This occupational epidemiology study used machine learning to evaluate whether workplace exposures (including magnetic and electric fields, vibration, noise, and heat stress) predict male reproductive indicators in 80 workers. The models and explainable AI outputs highlighted magnetic and electric field exposures and age as key predictors linked to lower free testosterone. The authors also report a 10-year forecast identifying electric field exposure as the most important long-term risk factor.

This paper presents a mixed-method study protocol examining electromagnetic hypersensitivity (EHS) in relation to mobile phone radiofrequency radiation exposure among undergraduate students. The quantitative component aims to identify predictors of EHS using a biopsychosocial model, while the qualitative component explores individual experiences through in-depth interviews. The abstract provides study design details and sample size but does not report study results.

This analytical study evaluated machine learning models (SVM and Random Forest) to predict health symptoms in adults living near mobile phone base stations. The SVM model reportedly achieved high predictive performance for headache, sleep disturbance, dizziness, vertigo, and fatigue, and outperformed Random Forest and prior models. The abstract concludes that proximity to base stations is connected with increased prevalence of several symptoms and emphasizes distance, age, and duration of residence as key predictors.