본문 바로가기
AI-LAB/논문리뷰

[논문리뷰] Detection of Depression and Suicide Risk Based on Text From Clinical Interviews Using Machine Learning: Possibility of a New Objective Diagnostic Marker

by JS LAB 2023. 6. 24.
728x90
반응형

 

https://www.frontiersin.org/articles/10.3389/fpsyt.2022.801301/full

 

Detection of Depression and Suicide Risk Based on Text From Clinical Interviews Using Machine Learning: Possibility of a New Obj

BackgroundDepression and suicide are critical social problems worldwide, but tools to objectively diagnose them are lacking. Therefore, this study aimed to diagnose depression through machine learning and determine whether it is possible to identify groups

www.frontiersin.org

 

 

본 연구에서는 MINI 인터뷰 참여자들이 내뱉은 말을 바탕으로 Naive Bayes 분류기법에 기반한 기계학습을 통해 우울증을 검출하고, 우울증 환자의 자살위험도를 예측하는 앙상블 모델을 구축하여 정확성을 확인하였다.

 

텍스트만으로 우울증을 감지한 경우 AUC는 0.905로 나타났고, 이러한 환자의 자살 위험도를 예측한 경우 AUC는 0.632로 나타났습니다.

 

자살 위험 예측에서 텍스트는 인구 통계와 함께 사용할 때 AUC가 0.800인 진단 유용성을 보여주었습니다.

728x90
반응형

'AI-LAB > 논문리뷰' 카테고리의 다른 글

TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendations  (0) 2025.02.15
Learnable Item Tokenization for Generative Recommendation  (0) 2025.02.15
Large Language Models for Next Point-of-Interest Recommendation  (0) 2025.02.15
Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System  (0) 2025.02.15
[논문리뷰] Medical Specialty Recommendations by an Artificial Intelligence Chatbot on a Smartphone: Development and Deployment  (0) 2023.06.25

관련글

티스토리툴바