Establish an Effective Framework for Accurate Prediction of Employee Mental Health for Public Health

Abstract

Employee mental health is a primary feature of workplace efficiency and overall public health. With rising mental health problems impaired by variables contains stress, burnout, and isolation, there is an urgent need for effective prediction models that can identify at-risk employees. This study proposes a robust predictive model utilizing dynamic lion optimized VGG16 (DLO-VGG16), for employee mental health prediction represents a significant advancement in public healthcare. The use of these sophisticated prediction models can improve medical results for groups at risk and is essential in the battle against heart disease. Employee’s mental health data collected from Kaggle website. The data preprocessing phase employed Z-score normalization to standardize input values, thereby addressing data inconsistencies and errors. The Sequential Forward Floating Search Algorithm (SFFS) was utilized for extracting the employee’s mental health. This enhanced heuristic search method begins with an empty feature set, incrementally adding features until the optimal set is identified. The proposed DLO-VGG16 framework to balance accuracy, ROC curve, and f1-score ensuring reliable detection and forecasting of employee mental health issues, thereby contributing to the broader public health landscape.