摘要
抑郁症是一种严重影响生活质量的精神疾病,会伴随面部表情和行为的变化。目前的抑郁症诊断评估主要依赖于自我报告和医师观察,存在主观误差,缺乏客观有效的自动化抑郁症检测方法。面部表情可呈现重要的非语言信息,研究人员开始通过面部特征来辅助识别和诊断抑郁症。而机器学习作为人工智能的核心,在图像特征提取和分类方面有着突出的优势。该文以IEEE Xplore数据库为数据来源,梳理了2016—2021年基于机器学习的抑郁症患者面部特征研究,并对未来研究方向进行展望,以期为日后抑郁症临床智能化诊断和跟踪提供参考。
Major depressive disorder(MDD) is a mental illness that severely affects the quality of life, accompanied by changes in facial expressions and other behaviors. The current diagnosis for MDD mainly relies on self-reports and observations from doctors,which has subjective errors. There is a lack of objective and effective automated MDD detection methods. Facial expressions are important nonverbal behaviors, and the researchers have begun to use facial features to assist in identifying and diagnosing depression. As the core of artificial intelligence, machine learning has outstanding advantages in image feature extraction and classification. Taking IEEE Xplore database as the data source, this article sorts out the researches on the facial features of MDD patients based on machine learning from 2016 to 2021, and prospects the future research directions, to provide reference for clinical intelligent diagnosis and tracking of MDD in the future.
作者
李欣
范青
LI Xin;FAN Qing(Shanghai Mental Health Center,Shanghai Jiao Tong University School of Medicine,Shanghai 200030,China)
出处
《上海交通大学学报（医学版）》
CAS
CSCD
北大核心
2022年第1期124-129,共6页
Journal of Shanghai Jiao tong University:Medical Science
基金
上海市科学技术委员会“科技创新行动计划”临床医学领域项目(18411952000)。
关键词
抑郁症
机器学习
面部特征
面部表情
major depressive disorder(MDD)
machine learning
facial feature
facial expression
