Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 10, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Predicting Psychiatric Readmission of Children and Adolescents Using Machine Learning.

Ethan A Poweleit^1,2,3,4, Jeffrey R Strawn^5,4,6,7, Rhonda D Szczesniak^7,8

¹Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA.

Journal of Child and Adolescent Psychopharmacology

|July 9, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Real-time prediction of rapid weight change in children with cystic fibrosis who have initiated modulator therapy.

Clinical nutrition ESPEN·2026

Same author

A methotrexate dashboard: integrating MTXPK.org into the electronic health record to facilitate model-informed care for pediatric patients receiving high-dose methotrexate.

JAMIA open·2026

Same author

Severe Thiopurine-Induced Myelosuppression in a Pediatric Acute Lymphoblastic Leukemia Patient With the NUDT15 1/6 Genotype: A Brief Report.

Clinical and translational science·2026

Same author

Association Between Venlafaxine Exposure And Treatment Outcomes In Older Adults With Depression: Association entre l'exposition à la venlafaxine et les résultats du traitement chez les personnes âgées atteintes de dépression.

Canadian journal of psychiatry. Revue canadienne de psychiatrie·2026

Same author

Acute exposure to fine ambient particulate matter and pulmonary exacerbations in cystic fibrosis: A case-crossover study.

Atmospheric Environment: X·2026

Same author

Toward Precision Psychiatry: Using Clinical and Pharmacokinetic Data to Increase Antidepressant Dose or Change Treatment in Late-Life Depression.

Journal of clinical psychopharmacology·2026

This summary is machine-generated.

Machine learning models can predict psychiatric readmission in youth. This approach identifies at-risk children and adolescents for targeted interventions, reducing costly hospitalizations.

Area of Science:

Adolescent psychiatry
Computational psychiatry
Health informatics

Background:

Recurrent psychiatric hospitalizations in youth incur significant costs and burdens.
Current postdischarge planning lacks risk stratification for readmission.
Predictive modeling offers a pathway to identify at-risk youth for interventions.

Purpose of the Study:

To develop and validate machine learning models for predicting psychiatric readmission in children and adolescents.
To identify key predictors of psychiatric readmission in this population.
To enable targeted interventions for at-risk youth.

Main Methods:

Retrospective cohort study of 11,225 patients (≤18 years) with anxiety or depressive disorders.
Development of random forest models using electronic health record data.

Keywords:

anxiety depression hospitalization machine learning pediatrics readmission

Related Experiment Videos

Last Updated: Jul 10, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Internal validation at the development site and external validation at a second institution.

Main Results:

Models achieved AUROCs of 0.739-0.746 for 30-, 90-, and 180-day readmission during internal validation.
Key predictors included prior admissions, length of stay, age, and antipsychotic use.
External validation showed AUROCs of 0.598-0.657, indicating potential for generalization.

Conclusions:

Machine learning models demonstrate capability in identifying youth at risk for psychiatric readmission.
These models can inform targeted interventions to improve patient outcomes.
Further research can refine models for enhanced clinical utility.