Machine Learning, Deep Learning, and Data PreprocessingTechniques for Detecting, Predicting, and Monitoring Stress andStress-Related Mental Disorders:Scoping Review

Background: Mental stress and its consequent mental health disorders (MDs) constitute a significant public health issue. Withthe advent of machine learning (ML), there is potential to harness computational techniques for better understanding and addressingmental stress and MDs. This comprehensive review seeks to elucidate the current ML methodologies used in this domain to pavethe way for enhanced detection, prediction, and analysis of mental stress and its subsequent MDs.Objective: This review aims to investigate the scope of ML methodologies used in the detection, prediction, and analysis ofmental stress and its consequent MDs.Methods: Using a rigorous scoping review process with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews andMeta-Analyses extension for Scoping Reviews) guidelines, this investigation delves into the latest ML algorithms, preprocessingtechniques, and data types used in the context of stress and stress-related MDs.Results: A total of 98 peer-reviewed publications were examined for this review. The findings highlight that support vectormachine, neural network, and random forest models consistently exhibited superior accuracy and robustness among all MLalgorithms examined. Physiological parameters such as heart rate measurements and skin response are prevalently used as stresspredictors due to their rich explanatory information concerning stress and stress-related MDs, as well as the relative ease of dataacquisition. The application of dimensionality reduction techniques, including mappings, feature selection, filtering, and noisereduction, is frequently observed as a crucial step preceding the training of ML algorithms.Conclusions: The synthesis of this review identified significant research gaps and outlines future directions for the field. Theseencompass areas such as model interpretability, model personalization, the incorporation of naturalistic settings, and real-timeprocessing capabilities for the detection and prediction of stress and stress-related MDs.