Swarm intelligence-based novel machine learning approach for forecasting mental illness

Stress takes place as one of the leading health challenges that exists in present-day society. The worldwide population suffers serious mental conditions including anxiety and depression due to this condition. The current methods for stress assessment do not meet accuracy standards and take substantial time to complete. üficient mental health monitoring tools and limited medical professional availability create a strong requirement for technological advancements in mental healthcare identification. This research creates a novel framework for psychiatric disorder prognosis using Enhanced Salp Swarm Optimization-based Support Vector Machine (ESSO-SVM). The objective is designed to propose a highly reliable and accurate method to differentiate between healthy subjects and those undergoing stress conditions with early detection and intervention. The approach proposed is based on comprehensive preprocessing of data by Min–Max normalization to scale features for the best performance of the model. Independent Component Analysis (ICA) is used to reduce the dimensionality of the data while retaining the most essential information. This approach optimizes SVMs with the ESSO algorithm by enhancing its capabilities through improved parameter-tuning, and feature selection. Experimental evaluation shows that the ESSO-SVM framework achieves 98% accuracy, 88% sensitivity, 90% specificity, and an error rate of 67%. These results show that the model is much better at differentiating stressed subjects from healthy participants than traditional methods. The combined ESSO and SVM integrated framework promises to be a powerful and reliable forecasting solution for mental illness. The approach addresses the limitations of conventional diagnostic methods to support early stress detection and better management of mental health. Findings indicate that swarm-intelligent machine learning techniques can be utilized to advance healthcare solutions and enhance the quality of life for people facing mental health challenges.