Unravelling the gait and balance: A novel approach for detecting depression in young healthy individuals

• Published in: Journal of intelligent & fuzzy systems Vol. 45; no. 6; pp. 12079 - 12093
• Main Authors: Maguluri, Lakshmana Phaneendra, Vinya, Viyyapu Lokeshwari, Goutham, V., Uma Maheswari, B., Kumar, Boddepalli Kiran, Musthafa, Syed, Manikandan, S., Srivastava, Suraj, Munjal, Neha
• Format: Journal Article
• Language: English
• Published: Amsterdam IOS Press BV 02.12.2023
• Subjects: Algorithms; Atmospheric pressure; Balance; Evaluation; Mental depression; Pattern recognition; Physiology; Pressure sensors; Sensors
• ISSN: 1064-1246; 1875-8967
• DOI: 10.3233/JIFS-235058

Depression is a prevalent mental health disorder that affects people of all ages and origins; therefore, early detection is essential for timely intervention and support. This investigation proposes a novel method for detecting melancholy in young, healthy individuals by analysing their gait and balance patterns. In order to accomplish this, a comprehensive system is designed that incorporates cutting-edge technologies such as a Barometric Pressure Sensor, Beck Depression Inventory (BDI), and t-Distributed Stochastic Neighbour Embedding (t-SNE) algorithm. The system intends to capitalize on the subtle motor and physiological changes associated with melancholy, which may manifest in a person’s gait and balance. The Barometric Pressure Sensor is used to estimate variations in altitude and vertical velocity, thereby adding context to the evaluation. The mood states of participants are evaluated using the BDI, a well-established psychological assessment instrument that provides insight into their emotional health. Integrated and pre-processed data from the Barometric Pressure Sensor, BDI responses, and gait and balance measurements. The t-SNE algorithm is then used to map the high-dimensional data into a lower-dimensional space while maintaining the local structure and identifying underlying patterns within the dataset. The t-SNE algorithm improves visualization and pattern recognition by reducing the dimensionality of the data, allowing for a more nuanced analysis of depression-related markers. As the proposed system combines objective physiological measurements with subjective psychological assessments, it has the potential to advance the early detection and prediction of depression in young, healthy individuals. The results of this exploratory study have implications for the development of non-intrusive and easily accessible instruments that can assist healthcare professionals in identifying individuals at risk and implementing targeted interventions.