A Reproducible Model Based on Clinical Text for Predicting Suicidal Behavior.

Obeid, Jihad S; Tsalatsanis, Athanasios; Chaphalkar, Chaitanya; Robinson, Sara; Klein, Sierra; Cool, Sarah; Szwast, Elizabeth; Bunnell, Brian E

Obeid, Jihad S; Tsalatsanis, Athanasios; Chaphalkar, Chaitanya; Robinson, Sara; Klein, Sierra; Cool, Sarah; Szwast, Elizabeth; Bunnell, Brian E.

Afiliação

Obeid JS; Medical University of South Carolina, Charleston, SC, USA.
Tsalatsanis A; University of South Florida, Tampa, FL, USA.
Chaphalkar C; University of South Florida, Tampa, FL, USA.
Robinson S; University of South Florida, Tampa, FL, USA.
Klein S; University of South Florida, Tampa, FL, USA.
Cool S; University of South Florida, Tampa, FL, USA.
Szwast E; Medical University of South Carolina, Charleston, SC, USA.
Bunnell BE; University of South Florida, Tampa, FL, USA.

Stud Health Technol Inform ; 310: 1486-1487, 2024 Jan 25.

Article em En | MEDLINE | ID: mdl-38269709

ABSTRACT

ABSTRACT

Suicide risk models are critical for prioritizing patients for intervention. We demonstrate a reproducible approach for training text classifiers to identify patients at risk. The models were effective in phenotyping suicidal behavior (F1=.94) and moderately effective in predicting future events (F1=.63).

Assuntos

Ideação Suicida; Humanos; Modelos Teóricos; Previsões

Palavras-chave

Suicidal behavior; machine learning; reproducibility; text classification

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Ideação Suicida Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Humans Idioma: En Revista: Stud Health Technol Inform Assunto da revista: INFORMATICA MEDICA / PESQUISA EM SERVICOS DE SAUDE Ano de publicação: 2024 Tipo de documento: Article País de afiliação: Estados Unidos

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google