Occupational health knowledge discovery based on association rules applied to workers' body parts protection: a case study in the automotive industry.

Occupational Health Protection (OHP) is mandatory by law and can be accomplished by considering the participation of others besides occupational physicians. The data shared can originate knowledge that might influence other processes related to occupational risk prevention. In this study, we used Artificial Intelligence (AI) methods to extract patterns among records shared under these circumstances over two years in the automotive industry. Records featuring OHP data against physical working conditions were selected, and a database of 383 profiles was designed. As Occupational Health Protection profiles under study are associated with work functional ability reduction, the body part(s) (n = 14) where it occurred were identified. Association Rules (ARs) coupled with Natural Language Processing techniques were applied to find meaningful hidden relationships and to identify the occurrence of protection profiles being assigned to at least two body parts simultaneously. After filtering ARs using three metrics (support, confidence, and lift), 54 ARs were found. The distribution of simultaneous body parts is presented as being higher in Special projects (n = 5). The results can use in: (i) design a multi-site body parts functional work ability (loss) model; (ii) model the capacity of organizations to retain workers in their working settings and (iii) prevent work-related musculoskeletal symptoms.

The role of work conditions on the functional decline in senior workers in the automotive industry.

BACKGROUND: The aging of the workforce is changing, but working conditions have not changed at the same exponential growth rate for senior workers. Such a situation can compromise the worker's physical and cognitive capability, reducing the ability to perform work activities. OBJECTIVES: This study aims to understand the main functional capacity changes in senior workers in the automotive industry and to determine the contribution of working conditions on the decline of the functional capacity in senior workers. METHODS: To achieve the objectives of the study, a set of questionnaires (Sociodemographic Data, COPSOQ, Nordic Questionnaire, and Par-Q) and a battery of 4 functional capacity tests were used. RESULTS: Work conditions, namely awkward postures, force demands and manual material handling, and age, were statistically associated to the functional decline in workers. Additionally, multiple linear regression showed that height, weight, seniority, and strength have predictive value to the handgrip decline (both positions HG2 and HG5). CONCLUSION: These results suggest that workers' handgrip assessment should be considered as a future measure as an indicator of strength ability in the occupational field.

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

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.

A genetic algorithm approach to design job rotation schedules ensuring homogeneity and diversity of exposure in the automotive industry.

Job rotation is a work organization strategy with increasing popularity, given its benefits for workers and companies, especially those working with manufacturing. This study proposes a formulation to help the team leader in an assembly line of the automotive industry to achieve job rotation schedules based on three major criteria: improve diversity, ensure homogeneity, and thus reduce exposure level. The formulation relied on a genetic algorithm, that took into consideration the biomechanical risk factors (EAWS), workers' qualifications, and the organizational aspects of the assembly line. Moreover, the job rotation plan formulated by the genetic algorithm formulation was compared with the solution provided by the team leader in a real life-environment. The formulation proved to be a reliable solution to design job rotation plans for increasing diversity, decreasing exposure, and balancing homogeneity within workers, achieving better results in all of the outcomes when compared with the job rotation schedules created by the team leader. Additionally, this solution was less time-consuming for the team leader than a manual implementation. This study provides a much-needed solution to the job rotation issue in the manufacturing industry, with the genetic algorithm taking less time and showing better results than the job rotations created by the team leaders.

Predictive Factors of Short-Term Related Musculoskeletal Pain in the Automotive Industry.

To determine the short-term associations between biomechanical risk factors and musculoskeletal symptoms in the upper limbs and low back in an automotive company, a longitudinal study with a follow-up of 4 days was conducted in a sample of 228 workers of the assembly and paint areas. Data were analyzed using generalized estimating equations, calculating the crude and adjusted model for age, sex, seniority, and intensity of pain at baseline. The interactions found were the same for both models. Workers were divided in low-risk and high-risk group for posture, force, exposure, percentage of cycle time with the arm at/above shoulder level, and with the trunk flexed or/and strongly flexed. The predictive factors showed by time × group effect were found between pain intensity on the left shoulder for posture (ß = 0.221, p < 0.001), percentage of time with the trunk flexed (ß = 0.136, p = 0.030) and overall exposure (ß = 0.140, p = 0.013). A time × group interactions were observed, namely between neck pain and posture (ß = 0.218, p = 0.005) and right wrist and force (ß = 0.107, p = 0.044). Workers in the high-risk group were more prone to report unfavorable effects on their self-reported musculoskeletal pain, across a workweek when exposed to specific risk factor, being posture important to neck, right wrist and left shoulder pain.

Normative reference values of the handgrip strength for the Portuguese workers.

INTRODUCTION: The active workforce is increasingly aging. However workload, as well as working time and intensity, sometimes remains unchanged. This can be an even more critical situation in older people, since occupational exposure associated with aging, will further reduce the muscle's ability to generate energy, which in turn facilitates the development of these age-related syndromes. This study aims to identify the normative values of handgrip strength for Portuguese workers in the automotive industry. METHODS: About 1225 employees were invited to participate in the study. The final sample consisted of 656 employees in the assembly area. The handgrip strength was measured in kilograms (kg) using the Jamar digital dynamometer. Sex-specific profiles of handgrip strength were designed by the Ordinary Least Square regression (OLS) analysis, where height, age, age squared, and height squared are entered into the models as determining factors of the maximum grip strength in both female and male groups. RESULTS: The peak mean values of handgrip strength in the group of women was 34 kg in the age group of 35-39 years, and in the group of men the peak mean was 52 kg in the age group of 25-34 years. The most pronounced decline in the female group appears in the age of 30-34 years of about 4 kg and the male group the decline occurs at 2kg below the peak force, in the age group of 40-57 year-olds. This study used a cut-off at 2 SD below by the sex-specific peak mean. CONCLUSION: Normative values can help delineate the career path of workers because they portray risk values according to age, height, and gender. The normative values assist health and engineering professionals and ergonomists in adjusting task demands to the morphological and strength characteristics of the workers.