Survey of Canadian vascular surgeons and trainees finds work-related musculoskeletal pain and discomfort is common

Construction and validation of a musculoskeletal disease risk prediction model for underground coal miners

Objective

To understand the prevalence among underground coal miners of musculoskeletal disorders (MSDs), analyze the risk factors affecting MSDs, and develop and validate a risk prediction model for the development of MSDs.

Materials and methods

MSD questionnaires were used to investigate the prevalence of work-related musculoskeletal disorders among 860 underground coal miners in Xinjiang. The Chinese versions of the Effort-Reward Imbalance Questionnaire (ERI), the Burnout Scale (MBI), and the Self-Rating Depression Inventory (SDS) were used to investigate the occupational mental health status of underground coal miners. The R4.1.3 software cart installation package was applied to randomly divide the study subjects into a 1:1 training set and validation set, screen independent predictors using single- and multi-factor regression analysis, and draw personalized nomogram graph prediction models based on regression coefficients. Subject work characteristic (ROC) curves, calibration (Calibrate) curves, and decision curves (DCA) were used to analyze the predictive value of each variable on MSDs and the net benefit.

Results

(1) The prevalence of MSDs was 55.3%, 51.2%, and 41.9% since joining the workforce, in the past year, and in the past week, respectively; the highest prevalence was in the lower back (45.8% vs. 38.8% vs. 33.7%) and the lowest prevalence was in the hips and buttocks (13.3% vs. 11.4% vs. 9.1%) under different periods. (2) Underground coal miners: the mean total scores of occupational stress, burnout, and depression were 1.55 ± 0.64, 51.52 ± 11.53, and 13.83 ± 14.27, respectively. (3) Univariate regression revealed a higher prevalence of MSDs in those older than 45 years (49.5%), length of service > 15 years (56.4%), annual income <$60,000 (79.1%), and moderate burnout (43.2%). (4) Binary logistic regression showed that the prevalence of MSDs was higher for those with 5-20 years of service (OR = 0.295, 95% CI: 0.169-0.513), >20 years of service (OR = 0.845, 95% CI: 0.529-1.350), annual income ≥$60,000 (OR = 1.742, 95% CI: 1.100-2.759), and severe burnout (OR = 0.284, 95% CI: 0.109-0.739), and that these were independent predictors of the occurrence of MSDs among workers in underground coal mine operations (p <  0.05). (5) The areas under the ROC curve for the training and validation sets were 0.665 (95% CI: 0.615-0.716) and 0.630 (95% CI: 0.578-0.682), respectively, indicating that the model has good predictive ability; the calibration plots showed good agreement between the predicted and actual prevalence of the model; and the DCA curves suggested that the predictive value of this nomogram model for MSDs was good.

Conclusion

The prevalence of MSDs among workers working underground in coal mines was high, and the constructed nomogram showed good discriminatory ability and optimal accuracy.

Perceptions of Canadian vascular surgeons toward artificial intelligence and machine learning

Background

Artificial intelligence (AI) and machine learning (ML) are rapidly advancing fields with increasing utility in health care. We conducted a survey to determine the perceptions of Canadian vascular surgeons toward AI/ML.

Methods

An online questionnaire was distributed to 162 members of the Canadian Society for Vascular Surgery. Self-reported knowledge, attitudes, and perceptions with respect to potential applications, limitations, and facilitators of AI/ML were assessed.

Results

Overall, 50 of the 162 Canadian vascular surgeons (31%) responded to the survey. Most respondents were aged 30 to 59 years (72%), male (80%), and White (67%) and practiced in academic settings (72%). One half of the participants reported that their knowledge of AI/ML was poor or very poor. Most were excited or very excited about AI/ML (66%) and were interested or very interested in learning more about the field (83.7%). The respondents believed that AI/ML would be useful or very useful for diagnosis (62%), prognosis (72%), patient selection (56%), image analysis (64%), intraoperative guidance (52%), research (88%), and education (80%). The limitations that the participants were most concerned about were errors leading to patient harm (42%), bias based on patient demographics (42%), and lack of clinician knowledge and skills in AI/ML (40%). Most were not concerned or were mildly concerned about job replacement (86%). The factors that were most important to encouraging clinicians to use AI/ML models were improvements in efficiency (88%), accurate predictions (84%), and ease of use (84%). The comments from respondents focused on the pressing need for the implementation of AI/ML in vascular surgery owing to the potential to improve care delivery.

Conclusions

Canadian vascular surgeons have positive views on AI/ML and believe this technology can be applied to multiple aspects of the specialty to improve patient care, research, and education. Current self-reported knowledge is poor, although interest was expressed in learning more about the field. The facilitators and barriers to the effective use of AI/ML identified in the present study can guide future development of these tools in vascular surgery.