A large-scale new study out of China has found that workers exposed to both occupational noise and industrial dust face significantly higher risks of developing noise-induced hearing loss (NIHL) than those exposed to noise alone. The research, published in Scientific Reports, used machine learning models to identify key risk factors for NIHL and to assess the added impact of combined exposure in the workplace.
The authors analyzed data from 14,145 workers who underwent occupational health examinations at the Hebei Medical Examination Center between 2017 and 2023. Of those, 627 had been diagnosed with occupational noise-induced hearing loss (ONIHL). Participants included in the study had no known underlying conditions or alternative causes of hearing loss, such as ototoxic medications or infectious diseases.
The goal was to assess the influence of environmental exposure and health-related variables on hearing outcomes.
Why the Study Matters
While noise has long been recognized as a cause of hearing loss, the interaction between noise and dust exposure is less well understood. Previous research has suggested that both exposures can impact cardiovascular and metabolic health, and the authors sought to examine how they may jointly influence hearing loss and related health markers such as blood pressure, blood glucose, and body mass index (BMI).
By applying both traditional statistical methods and machine learning algorithms, the study aimed to identify individual risk factors for ONIHL and assess how accurately predictive models could forecast hearing loss in occupational settings.
Key Findings
The data revealed several important associations:
- Combined exposure to noise and dust significantly increased the risk of ONIHL, compared to noise exposure alone.
- Male workers, older age, smoking, high diastolic blood pressure, and elevated fasting blood glucose were identified as independent risk factors for ONIHL.
- Interestingly, elevated systolic blood pressure was associated with a reduced risk of ONIHL in multivariate analysis, a finding the authors suggest may be related to differences in health management behaviors or circulatory dynamics affecting the inner ear.
Identifying Who’s Most at Risk
Further analysis of the data revealed that men between the ages of 30 and 39, with fewer than 10 years of work experience and no existing metabolic or cardiovascular health conditions, were particularly vulnerable to noise-induced hearing loss when exposed to both occupational noise and dust.
In addition to increased hearing risk, workers exposed to both hazards showed higher rates of elevated diastolic blood pressure, greater body mass index (particularly obesity), higher fasting blood glucose levels, and more frequent signs of liver dysfunction.
These findings suggest that the health impacts of combined noise and dust exposure may extend beyond the ears, affecting broader aspects of metabolic and cardiovascular health.
Using Machine Learning to Improve Risk Prediction
To better understand who is most at risk for occupational hearing loss, the researchers used machine learning to analyze health and exposure data from more than 14,000 workers. These tools helped identify patterns and highlight which factors were most strongly linked to hearing loss.
The analysis showed that age and smoking were the most consistent risk factors across all models. Other factors—such as combined exposure to noise and dust, blood pressure, and blood sugar levels—also played a role, but their influence varied.
By using machine learning, the researchers were able to sort through complex data and pinpoint which groups of workers may need extra attention when it comes to hearing protection and overall health monitoring.
Implications for Workplace Hearing Health
The findings highlight the need for more comprehensive approaches to hearing conservation in occupational settings. The authors note that hearing loss risk assessments should consider the combined impact of multiple exposures, including both noise and dust, rather than focusing on noise alone.
Younger and less experienced workers may need additional education and protective measures, especially in industries where combined exposures are common. The inclusion of broader health markers—such as blood pressure and glucose levels—could also improve the accuracy and effectiveness of hearing health screenings.
The use of machine learning in this context shows promise as a tool for identifying workers at elevated risk and guiding personalized prevention strategies. These models could eventually support more targeted interventions, including the use of specific protective equipment or tailored health monitoring.
Study Limitations and Future Research
While this study offers important insights into the impact of combined noise and dust exposure on hearing and overall health, the authors note several limitations. Because the data was collected retrospectively, it cannot prove cause and effect. In addition, the study lacked detailed information about the specific types and levels of dust exposure, which limits the ability to fully understand how different environmental conditions may contribute to risk.
Even so, the findings add to growing evidence that workplace hearing loss is shaped by multiple factors—not just noise alone. Younger male workers with fewer years of experience appear especially vulnerable when exposed to both hazards. As machine learning tools continue to improve, they offer a promising way to identify high-risk individuals and guide more targeted prevention strategies. Future research that includes real-time exposure tracking, genetic influences, and long-term follow-up could further strengthen efforts to reduce the burden of occupational hearing loss.
Reference:
- Li, Y., Sun, X., Qu, Y. et al. Applying machine learning algorithms to explore the impact of combined noise and dust on hearing loss in occupationally exposed populations. Sci Rep 15, 9097 (2025). https://doi.org/10.1038/s41598-025-93976-5
