Probability of somatic disease detection in metallurgic production workers using gradient boosting and fuzzy logic methods

View or download the full article: 
PDF icon health-risk-analysis-2026-3-9.pdf
UDC: 
613.6:669:616-036.22:004.8
DOI: 
10.21668/health.risk/2026.3.09.eng
Authors: 

E.R. Abdrakhmanova1,2, I.I. Zaydullin1, A.I. Borisova1, E.T. Valeeva1,2, L.M. Masyagutova1,2, T.K. Valeev1

Organization: 

1Ufa Research Institute of Occupational Medicine and Human Ecology, 94 Stepana Kuvykina St., Ufa, 450106, Russian Federation
2Bashkir State Medical University, 3 Lenina St., Ufa, 450008, Russian Federation

Abstract: 

The study object was represented by metallurgical production workers undergoing periodic medical examinations under exposure to a complex of occupational and work-related factors. The aim of the study was to assess the probability of detecting somatic pathology in metallurgical production workers exposed to a complex of occupational and non-occupational factors using machine learning, in order to scientifically substantiate approaches to forming preventive observation groups.

A cross-sectional epidemiological study included 1,899 workers. Age, length of service in harmful working conditions, smoking status, and 32 binary occupational exposure variables were used as input predictors. Clinical, laboratory, and instrumental indicators used for diagnostic verification were excluded from the model to prevent artificial overestimation of predictive accuracy. CatBoost was applied for prediction, SHAP analysis for interpreting predictor contributions, and ANFIS for formalizing the identified dependencies. Model performance was assessed using AUC-ROC, sensitivity, and specificity.

Musculoskeletal diseases and circulatory system diseases prevailed in the structure of detected pathology. The best dis-criminative ability was obtained for diseases of the ear and mastoid process (AUC-ROC = 0.820), musculoskeletal diseases (0.746), and circulatory system diseases (0.722). Models for respiratory, digestive, eye, and nervous system diseases did not demonstrate sufficient predictive performance for practical interpretation. SHAP analysis showed that age made the greatest contribution to prediction; among occupational and behavioral factors, work hardness, occupational noise, and smoking were the most significant. ANFIS modeling made it possible to construct length-of-service risk profiles and identify factor combinations associated with an increased probability of ear, musculoskeletal, and circulatory system diseases.

The proposed approach can be used for preliminary risk stratification during periodic medical examinations, formation of follow-up groups, and substantiation of indications for more detailed examination according to the most relevant pathology profile.

Keywords: 
metallurgical production, working conditions, occupational risk, somatic pathology, periodic medical examination, machine learning, CatBoost, SHAP, ANFIS, fuzzy logic
Abdrakhmanova E.R., Zaydullin I.I., Borisova A.I., Valeeva E.T., Masyagutova L.M., Valeev T.K. Probability of somatic disease detection in metallurgic production workers using gradient boosting and fuzzy logic methods. Health Risk Analysis, 2026, no. 3, pp. 96–105. DOI: 10.21668/health.risk/2026.3.09.eng
References: 
  1. Bukhtiyarov I.V. Current state and main directions of preservation and strengthening of health of the working popula-tion of Russia. Meditsina truda i promyshlennaya ekologiya, 2019, vol. 59, no. 9, pp. 527–532. DOI: 10.31089/1026-9428-2019-59-9-527-532 (in Russian).
  2. Zibarev E.V., Bukhtiyarov I.V., Vostrikova S.M., Kravchenko O.K., Umnitsyna O.B., Bessonova A.K., Mukhin K.S. Risk factors for the development of professional unfit health status among workers in harmful working conditions. Gigiena i sanitariya, 2025, vol. 104, no. 8, pp. 974–983. DOI: 10.47470/0016-9900-2025-104-8-974-983 (in Russian).
  3. Chebotarev A.G., Sementsova D.D. Comprehensive assessment of working conditions and occupational disease rates at mining and metallurgical enterprises. Gornaya promyshlennost', 2021, no. 1, pp. 114–119. DOI: 10.30686/1609-9192-2021-1-114-119 (in Russian).
  4. Shur P.Z., Redko S.V., Fadeev A.G., Goryaev D.V., Fokin V.A. Assessment of working conditions and health conditions of employees of non-ferrous metallurgy enterprises. Meditsina truda i promyshlennaya ekologiya, 2023, vol. 63, no. 8, pp. 537–544. DOI: 10.31089/1026-9428-2023-63-8-537-544 (in Russian).
  5. Masyagutova L.M., Abdrakhmanova E.R., Bakirov A.B., Gimranova G.G., Akhmetshina V.T., Gizatullina L.G., Gabdulvaleeva E.F., Volgareva A.D., Hafizova A.S. The role of working conditions in the formation of occupational morbidity of workers in metallurgical production. Gigiena i sanitariya, 2022, vol. 101, no. 1, pp. 47–52. DOI: 10.47470/0016-9900-2022-101-1-47-52 (in Russian).
  6. Panev N.I., Korotenko O.Yu., Filimonov S.N., Semenova E.A., Panev R.N. Prevalence of cardiovascular pathology in workers of the aluminum industry. Gigiena i sanitariya, 2019, vol. 98, no. 3, pp. 276–279. DOI: 10.18821/0016-9900-2019-98-3-276-279 (in Russian).
  7. Vermeulen R., Schymanski E.L., Barabási A.-L., Miller G.W. The exposome and health: Where chemistry meets biol-ogy. Science, 2020, vol. 367, no. 6476, pp. 392–396. DOI: 10.1126/science.aay3164
  8. Nwanosike E.M., Conway B.R., Merchant H.A., Hasan S.S. Potential applications and performance of machine learn-ing techniques and algorithms in clinical practice: a systematic review. Int. J. Med. Inform., 2022, vol. 159, pp. 104679. DOI: 10.1016/j.ijmedinf.2021.104679
  9. Uddin S., Khan A., Hossain M.E., Moni M.A. Comparing different supervised machine learning algorithms for disease prediction. BMC Med. Inform. Decis. Mak., 2019, vol. 19, no. 1, pp. 281. DOI: 10.1186/s12911-019-1004-8
  10. Ali S., Akhlaq F., Imran A.S., Kastrati Z., Daudpota S.M., Moosa M. The enlightening role of explainable artificial intelligence in medical and healthcare domains: a systematic literature review. Comput. Biol. Med., 2023, vol. 166, pp. 107555. DOI: 10.1016/j.compbiomed.2023.107555
  11. Czmil A. Comparative study of fuzzy rule-based classifiers for medical applications. Sensors (Basel), 2023, vol. 23, no. 2, pp. 992. DOI: 10.3390/s23020992
  12. Prokhorenkova L., Gusev G., Vorobev A., Dorogush A.V., Gulin A. CatBoost: unbiased boosting with categorical features. NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montréal, Canada, 2018, pp. 6639–6649.
  13. Lundberg S.M., Lee S.-I. A unified approach to interpreting model predictions. NIPS'17: Proceedings of the 31st In-ternational Conference on Neural Information Processing Systems, Long Beach California USA, 2017, pp. 4768–4777.
  14. Walia N., Singh H., Sharma A. ANFIS: Adaptive Neuro-Fuzzy Inference System – A survey. International Journal of Computer Applications, 2015, vol. 123, no. 13, pp. 32–38. DOI: 10.5120/ijca2015905635
  15. Lan Y., Zhan X., Wang Z., Jiang D., Li X., Peng C. Global prevalence and associated risk factors of work-related musculoskeletal disorders among steelworkers: a systematic review and meta-analysis. Front. Public Health, 2026, vol. 14, pp. 1718101. DOI: 10.3389/fpubh.2026.1718101
  16. Leino-Arjas P. Smoking and musculoskeletal disorders in the metal industry: a prospective study. Occup. Environ. Med., 1998, vol. 55, no. 12, pp. 828–833. DOI: 10.1136/oem.55.12.828
  17. Cillekens B., Huysmans M.A., Holtermann A., van Mechelen W., Straker L., Krause N., van der Beek A.J., Coenen P. Physical activity at work may not be health enhancing. A systematic review with meta-analysis on the association between oc-cupational physical activity and cardiovascular disease mortality covering 23 studies with 655 892 participants. Scand. J. Work Environ. Health, 2022, vol. 48, no. 2, pp. 86–98. DOI: 10.5271/sjweh.3993
  18. Lie A., Skogstad M., Johannessen H.A., Tynes T., Mehlum I.S., Nordby K.-C., Engdahl B., Tambs K. Occupational noise exposure and hearing: a systematic review. Int. Arch. Occup. Environ. Health, 2016, vol. 89, no. 3, pp. 351–372. DOI: 10.1007/s00420-015-1083-5
  19. Ferrite S., Santana V. Joint effects of smoking, noise exposure and age on hearing loss. Occup. Med. (Lond.), 2005, vol. 55, no. 1, pp. 48–53. DOI: 10.1093/occmed/kqi002
  20. Sung J.H., Sim C.S., Lee C.-R., Yoo C.-I., Lee H., Kim Y., Lee J. Relationship between cigarette smoking and hearing loss in workers exposed to occupational noise. Ann. Occup. Environ. Med., 2013, vol. 25, no. 1, pp. 8. DOI: 10.1186/2052-4374-25-8
  21. Zaitseva N.V., Savochkina А.А., Zemlyanova М.А., Goryaev D.V., Fadeev А.G. Methodology for assessing and pre-dicting personalized occupational health risks based on adaptive neural fuzzy network for image recognition. Health Risk Analysis, 2025, no. 2, pp. 4–15. DOI: 10.21668/health.risk/2025.2.01.eng
Received: 
29.04.2026
Approved: 
01.06.2026
Accepted for publication: 
27.09.2026

You are here

Home