This study explores the use of neural networks for occupational disease risk prediction based on worker and workplace characteristics. The goal is to develop a tool to assist occupational physicians in monitoring workers. Using a dataset from the Italian MalProf National Surveillance System (2019-2023), an ensemble of one-vs-all classifiers is trained to identify six prevalent disease classes. Performance is evaluated using accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The results indicate promising performance. The specificity values for all six disease classes under study exceed 0.920 on average over 10 runs, and for five out of six classes, they surpass 0.967. Regarding sensitivity, the performance is positive (average over 10 runs greater than 0.920) for all classes, except for “Carpal Tunnel Syndrome and other Mononeuropathies of Upper Limb”, which performs less effectively (average over 10 runs = 0.655). Future research could focus on optimizing neural network architectures, applying oversampling techniques for underrepresented classes, and analyzing misclassifications.
References
[1]
Mukherjee, C., Gupta, K. and Nallusamy, R. (2012) A Decision Support System for Employee Healthcare. 2012 Third International Conference on Services in Emerging Markets, Mysore, 12-15 December 2012, 130-135. https://doi.org/10.1109/icsem.2012.25
[2]
Paul, R. and Hoque, A.S.M.L. (2010) Clustering Medical Data to Predict the Likelihood of Diseases. 2010 Fifth International Conference on Digital Information Management (ICDIM), Thunder Bay, 5-8 July 2010, 44-49. https://doi.org/10.1109/icdim.2010.5664638
[3]
Huang, Z.H., Yu, D.H. and Zhao, J.Y. (2000) Application of Neural Networks with Linear and Nonlinear Weights in Occupational Disease Incidence Forecast. IEEE APCCAS 2000. 2000 IEEE Asia-Pacific Conference on Circuits and Systems. Electronic Communication Systems. (Cat. No.00EX394), Tianjin, 4-6 December 2000, 383-386. https://doi.org/10.1109/apccas.2000.913515
[4]
Yuan, C., Li, G., Peihong, Z. and Li, C. (2010). Artificial Neural Network Modeling of Prevalence of Pneumoconiosis among Workers in Metallurgical Industry—A Case Study. 2010 International Conference on Intelligent System Design and Engineering Application, Changsha, 13-14 October 2010, 388-393. https://doi.org/10.1109/isdea.2010.111
[5]
Filho, D.V., dos Santos, M.A., Ludermir, T.B. and Silva, M.J. (2002) A Fuzzy Approach to Support a Musculoskeletal Disorders Diagnosis. VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings, Pernambuco, 11-14 November 2002, 154. https://doi.org/10.1109/sbrn.2002.1181461
[6]
Martiniano, A., Ferreira, R.P., Sassi, R.J. and Affonso, C. (2012) Application of a Neuro Fuzzy Network in Prediction of Absenteeism at Work. Iberian Conference on Information Systems and Technologies (CISTI), Madrid, 20-23 June 2012, 1-4.
[7]
Liu, H., Tang, Z., Yang, Y., Weng, D., Sun, G., Duan, Z., et al. (2009) Identification and Classification of High Risk Groups for Coal Workers’ Pneumoconiosis Using an Artificial Neural Network Based on Occupational Histories: A Retrospective Cohort Study. BMCPublicHealth, 9, Article No. 366. https://doi.org/10.1186/1471-2458-9-366
[8]
Srinivas, K., Rao, G.R. and Govardhan, A. (2010) Analysis of Coronary Heart Disease and Prediction of Heart Attack in Coal Mining Regions Using Data Mining Techniques. 2010 5th International Conference on Computer Science & Education, Hefei, 24-27 August 2010, 1344-1349. https://doi.org/10.1109/iccse.2010.5593711
[9]
Di Noia, A., Montanari, P. and Rizzi, A. (2014) Occupational Diseases Risk Prediction by Cluster Analysis and Genetic Optimization. Proceedings of the International Conference on Evolutionary Computation Theory and Applications, Rome, 22-24 October, 68-75. https://doi.org/10.5220/0005077800680075
[10]
di Noia, A., Montanari, P. and Rizzi, A. (2015) Occupational Diseases Risk Prediction by Genetic Optimization: Towards a Non-Exclusive Classification Approach. In: Merelo, J.J., Rosa, A., Cadenas, J.M., Dourado, A., Madani, K. and Filipe, J., Eds., Computational Intelligence, Springer, 63-77. https://doi.org/10.1007/978-3-319-26393-9_5
[11]
Di Noia, A., Martino, A., Montanari, P. and Rizzi, A. (2019) Supervised Machine Learning Techniques and Genetic Optimization for Occupational Diseases Risk Prediction. SoftComputing, 24, 4393-4406. https://doi.org/10.1007/s00500-019-04200-2
