自動評估特定年齡憂鬱症狀的嚴重程度：整合臨床量表和多模態資料的機器學習模型;Automated Assessment of Age-Specific Depression Symptoms Severity: A Machine Learning Model Integrating Clinical Scales and Multimodal Data

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/95391

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/95391

Title:	自動評估特定年齡憂鬱症狀的嚴重程度：整合臨床量表和多模態資料的機器學習模型;Automated Assessment of Age-Specific Depression Symptoms Severity: A Machine Learning Model Integrating Clinical Scales and Multimodal Data
Authors:	楊政哲;Yang, Zheng-Zhe
Contributors:	資訊工程學系
Keywords:	特定年齡憂鬱症分析;憂鬱症症狀評估;多模態融合;憂鬱症診斷標準;age-specific depression analysis;depression symptom assessment;multi-modal fusion;depression criteria
Date:	2024-04-17
Issue Date:	2024-10-09 16:45:33 (UTC+8)
Publisher:	國立中央大學
Abstract:	憂鬱症是一個嚴重的公共衛生問題，影響著全球數百萬人。對於憂鬱症患者提供有效治療對於改善他們的生活至關重要，但對於每位患者提供個性化的照顧尤其挑戰重重，特別是對於那些有著複雜和多面性症狀的患者。本研究開發了一種機器學習模型，旨在預測不同年齡群體中人們的憂鬱症狀嚴重程度。該模型訓練於一個包括外部信息（例如文本、音頻、面部表情）和生理信息（例如心率、眼動）的多模態數據集上。結果顯示，該模型能夠準確預測不同年齡群體中人們的憂鬱症狀嚴重程度。模型還能夠提高憂鬱症狀預測的準確性，超越現有方法。這些發現對於憂鬱症治療的臨床實踐具有重要意義。所提出的機器學習模型可以用來協助臨床醫生為憂鬱症患者，特別是那些有嚴重症狀或來自不同年齡群體的患者，提供更加個性化的照顧。;Depression is a serious public health problem that affects millions of people worldwide. Effective treatment is essential to improving the lives of people with depression, but it can be challenging to provide individualized care for each patient, especially for those with complex and multifaceted symptoms. This study developed a machine learning model to predict the severity of depression symptoms in people of different age groups. The model was trained on a dataset of multimodal data, including external information (e.g., text, audio, facial expressions) and physiological information (e.g., heart rate, eye movement). The results showed that the model was able to accurately predict the severity of depression symptoms in people of different age groups. The model was also able to improve the prediction accuracy of depression symptoms over existing methods. These findings have important implications for the clinical practice of depression treatment. The proposed machine learning model could be used to assist clinicians in providing more individualized care for people with depression, especially those with severe symptoms or from different age groups.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	113	View/Open

社群 sharing

Loading...