Depression has become a very common problem nowadays. Depression affects the mental state, so the patient suffering from it faces a problem of communicating his/her condition to the doctor. The depression is diagnosed on the basis of questionnaire set by the psychiatrist. This questionnaires are the different scales related to the symptoms for assessment of depression. Apart, from the questionnaire there are also laboratory test available for diagnosing depression. In the recent years, there are many techniques used for diagnosis like machine learning. Deep learning and Data mining methods. As depression is dependent on multiple disorders, so diagnosing it by using multiple modalities will be effective as compared to that of single modality. The single factor approaches are EEG, FMRI, Speech Signals; Twitter data etc. The multimodal approach will combine the different depression techniques to give a efficient or effective diagnosis. This paper reviews a different depression detection system that uses single modality and multiple modalities to diagnose depression. The survey shows the depression detection using multiple modalities has higher performance as compared to single modality approach.
CITATION STYLE
Naregalkar, P. R., & Shinde, A. A. (2023). Different Approaches of Diagnosing Depressed and Non-depressed Patients. In Lecture Notes in Electrical Engineering (Vol. 892, pp. 207–216). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-1645-8_21
Mendeley helps you to discover research relevant for your work.