Human-Centered Explainable Artificial Intelligence: Automotive Occupational Health Protection Profiles in Prevention Musculoskeletal Symptoms

Overview

Journal Int J Environ Res Public Health

Publisher MDPI

Specialties Environmental Health
Public Health

Date 2022 Aug 12

PMID 35954919

Authors

Nafiseh Mollaei

Carlos Fujao

Luis Silva

Joao Rodrigues

Catia Cepeda

Hugo Gamboa

Affiliations

Soon will be listed here.

Abstract

In automotive and industrial settings, occupational physicians are responsible for monitoring workers' health protection profiles. Workers' Functional Work Ability (FWA) status is used to create Occupational Health Protection Profiles (OHPP). This is a novel longitudinal study in comparison with previous research that has predominantly relied on the causality and explainability of human-understandable models for industrial technical teams like ergonomists. The application of artificial intelligence can support the decision-making to go from a worker's Functional Work Ability to explanations by integrating explainability into medical (restriction) and support in contexts of individual, work-related, and organizational risk conditions. A sample of 7857 for the prognosis part of OHPP based on Functional Work Ability in the Portuguese language in the automotive industry was taken from 2019 to 2021. The most suitable regression models to predict the next medical appointment for the workers' body parts protection were the models based on CatBoost regression, with an RMSLE of 0.84 and 1.23 weeks (mean error), respectively. CatBoost algorithm is also used to predict the next body part severity of OHPP. This information can help our understanding of potential risk factors for OHPP and identify warning signs of the early stages of musculoskeletal symptoms and work-related absenteeism.

Citing Articles

Ethical considerations in telehealth and artificial intelligence for work related musculoskeletal disorders: A scoping review.

Karaibrahimoglu A, Ince F, Hassanzadeh G, Alizadeh A, Bagheri K, Yucel I Work. 2024; 79(3):1577-1588.

PMID: 39093108 PMC: 11612935. DOI: 10.3233/WOR-240187.

References

Mohanty S, Lekan D, McCoy T, Jenkins M, Manda P . Machine learning for predicting readmission risk among the frail: Explainable AI for healthcare. Patterns (N Y). 2022; 3(1):100395. PMC: 8767300. DOI: 10.1016/j.patter.2021.100395. View

Kim Y, Lee J, Choi S, Lee J, Kim J, Seok J . Validation of deep learning natural language processing algorithm for keyword extraction from pathology reports in electronic health records. Sci Rep. 2020; 10(1):20265. PMC: 7679382. DOI: 10.1038/s41598-020-77258-w. View

Cabitza F, Campagner A, Sconfienza L . As if sand were stone. New concepts and metrics to probe the ground on which to build trustable AI. BMC Med Inform Decis Mak. 2020; 20(1):219. PMC: 7488864. DOI: 10.1186/s12911-020-01224-9. View

Neupane S, Miranda H, Virtanen P, Siukola A, Nygard C . Multi-site pain and work ability among an industrial population. Occup Med (Lond). 2011; 61(8):563-9. DOI: 10.1093/occmed/kqr130. View

Kaluarachchi T, Reis A, Nanayakkara S . A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning. Sensors (Basel). 2021; 21(7). PMC: 8038476. DOI: 10.3390/s21072514. View

Lundberg S, Nair B, Vavilala M, Horibe M, Eisses M, Adams T . Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat Biomed Eng. 2019; 2(10):749-760. PMC: 6467492. DOI: 10.1038/s41551-018-0304-0. View

Assuncao A, Moniz-Pereira V, Fujao C, Bernardes S, Veloso A, Carnide F . Predictive Factors of Short-Term Related Musculoskeletal Pain in the Automotive Industry. Int J Environ Res Public Health. 2021; 18(24). PMC: 8700848. DOI: 10.3390/ijerph182413062. View

Yang H, Bath P . The Use of Data Mining Methods for the Prediction of Dementia: Evidence From the English Longitudinal Study of Aging. IEEE J Biomed Health Inform. 2019; 24(2):345-353. DOI: 10.1109/JBHI.2019.2921418. View

Stoll T, Huber E, Seifert B, Michel B, Stucki G . Maximal isometric muscle strength: normative values and gender-specific relation to age. Clin Rheumatol. 2000; 19(2):105-13. DOI: 10.1007/s100670050026. View

10.

Miller T, Levy D . Cost-outcome analysis in injury prevention and control: eighty-four recent estimates for the United States. Med Care. 2000; 38(6):562-82. DOI: 10.1097/00005650-200006000-00003. View

11.

Koh D, Aw T . Surveillance in occupational health. Occup Environ Med. 2003; 60(9):705-10, 633. PMC: 1740637. DOI: 10.1136/oem.60.9.705. View

12.

H M van der Velden B, Kuijf H, Gilhuijs K, Viergever M . Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Med Image Anal. 2022; 79:102470. DOI: 10.1016/j.media.2022.102470. View

13.

Gao J, Liu N, Lawley M, Hu X . An Interpretable Classification Framework for Information Extraction from Online Healthcare Forums. J Healthc Eng. 2017; 2017:2460174. PMC: 5559930. DOI: 10.1155/2017/2460174. View

14.

Danneskiold-Samsoe B, Bartels E, Bulow P, Lund H, Stockmarr A, Holm C . Isokinetic and isometric muscle strength in a healthy population with special reference to age and gender. Acta Physiol (Oxf). 2009; 197 Suppl 673:1-68. DOI: 10.1111/j.1748-1716.2009.02022.x. View

15.

Assuncao A, Mollaei N, Rodrigues J, Fujao C, Osorio D, Veloso A . A genetic algorithm approach to design job rotation schedules ensuring homogeneity and diversity of exposure in the automotive industry. Heliyon. 2022; 8(5):e09396. PMC: 9123225. DOI: 10.1016/j.heliyon.2022.e09396. View

16.

Neves I, Folgado D, Santos S, Barandas M, Campagner A, Ronzio L . Interpretable heartbeat classification using local model-agnostic explanations on ECGs. Comput Biol Med. 2021; 133:104393. DOI: 10.1016/j.compbiomed.2021.104393. View

17.

Armstrong T, Buckle P, Fine L, Hagberg M, Jonsson B, Kilbom A . A conceptual model for work-related neck and upper-limb musculoskeletal disorders. Scand J Work Environ Health. 1993; 19(2):73-84. DOI: 10.5271/sjweh.1494. View