Comprehensive review of depression detection techniques based on machine learning approach

Depression has become a serious disease that affects people's mental state and is an important part of the global disease burden. Research in this area began later in 1920 and has steadily increased due to the pandemic. Many studies on depression have been conducted worldwide. Still, obtaining comparable data for physiological and biological detection techniques, existing datasets, acquisition, and data classification methods in one platform is challenging. In addition, clinical methods using screening instruments, questionnaires, and episodic examinations to determine depression severity are time-consuming. Therefore, an alternative approach is to incorporate assessment into a person's daily activities in their environment or clinic, preferably via sensor technologies with smart systems. Recently, much research has been conducted on machine learning methods that can automatically decode mental and cognitive states to improve efficiency, accuracy, and precision. In this proposed review, depression detection methods based on electrical and acoustic signals and verbal and nonverbal communication are described in detail and then organized for practical/commercial applications. This paper also reviews the potential and challenges of various depression detection methods to serve as a suitable reference for upcoming researchers.