Managing Human Factor Risk: An Interpretable Decision Support System for Preselecting PTSD Symptoms in Occupational Groups

Occupational stress is a critical human factor that affects efficiency, safety, and the continuity of operational processes, particularly in high-risk professions such as uniformed services. The aim of this study was to develop and validate an interpretable decision support system (DSS) for the early pre-screening of employees exhibiting symptoms of post-traumatic stress disorder (PTSD). To this end, the J48 decision tree algorithm was applied to extract classification rules based on psychological symptoms defined in the DSM-5. The performance of the J48 model was compared with Support Vector Machine and Random Forest algorithms. Among the evaluated models, J48 demonstrated the highest overall effectiveness, achieving top results across all key metrics, including an F1-score of 0.976 and a ROC Area of 0.987. The generated classification rules ensure model transparency and interpretability – features essential for practical implementation in organizational occupational health procedures. The proposed tool contributes to the field of human factors engineering by offering a practical solution for managing mental health risks, ultimately supporting improved safety and operational performance in organizational settings.