Analyzing the Impact of Occupational Exposures on Male Fertility Indicators: A Machine Learning Approach
Abstract
Category: Epidemiology Tags: occupational exposure, male fertility, machine learning, electromagnetic fields, vibration, reproductive health, workplace safety DOI: 10.1016/j.reprotox.2025.108959 URL: pubmed.ncbi.nlm.nih.gov Overview Occupational exposures are critical factors affecting workers' reproductive health. This study investigates the impact of magnetic fields, electric fields, whole-body vibration, noise levels, and heat stress on male reproductive indicators using advanced machine learning models. The primary aim is to identify key risk factors and provide predictive insights into workers' reproductive health over the next decade. - Data were collected from 80 male workers in an automobile part manufacturing plant. - Demographic characteristics, occupational exposures, biochemical markers, hormone levels, and sperm parameters were analyzed. Findings - Five machine learning models (logistic regression, bagging classifier, extreme gradient boosting, random forest, and support vector machine) were trained and evaluated using 5-fold cross-validation to determine effective predictors of reproductive health outcomes. - Exposure to whole-body vibration, magnetic fields, electric fields, and heat stress were found to closely affect free testosterone levels. - SHAP analysis indicated Magnetic Field Exposure (0.339) and Wet Bulb Globe Temperature (0.138) as significant contributors, with Worker Age (0.244) being the most influential demographic factor negatively impacting Free Testosterone. - The XGBoost and Random Forest models achieved the highest predictive accuracy with AUC (0.99). - Random Forest model Importance: Electric Field Exposure (5%) and Magnetic Field Exposure (4.7%) showed the most substantial negative impact on Free Testosterone, followed by Worker Age (4.1%). Conclusion This study concludes that machine learning, particularly tree-based models like Random Forest and XGBoost, can effectively identify key occupational and demographic factors influencing male reproductive health. Electric and magnetic field exposures, age, work experience, and oxidative stress biomarkers emerged as the most critical predictors. Explainable AI methods revealed complex interactions among these factors. The 10-year forecast highlighted electric field exposure as the most significant long-term risk. These findings emphasize the need for targeted interventions to reduce electromagnetic and vibration exposures and to protect aging workers. ⚠️ The study highlights a clear connection between electromagnetic field exposure and decreased male reproductive health indicators, noting significant negative impacts from both magnetic and electric fields.
AI evidence extraction
Main findings
In data from 80 male workers, machine learning models identified occupational exposures (including magnetic fields, electric fields, whole-body vibration, and heat stress) as important predictors of free testosterone levels. Explainable AI analyses (e.g., SHAP and Random Forest importance) highlighted magnetic and electric field exposures and worker age as contributors associated with negative impacts on free testosterone, and the authors report a 10-year forecast in which electric field exposure was the most significant long-term risk.
Outcomes measured
- Free testosterone
- Biochemical markers
- Hormone levels
- Sperm parameters
- Male reproductive health indicators
Limitations
- Single workplace sample (automobile part manufacturing plant), which may limit generalizability
- Cross-sectional/observational design limits causal inference
- Exposure metrics (e.g., field strengths, measurement methods, timing) are not described in the provided abstract
- Model performance (AUC) is reported, but external validation is not described in the provided abstract
Suggested hubs
-
occupational-exposure
(0.95) Study evaluates workplace electric and magnetic field exposures and other occupational hazards in workers.
View raw extracted JSON
{
"publication_year": 2025,
"study_type": "cross_sectional",
"exposure": {
"band": null,
"source": "occupational (automobile part manufacturing plant)",
"frequency_mhz": null,
"sar_wkg": null,
"duration": null
},
"population": "80 male workers in an automobile part manufacturing plant",
"sample_size": 80,
"outcomes": [
"Free testosterone",
"Biochemical markers",
"Hormone levels",
"Sperm parameters",
"Male reproductive health indicators"
],
"main_findings": "In data from 80 male workers, machine learning models identified occupational exposures (including magnetic fields, electric fields, whole-body vibration, and heat stress) as important predictors of free testosterone levels. Explainable AI analyses (e.g., SHAP and Random Forest importance) highlighted magnetic and electric field exposures and worker age as contributors associated with negative impacts on free testosterone, and the authors report a 10-year forecast in which electric field exposure was the most significant long-term risk.",
"effect_direction": "harm",
"limitations": [
"Single workplace sample (automobile part manufacturing plant), which may limit generalizability",
"Cross-sectional/observational design limits causal inference",
"Exposure metrics (e.g., field strengths, measurement methods, timing) are not described in the provided abstract",
"Model performance (AUC) is reported, but external validation is not described in the provided abstract"
],
"evidence_strength": "low",
"confidence": 0.7399999999999999911182158029987476766109466552734375,
"peer_reviewed_likely": "yes",
"stance": "concern",
"stance_confidence": 0.7800000000000000266453525910037569701671600341796875,
"summary": "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.",
"key_points": [
"Data were collected from 80 male workers in an automobile part manufacturing plant and included exposures and reproductive-related biomarkers.",
"Five machine learning models were trained with 5-fold cross-validation to identify predictors of reproductive health outcomes.",
"Whole-body vibration, magnetic fields, electric fields, and heat stress were reported to closely affect free testosterone levels.",
"SHAP analysis highlighted magnetic field exposure and heat stress (WBGT) as notable contributors, with age negatively impacting free testosterone.",
"Random Forest importance ranked electric and magnetic field exposures among the strongest negative contributors to free testosterone in the model.",
"The authors conclude that reducing electromagnetic and vibration exposures may help protect workers’ reproductive health, particularly for aging workers."
],
"categories": [
"Occupational Exposure",
"Male Fertility",
"Epidemiology",
"RF-EMF/ELF-EMF",
"Machine Learning"
],
"tags": [
"Occupational Exposure",
"Male Fertility",
"Reproductive Health",
"Electromagnetic Fields",
"Magnetic Field Exposure",
"Electric Field Exposure",
"Whole-Body Vibration",
"Heat Stress",
"Noise Exposure",
"Free Testosterone",
"Sperm Parameters",
"Explainable AI",
"Random Forest",
"XGBoost",
"SHAP"
],
"keywords": [
"occupational exposure",
"male fertility",
"machine learning",
"electromagnetic fields",
"vibration",
"reproductive health",
"workplace safety"
],
"suggested_hubs": [
{
"slug": "occupational-exposure",
"weight": 0.9499999999999999555910790149937383830547332763671875,
"reason": "Study evaluates workplace electric and magnetic field exposures and other occupational hazards in workers."
}
],
"social": {
"tweet": "Study of 80 male factory workers used ML models to identify occupational predictors of reproductive indicators. Electric and magnetic field exposures, vibration, heat stress, and age were highlighted as key predictors linked to lower free testosterone. (Reproductive Toxicology, 2025)",
"facebook": "A study in an automobile parts plant (80 male workers) applied machine learning to assess how workplace exposures relate to male reproductive indicators. The analysis highlighted electric and magnetic field exposures, vibration, heat stress, and age as important predictors, including associations with lower free testosterone.",
"linkedin": "Reproductive Toxicology (2025): In a dataset of 80 male workers, machine learning and explainable AI (e.g., SHAP) were used to identify occupational predictors of male reproductive indicators. Electric and magnetic field exposures, vibration, heat stress, and age emerged as key predictors, including negative associations with free testosterone."
}
}
AI can be wrong. Always verify against the paper.
Comments
Log in to comment.
No comments yet.