Diagnosis of depression level using multimodal approaches using deep learning techniques with multiple selective features

Abstract

Depression is a serious mental health condition that may lead to poor mental and emotional functioning at work, at school and in the family causing the mental imbalance. In worst scenarios, depression may lead to severe anxiety or suicide. Hence, it is necessary to diagnose depression at early stages. This paper elaborates the development of a novel approach for a convolutional neural network model that can examine facial images from the recorded interview sessions to discover facial patterns that could indicate depression level. The user‐generated data helps to distinguish between different depressive groups with depression symptoms that can manifest people with various mental illnesses in different ways. In particular, we want to automatically predict the depression scale and differentiate depression from other mental disorders using the patient's psychiatric illness history and dynamic textual descriptions extracted from the user inputs. We apply the k‐nearest neighbour algorithm on the dynamic textual descriptors to make a linguistic analysis for classifying mental illness into different classes. We apply dimensionality reduction and regression using the Random Forest algorithm to predict the depression scale. The proposed framework is an extension to pre‐existing frameworks, replacing the handcrafted feature extraction technique with the deep feature extraction. The model performs 2.7% better than existing frameworks in facial detection and feature extraction.

Efficacy of Progressive Muscle Relaxation in Adults for Stress, Anxiety, and Depression: A Systematic Review

“…When measuring the efficacy of PMR combined with other interventions versus PMR as a standalone relaxation technique, there are two (2) studies in this review 66,68 that found combining PMR with other variables to be more effective compared to the PMR training alone in their respective study. Korkut, Ülker, Çidem, Şahin 66 found combining PMR with nature sound to be more effective in reducing anxiety among the nursing students, while Robb 68 highlighted that combination of PMR with music to be more effective in reducing anxiety among the university students compared to PMR alone.…”

“…These poor conditions could lead to more serious psychiatric disorders or conditions such as clinical anxiety, depression, bipolar disorders, schizophrenia, or even suicide. 2–4 The aforementioned statement emphasizes the critical need to swiftly address stress, anxiety, and depression as these are major contributors to the wider range of mental health issues that people may encounter.…”

“…These poor conditions could lead to more serious psychiatric disorders or conditions such as clinical anxiety, depression, bipolar disorders, schizophrenia, or even suicide. [2][3][4] The aforementioned statement emphasizes the critical need to swiftly…”

Deep‐SQA: A deep learning model using motor activity data for objective sleep quality assessment assisting digital wellness in healthcare 5.0

“…Several recent research gyrated around applying Machine Learning (ML) and DL methods to assess mental health indicators using actigraph measurements (Choi et al, 2021; Garcia‐Ceja, Riegler, Jakobsen, Tørresen, et al, 2018, 2020; Raihan et al, 2021; Rodríguez‐Ruiz et al, 2019, 2020; Tazawa et al, 2020). Several research (Frogner et al, 2019; Garcia‐Ceja, Riegler, Jakobsen, Torresen, et al, 2018; Jakobsen et al, 2020; Kulam, 2019; Meshram & Rambola, 2022) have been published that show how DL techniques may be used to inevitably extract features from the dataset recordings. However, the reported studies primarily focus on detection of depression as the key indicator of mental health.…”

Multi-Class Adaptive Active Learning for Predicting Student Anxiety

“…Machine learning algorithms can analyze various data sources, such as student's academic performance, participation levels, and physiological data like heart rate or skin conductance [9]. These algorithms can then identify patterns and early warning signs of anxiety [10]. Integrating active learning and machine learning techniques into the educational process makes it possible to address these indicators [11].…”