Scholarlink

With the rising number of patients with depression in recent years, now has nearly 280 million people worldwide suffer from depression, China has 95 million patients with depression, depression has become the second big mental illness. With the increase of age, college students will gradually face great academic pressure and work pressure. In recent years, it has occurred frequently that college students cannot resolve their depression and gradually turn into depression, which eventually leads to accidentss. In the face of the increasingly severe depression of students, early assessment of depression is particularly important. The traditional assessment of depression mainly uses scale assessment and interview, but its subjectivity is strong, and it cannot avoid the situation that the subjects hide their emotions and conceal the facts, and the error is large. With the development of artificial intelligence, machine learning and deep learning is widely used in assessing depression, is mainly used for the scale of data mining, to promote the new assessment scale for depression, but still can’t change subjects fill out a form to hide the error caused. With the development of physiological data acquisition device and the further development of artificial intelligence technology, on the basis of the symptoms of depression in patients with obvious negative emotion tendency, early study compared the physiological indexes in patients with depression and healthy controls, found its differences, there are experiments prove that the method is effective, Therefore, the use of eye movement, electroencephalogram, expression and other physiological data as indicators has been widely used in the assessment of depression. Combined with machine learning and deep learning, an intelligent evaluation of physiological data is widely respected, promote the depression assessment more objective, more efficient, is beneficial to early screening depression group, promote the doctors, the teacher carries on the psychological counseling, promote the patient recover soon.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Review of Machine Learning-Based Assessment of Depression

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Wang Zhao,
  • Ziyi Cai,
  • Shuya Dong,
  • Weihe Hei

摘要

With the rising number of patients with depression in recent years, now has nearly 280 million people worldwide suffer from depression, China has 95 million patients with depression, depression has become the second big mental illness. With the increase of age, college students will gradually face great academic pressure and work pressure. In recent years, it has occurred frequently that college students cannot resolve their depression and gradually turn into depression, which eventually leads to accidentss. In the face of the increasingly severe depression of students, early assessment of depression is particularly important. The traditional assessment of depression mainly uses scale assessment and interview, but its subjectivity is strong, and it cannot avoid the situation that the subjects hide their emotions and conceal the facts, and the error is large. With the development of artificial intelligence, machine learning and deep learning is widely used in assessing depression, is mainly used for the scale of data mining, to promote the new assessment scale for depression, but still can’t change subjects fill out a form to hide the error caused. With the development of physiological data acquisition device and the further development of artificial intelligence technology, on the basis of the symptoms of depression in patients with obvious negative emotion tendency, early study compared the physiological indexes in patients with depression and healthy controls, found its differences, there are experiments prove that the method is effective, Therefore, the use of eye movement, electroencephalogram, expression and other physiological data as indicators has been widely used in the assessment of depression. Combined with machine learning and deep learning, an intelligent evaluation of physiological data is widely respected, promote the depression assessment more objective, more efficient, is beneficial to early screening depression group, promote the doctors, the teacher carries on the psychological counseling, promote the patient recover soon.