EUVIMEDEUVIMED entdecken
EvaluationsstudieOpen Access

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

Antonio Baldassarre iD, Martina Padovan, Alessandro Palla, Augusto Quercia, Rita Leonori, Stefano Dugheri, Nicola Mucci, Veronica Traversini

La Medicina del Lavoro · 2026

DOI: 10.23749/mdl.2026.18371 ↗

Kurz gefasst

Evaluationsstudie in der Zeitschrift La Medicina del Lavoro, 2026. Verfasst von Antonio Baldassarre und 7 weiteren Autor:innen. Beteiligte Einrichtung: Occupational Medicine, Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy. Hauptthemen laut MEDLINE: Artificial Intelligence, Pneumoconiosis, Occupational Health, Radiography, Thoracic. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Pneumoconioses remain an important occupational health issue, particularly in low- and middle-income countries. The International Labour Organization (ILO) Classification standardizes chest radiograph interpretation but requires trained readers and is affected by inter-reader variability. This study evaluated whether generative multimodal artificial intelligence (AI) models can approximate ILO-based diagnostic reasoning.

Methods

Eighty-two chest radiographs from the official NIOSH B Reader syllabus were analysed using four AI systems (GPT-4o, GPT-5, MedGemma-4B, MedGemma-27B). Each image was evaluated with a standardized prompt based on the 2022 revised ILO guidelines using deterministic settings. Model outputs were mapped to ILO codes and compared with the official answer keys of the ILO Standard Radiograph Set used for B Reader training and examination. Performance metrics included balanced accuracy, sensitivity, specificity, precision, and Matthews correlation coefficient (MCC). Bootstrap 95% confidence intervals, McNemar’s test, and Cohen’s κ assessed performance variability and agreement.

Results

All four AI models showed moderate diagnostic performance, with balanced accuracy ranging from 60.8% to 70.3%. Sensitivity remained limited (35.5%–54.9%), while specificity was consistently high (84.6%–86.2%). MedGemma-27B performed best for small opacities, GPT-5 for pleural abnormalities and for technical quality. Large opacities and rare findings were systematically under-detected. Statistical comparisons showed significant differences between models, although agreement patterns were broadly similar.

Conclusion

All AI models partially followed structured ILO radiographic criteria but did not achieve expert-level performance, confirming that they cannot replace certified B Readers. Larger, real-world datasets are needed to assess their potential clinical utility as supportive tools in occupational health surveillance programs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligencePneumoconiosisOccupational HealthRadiography, ThoracicHumansSensitivity and SpecificityGenerative Artificial Intelligence

Autor:innen und Institutionen

  • Occupational Medicine, Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy.
  • Preventive Medicine, Tuscany North-West Health Local Unit, Italy.
  • Intel Corporation, Santa Clara, USA.
  • (Former chief) Workplace Prevention and Safety Unit, Viterbo Health Local Unit, Italy.
  • Workplace Prevention and Safety Unit, Viterbo Health Local Unit, Italy.
  • Department of Life Science, Health, and Health Professions, Link Campus University, Rome, Italy.

ORCID-Profile: Antonio Baldassarre

Zitieren

APA

Baldassarre, A., Padovan, M., Palla, A., Quercia, A., Leonori, R., Dugheri, S., Mucci, N., & Traversini, V. (2026). Artificial Intelligence in Occupational Health Surveillance: Evaluating AI-Assisted ILO Classification of Radiographs of Pneumoconioses. La Medicina del Lavoro. https://doi.org/10.23749/mdl.2026.18371

Vancouver

Baldassarre A, Padovan M, Palla A, Quercia A, Leonori R, Dugheri S, et al. Artificial Intelligence in Occupational Health Surveillance: Evaluating AI-Assisted ILO Classification of Radiographs of Pneumoconioses. La Medicina del Lavoro. 2026. doi:10.23749/mdl.2026.18371

BibTeX
@article{Baldassarre2026,
  author = {Baldassarre, Antonio and Padovan, Martina and Palla, Alessandro and Quercia, Augusto and Leonori, Rita and Dugheri, Stefano and Mucci, Nicola and Traversini, Veronica},
  title = {Artificial Intelligence in Occupational Health Surveillance: Evaluating AI-Assisted ILO Classification of Radiographs of Pneumoconioses},
  journal = {La Medicina del Lavoro},
  year = {2026},
  doi = {10.23749/mdl.2026.18371}
}
Kostenlos starten →