ASSESSMENT OF IMPACT OF COVID-19 ON MENTAL HEALTH USING MACHINE LEARNING TECHNIQUES

Abstract

Major mental health disorders, like depression and anxiety, constitute a growing global public health challenge grossly exacerbated by large-scale crises, such as that presented by the COVID-19 pandemic. The unprecedented disruption brought on by prolonged lockdowns, social isolation, economic uncertainty, and health-related stressors has increased psychological distress throughout diverse populations, leading to an increase in undiagnosed and untreated mental health disorders. The early recognition and correct classification of depression and anxiety are thus very important to facilitate timely intervention and the development of appropriate mental health policies. Against this background, Machine Learning (ML) and Deep Learning (DL) approaches have emerged to have potential for use in the automated assessment of mental health. The proposed thesis seeks to move the state-of-the-art in automated detection of depression and anxiety by thoroughly examining classical ML, DL, and hybrid intelligent techniques based on psychological assessment data obtained during and post the COVID-19 era. Contrary to several prior approaches that have a narrow focus and binary classification boundaries, this study will prioritize scalability and multiclass prediction tasks. The thesis starts by performing a systematic literature review on ML,DL based mental health evaluation techniques, particularly in terms of COVID-19-related depression and anxiety. The literature survey analyzes different techniques, datasets, instruments, feature designs, and metrics that are currently used. Critical gaps in the literature are identified, including the absence of long-term studies, multi-class studies, the consideration of the size of datasets in analyses, rigorous statistical validation of the models, and the use of learning framework combinations. The thesis also examines post-pandemic mental health outcomes, highlighting emerging trends and research vi directions. These areas provide a foundation to the methodological contributions made in this thesis. Inthesubsequentphase,thethesisexaminestheeffectofthesizeofthedatasetonthe predictive capabilities of the traditional classifiers based on ML, such as the K-Nearest Neighbor (KNN) classifier, the Decision Trees (DT) classifier, the Random Forest (RF) classifier, and the Support Vector Machine (SVM) classifier. The experiment will make use of mental health survey data obtained during the COVID-19 pandemic. The results show that the model performs better with an increase in the size of the dataset, and it helps in understanding optimal levels of dataset collection needed to make a mental health model. The work is further continued with a comparative assessment of DL models to classify depression and anxiety. Different DL models like Artificial Neural Network (ANN), Recurrent Neural Network (RNN), Long Short-Term Memory Network (LSTM), Convolutional Neural Network (CNN), and TabNet are used on three different mental health datasets. The data shows that the performance of DL models,especiallyLSTMandCNN,issignificantlybetterthantraditionalMLmodelsin modeling complex interactions in features and multiclass classification. This outcome points to the effectiveness of applying DL models to model psychological patterns related to depression and anxiety. However, to circumvent some limitations in single models, some models in this research use a combination of several models with complementary properties. This combination will be in the form of hybrid classifiers; some examples include DT+KNN classification and RF+NNclassification. Theempiricaloutcomeshaveclearlyindicated the ability of the proposed hybrid models to provide significantly higher levels of predictive accuracy and robustness than the stand-alone classifiers, performing up to 99-100% accuracy on some datasets. This confirms the effectiveness of the hybrid learning approach for precise mental health prediction. The originalities in the thesis lie in the formulation of two predictive models for the detection of depression and anxiety. Firstly, the development of the multiclass Depression Anxiety-TabSVM (DA-TabSVM) hybrid model has taken place in order to tackle the complex, nonlinear nature of the data in the psychological tables. Secondly, the formulation of the Adaptive Sigma KNN (ASKNN) model has taken place. The vii model has the unique ability to alter the weight given to the surrounding samples through the adaptation of the sigma parameter. In traditional KNN models, this has not been the case. Thorough experimental studies, including cross-validation, analysis of Area Under the Curve– Receiver Operating Characteristic (AUC-ROC) curves, and statistical significance tests with the Friedman and Wilcoxon signed-rank tests, support that the new models clearly outperform existing baselines in ML. The effect-size analysis via Cohen’s d and Cliff’s Delta values strengthens the relevance of the obtained improvements. Furthermore, this thesis proposes a Feature-Weighted Adaptive Kernel KNN(FW-AK-KNN)modelthatincorporates feature importance and adaptive kernel basedneighborweighting toenhancebothaccuracyand interpretability inmental health prediction. On thewhole, this thesis makes a valuable contribution to a complete, scalable, and statistically valid framework for the automatic diagnosis of depression and anxiety using ML,DL,andhybridmodels. Withthedevelopmentoftrustworthyandefficientmethods of identifying mental health disorders at an earlier stage, the presented solutions contribute to global initiatives with regard to mental health issues and are in line with the United Nations (UN)’s Sustainable Development Goal (SDG) 3 and the importance of AI solutions in managing this burden worldwide.