Artificial Intelligence in Occupational Health Surveillance: Evaluating AI-Assisted ILO Classification of Radiographs of Pneumoconioses

Key Points

• The aim is to evaluate the performance of AI models in classifying radiographs based on ILO criteria for pneumoconioses.
• Assessment of AI models against structured ILO radiographic criteria.
• Comparison with certified B Readers to determine expert-level performance.
• AI models partially followed ILO criteria but did not match expert-level performance.
• The need for larger, real-world datasets was identified to evaluate the clinical utility of AI in practice.