LLM Questionnaire Completion for Automatic Psychiatric Assessment

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Rosenman, Gony, Wolf, Lior, Hendler, Talma
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910480944070656
author Rosenman, Gony
Wolf, Lior
Hendler, Talma
author_facet Rosenman, Gony
Wolf, Lior
Hendler, Talma
contents We employ a Large Language Model (LLM) to convert unstructured psychological interviews into structured questionnaires spanning various psychiatric and personality domains. The LLM is prompted to answer these questionnaires by impersonating the interviewee. The obtained answers are coded as features, which are used to predict standardized psychiatric measures of depression (PHQ-8) and PTSD (PCL-C), using a Random Forest regressor. Our approach is shown to enhance diagnostic accuracy compared to multiple baselines. It thus establishes a novel framework for interpreting unstructured psychological interviews, bridging the gap between narrative-driven and data-driven approaches for mental health assessment.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06636
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLM Questionnaire Completion for Automatic Psychiatric Assessment
Rosenman, Gony
Wolf, Lior
Hendler, Talma
Computation and Language
Machine Learning
68T50
I.2.7
We employ a Large Language Model (LLM) to convert unstructured psychological interviews into structured questionnaires spanning various psychiatric and personality domains. The LLM is prompted to answer these questionnaires by impersonating the interviewee. The obtained answers are coded as features, which are used to predict standardized psychiatric measures of depression (PHQ-8) and PTSD (PCL-C), using a Random Forest regressor. Our approach is shown to enhance diagnostic accuracy compared to multiple baselines. It thus establishes a novel framework for interpreting unstructured psychological interviews, bridging the gap between narrative-driven and data-driven approaches for mental health assessment.
title LLM Questionnaire Completion for Automatic Psychiatric Assessment
topic Computation and Language
Machine Learning
68T50
I.2.7
url https://arxiv.org/abs/2406.06636