Bayesian network model to diagnose WMSDs with working characteristics

Ahn, Gilseung; Hur, Sun; Jung, Myung‐Chul

doi:10.1080/10803548.2018.1502131

Cited by 11 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interestingly, the available literature data demonstrated that the prevalence of these disorders in specific working populations and/or occupational sectors is significantly higher than in general population [3] showing a causal relationship between different types of occupational risk factors (e.g. awkward positions, repetitive movements, low temperatures, manual handling of heavy loads, prolonged computer work, mechanical vibrations, work-related stress) and the development of MSDs that, in this context, are defined as Work related Musculoskeletal Disorders (WMSDs) [4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Prevalence of work related musculoskeletal disorders in Italian workers: is there an underestimation of the related occupational risk factors?

Russo

Tecco

Fontana

et al. 2020

BMC Musculoskelet Disord

View full text Add to dashboard Cite

Background Work-related musculoskeletal disorders (WMSDs) represent an important socio-economic burden. The current risk assessment and management involved in the ethiopathogenesis of WMSDs is based on observational tools and checklists, which have some limitations in terms of accuracy and reliability. The aim of this study was to assess WMSD prevalence and identify possible correlations with several socio-demographic and work-related variables in a large cohort representative of Italian workers in order to improve our understanding of the WMSD phenomenon. Methods This study includes data from INSuLa, a cross-sectional nationally representative survey of health and safety at work, developed by the Italian Workers’ Compensation Authority. A total of 8000 Italian workers were included. Multivariate logistic regression analyses were performed to evaluate the association of independent variables, such as workers’ perceptions of exposure to biomechanical/ergonomic and video display unit (VDU) risks (Risk Perceived) and the actual risk exposure (Risk Detected) on Back, Lower and Upper limb pain. Socio-demographic, occupational and other health-related variables were included to investigate possible association with musculoskeletal disorders. Results Workers perceiving a significant exposure to biomechanical/ergonomic and VDU risks but not included in a health surveillance program for them (Risk Perceived/No Risk Detected) have had significantly higher odds of reporting musculoskeletal disorders. Regarding the biomechanical/ergonomic risk these workers are in the 19–24 age range (39.9%), transportation, warehousing/information and communication sectors (38.9%) and are employed in companies with more than 250 workers (35.8%). Regarding VDU risk, workers are in the 45–54 age range (24.5%), professional, financial and business services (38.0%) and come from companies with more than 250 employees (25.6%). Conclusions Within the occupational safety and health management systems an appropriate assessment of occupational risk factors correlated to musculoskeletal disorders (mainly biomechanical/ergonomic and VDU) and the correct definition of their exposure levels is essential to adequately prevent the onset of WMSDs. In this regard, our findings provide useful information to design novel approaches, aimed at improving our understanding of emerging risks, identifying gaps in current risk assessment strategies and enhancing workplace interventions are mandatory to improve the occupational risk assessment and management process and therefore implement the subsequent health surveillance systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Prevalence of work related musculoskeletal disorders in Italian workers: is there an underestimation of the related occupational risk factors?

Russo

Tecco

Fontana

et al. 2020

BMC Musculoskelet Disord

View full text Add to dashboard Cite

show abstract

“…For this reason, the development and validation of a new assessment tool remain pertinent. According to the previous researches, [19][20][21] heavy physical work, high psychosocial work demands and the presence of comorbidities were risk factors that had at least reasonable evidence for the development of WMSDs. Smoking and body mass index were considered risk factors too.…”

Section: Resultsmentioning

confidence: 99%

Development of the Prevent for Work questionnaire (P4Wq) for assessment of musculoskeletal risk in the workplace: part 1—literature review and domains selection

et al. 2021

View full text Add to dashboard Cite

ObjectiveThis study aims to define appropriate domains and items for the development of a self-administered questionnaire to assess the risk of developing work-related musculoskeletal disorder (WMSD) and the risk of its progression to chronicity.DesignLiterature review and survey study.Setting and participantsA literature review and a two-round interview with 15 experts in musculoskeletal pain were performed to identify the available domains for WMSD assessment.Interventions and outcomeTo ensure quality, only validated questionnaires were included for the Delphi process. A three-round Delphi method, with three round steps, was used to select the most pertinent and relevant domains and items.ResultsNine questionnaires were identified through the expert discussion and literature review, comprising 38 candidate domains and 504 items. In the first round of the Delphi group, 17 domains reached more than 70% agreement and were selected. In the second round, 10 domains were rejected, while 11 were selected to complete the pool of domains. In the third and final round, 89 items belonging to 28 domains were defined as significant to develop a WMSDs risk assessment questionnaire.ConclusionsNo specific risk assessment questionnaires for WMSDs were identified from the literature. WMSD risk of presence and chronicity can be defined by an assessment tool based on the biopsychosocial model and the fear-avoidance components of chronic pain. The present study provides the formulation and operationalisation of the constructs in domains and items needed for developing and validating the questionnaire.

show abstract

“…Experts' knowledge and some algorithms are utilized for creating the casual structure of BN. Prior information and experts' knowledge can help structure learning, support parameters learning, prevent from overfitting and work with incomplete data as well (Ahn et al , 2018). However, many papers ignore these capabilities.…”

Section: Introductionmentioning

confidence: 99%

An efficient Bayesian network for differential diagnosis using experts' knowledge

Ershadi

Seifi

2020

IJICC

View full text Add to dashboard Cite

PurposeThis study aims to differential diagnosis of some diseases using classification methods to support effective medical treatment. For this purpose, different classification methods based on data, experts’ knowledge and both are considered in some cases. Besides, feature reduction and some clustering methods are used to improve their performance.Design/methodology/approachFirst, the performances of classification methods are evaluated for differential diagnosis of different diseases. Then, experts' knowledge is utilized to modify the Bayesian networks' structures. Analyses of the results show that using experts' knowledge is more effective than other algorithms for increasing the accuracy of Bayesian network classification. A total of ten different diseases are used for testing, taken from the Machine Learning Repository datasets of the University of California at Irvine (UCI).FindingsThe proposed method improves both the computation time and accuracy of the classification methods used in this paper. Bayesian networks based on experts' knowledge achieve a maximum average accuracy of 87 percent, with a minimum standard deviation average of 0.04 over the sample datasets among all classification methods.Practical implicationsThe proposed methodology can be applied to perform disease differential diagnosis analysis.Originality/valueThis study presents the usefulness of experts' knowledge in the diagnosis while proposing an adopted improvement method for classifications. Besides, the Bayesian network based on experts' knowledge is useful for different diseases neglected by previous papers.

show abstract

Bayesian network model to diagnose WMSDs with working characteristics

Abstract: It was verified that working characteristics, such as working hours and pace, impact the incidence rate of WMSDs, and a BN model was developed to probabilistically diagnose WMSDs.

Cited by 11 publications

References 38 publications

Prevalence of work related musculoskeletal disorders in Italian workers: is there an underestimation of the related occupational risk factors?

Prevalence of work related musculoskeletal disorders in Italian workers: is there an underestimation of the related occupational risk factors?

Development of the Prevent for Work questionnaire (P4Wq) for assessment of musculoskeletal risk in the workplace: part 1—literature review and domains selection

An efficient Bayesian network for differential diagnosis using experts' knowledge

Contact Info

Product

Resources

About