear recommendations for expedited follow up were not receiving any service at 30-75-days. For those internally referred to the systems outpatient psychiatric practice, the documentation system confirmed medical necessity and captured accessibility or non-accessibility for each element of evidence-based care of each patients treatment plan. ConclusionFeasible revisions of electronic health record documentation, coupled with clinical accountability pathways can enable health systems to assume responsibility for continuous, real-time epidemiologic estimation of gaps in the adequacy of provider networks to meet the mental health needs of insured children. HighlightsWe modeled health-system-based surveillance of gaps in access to medically necessary mental health care for children, toward fulfillment of federal mental health parity law. Health system-based monitoring of unmet needs was feasible and generated real-time epidemiologically-relevant estimates of gaps in community capacity for mental health services

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.