Validity of the Work Assessment Triage Tool for Selecting Rehabilitation Interventions for Workers' Compensation Claimants with Musculoskeletal Conditions

Injured worker participation in assessment during the acute phase of workers compensation rehabilitation: a scoping review

PURPOSE

Rates of return to work (RTW) are declining in the Australian workers compensation system alongside significant economic and social costs, disputes, and secondary psychological injury. Non-medical assessment of workplace injuries now considers psychosocial and workplace factors, and worker participation in the assessment process is limited. This scoping review examines studies regarding non-medical assessment during the acute phase of rehabilitation in terms of costs, disputes, secondary psychological injury, and worker participation.

METHOD

An electronic and manual search of relevant articles across four databases was conducted using PRISMA guidelines, followed by quality assessment.

RESULTS

Of the 1,630 studies retrieved, 12 met the inclusion criteria with most focused on assessment for risk of obstructed or delayed RTW.

CONCLUSIONS

Non-medical assessment in the acute stage of rehabilitation identifies risk for delayed or complicated RTW, overlooking potential for the process of assessment to contribute to disputes and development of secondary psychological injury. Doubt around the capacity of workers to participate objectively in assessment persists. These are aspects of assessment worthy of further exploration for their impact on RTW outcomes.

A Scoping Review on the Use of Machine Learning in Return-to-Work Studies: Strengths and Weaknesses

PURPOSE

Decisions to increase work participation must be informed and timely to improve return to work (RTW). The implementation of research into clinical practice relies on sophisticated yet practical approaches such as machine learning (ML). The objective of this study is to explore the evidence of machine learning in vocational rehabilitation and discuss the strengths and areas for improvement in the field.

METHODS

We used the PRISMA guidelines and the Arksey and O'Malley framework. We searched Ovid Medline, CINAHL, and PsycINFO; with hand-searching and use of the Web of Science for the final articles. We included studies that are peer-reviewed, published within the last 10 years to consider contemporary material, implemented a form of "machine learning" or "learning health system", undertaken in a vocational rehabilitation setting, and has employment as a specific outcome.

RESULTS

12 studies were analyzed. The most commonly studied population was musculoskeletal injuries or health conditions. Most of the studies came from Europe and most were retrospective studies. The interventions were not always reported or specified. ML was used to identify different work-related variables that were predictive of return to work. However, ML approaches were varied and no standard or predominant ML approach was evident.

CONCLUSIONS

ML offers a potentially beneficial approach to identifying predictors of RTW. While ML uses a complex calculation and estimation, ML complements other elements of evidence-based practice such as the clinician's expertise, the worker's preference and values, and contextual factors around RTW in an efficient and timely manner.

Comparison of Machine Learning Methods in the Study of Cancer Survivors' Return to Work: An Example of Breast Cancer Survivors with Work-Related Factors in the CONSTANCES Cohort

PURPOSE

Machine learning (ML) methods showed a higher accuracy in identifying individuals without cancer who were unable to return to work (RTW) compared to the classical methods (e.g. logistic regression models). We therefore aim to discuss the value of these methods in relation to RTW for cancer survivors.

METHODS

Breast cancer (BC) survivors who were working at diagnosis within the CONSTANCES cohort were included in the study. RTW was assessed five years after the BC diagnosis (early retirement was considered as non-RTW). Age and occupation at diagnosis, and physical occupational job exposures assessed using the Job Exposure Matrix, JEM-CONSTANCES, were evaluated as predictors of RTW five years after BC diagnosis. The following four ML methods were used: (i) k-nearest neighbors; (ii) random forest; (iii) neural network; and (iv) elastic net.

RESULTS

The training sample included 683 BC survivors (RTW: 85.7%), and the test sample 171 (RTW: 85.4%). The elastic net method had the best results despite low sensitivity (accuracy = 76.6%; sensitivity = 31.7%; specificity = 90.8%), and the random forest model was the most accurate (= 79.5%) but also the least sensitive (= 14.3%).

CONCLUSION

This study takes a first step towards opening up new possibilities for identifying the occupational determinants of cancer survivors' RTW. Further work, including a larger sample size, and more predictor variables, is now needed.

Accuracy of the Örebro Musculoskeletal Pain Questionnaire and Work Assessment Triage Tool for selecting interventions in workers with spinal conditions

BACKGROUND

Accurate clinical decision support tools may help clinicians select appropriate interventions for patients with spinal conditions. The Örebro Musculoskeletal Pain Questionnaire (ÖMPQ) is a screening questionnaire extensively studied as a predictive tool. The Work Assessment Triage Tool (WATT) is a clinical decision support tool developed to help select interventions for injured workers.

OBJECTIVE

To compare the classification accuracy of the ÖMPQ and WATT to clinician recommendations for selecting interventions leading to a successful return to work in patients with spinal conditions.

METHODS

A secondary analysis was undertaken of data from injured workers with spinal conditions assessed between 2013 and 2016. We considered it a success if the workers did not receive wage replacement benefits 30 days after assessment. Analysis included positive likelihood ratio (LR+) as an indicator of predictive accuracy.

RESULTS

Within the database, 2,872 patients had complete data on the ÖMPQ, WATT, and clinician recommendations. At 30 days, the ÖMPQ was most accurate for identifying treatments that lead to successful outcomes with a LR+= 1.51 (95% Confidence Interval 1.26-1.82) compared to 1.05 (95% Confidence Interval 1.02-1.09) for clinicians, and 0.85 (95% Confidence Interval 0.79-0.91) for the WATT.

CONCLUSIONS

All tool recommendations had poor accuracy, however the ÖMPQ demonstrated significantly better results.

A Descriptive Study of the Implementation of Remote Occupational Rehabilitation Services Due to the COVID-19 Pandemic Within a Workers' Compensation Context

Purpose The Coronavirus Disease (COVID-19) pandemic resulted in dramatic changes to avoid virus spread. In Canada, following provincial legislation the Workers' Compensation Board of Alberta (WCB-Alberta) stopped in-person rehabilitation services on March 23, 2020. On April 1, training began on remote service delivery using videoconferencing or telerehabilitation, which started April 3. We studied WCB-Alberta's transition to remote rehabilitation service delivery. Methods A population-based descriptive study was conducted, with data extracted from the WCB-Alberta database. This included clinical data from rehabilitation providers. We included workers completing services between January 1 and May 31, 2020. We statistically examined differences before and after the transition to remote services. Results The dataset included 4,516 individuals with work-related injuries. The mean number of work assessments per week pre-COVID was 244.6 (SD 83.5), which reduced to 135.9 (SD 74.5). Workers undergoing remote assessments were significantly more likely to work in health care or trades, did not require an interpreter, and were less likely to be working or judged as ready to return to work. Number of completed rehabilitation programs also reduced from 125.6 to 40.8 per week, with most (67.1%) remote programs being functional restoration. Few adverse effects were observed. Conclusions We describe the transition to completely remote delivery of occupational rehabilitation due to COVID-19 physical distancing restrictions in one Canadian compensation jurisdiction. It appears the use of remote services was successful but proceeded cautiously, with fewer complex cases being referred for assessment or rehabilitation. Further research examining longer-term work outcomes and stakeholder perceptions is needed.

Ethical Considerations of Using Machine Learning for Decision Support in Occupational Health: An Example Involving Periodic Workers' Health Assessments

Purpose Computer algorithms and Machine Learning (ML) will be integrated into clinical decision support within occupational health care. This will change the interaction between health care professionals and their clients, with unknown consequences. The aim of this study was to explore ethical considerations and potential consequences of using ML based decision support tools (DSTs) in the context of occupational health. Methods We conducted an ethical deliberation. This was supported by a narrative literature review of publications about ML and DSTs in occupational health and by an assessment of the potential impact of ML-DSTs according to frameworks from medical ethics and philosophy of technology. We introduce a hypothetical clinical scenario from a workers' health assessment to reflect on biomedical ethical principles: respect for autonomy, beneficence, non-maleficence and justice. Results Respect for autonomy is affected by uncertainty about what future consequences the worker is consenting to as a result of the fluctuating nature of ML-DSTs and validity evidence used to inform the worker. A beneficent advisory process is influenced because the three elements of evidence based practice are affected through use of a ML-DST. The principle of non-maleficence is challenged by the balance between group-level benefits and individual harm, the vulnerability of the worker in the occupational context, and the possibility of function creep. Justice might be empowered when the ML-DST is valid, but profiling and discrimination are potential risks. Conclusions Implications of ethical considerations have been described for the socially responsible design of ML-DSTs. Three recommendations were provided to minimize undesirable adverse effects of the development and implementation of ML-DSTs.

Machine Learning for Work Disability Prevention: Introduction to the Special Series

Rapid development in computer technology has led to sophisticated methods of analyzing large datasets with the aim of improving human decision making. Artificial Intelligence and Machine Learning (ML) approaches hold tremendous potential for solving complex real-world problems such as those faced by stakeholders attempting to prevent work disability. These techniques are especially appealing in work disability contexts that collect large amounts of data such as workers' compensation settings, insurance companies, large corporations, and health care organizations, among others. However, the approaches require thorough evaluation to determine if they add value to traditional statistical approaches. In this special series of articles, we examine the role and value of ML in the field of work disability prevention and occupational rehabilitation.

Smart Work Injury Management (SWIM) System: Artificial Intelligence in Work Disability Management

PURPOSE

This paper aims to illustrate an example of how to set up a work injury database: the Smart Work Injury Management (SWIM) system. It is a secure and centralized cloud platform containing a set of management tools for data storage, data analytics, and machine learning. It employs artificial intelligence to perform in-depth analysis via text-mining techniques in order to extract both dynamic and static data from work injury case files. When it is fully developed, this system can provide a more accurate prediction model for cost of work injuries. It can also predict return-to-work (RTW) trajectory and provide advice on medical care and RTW interventions to all RTW stakeholders. The project will comprise three stages. Stage one: to identify human factors in terms of both facilitators and barriers RTW through face-to-face interviews and focus group discussions with different RTW stakeholders in order to collect opinions related to facilitators, barriers, and essential interventions for RTW of injured workers; Stage two: to develop a machine learning model which employs artificial intelligence to perform in-depth analysis. The technologies used will include: 1. Text-mining techniques including English and Chinese work segmentation as well as N-Gram to extract both dynamic and static data from free-style text as well as sociodemographic information from work injury case files; 2. Principle component/independent component analysis to identify features of significant relationships with RTW outcomes or combine raw features into new features; 3. A machine learning model that combines Variational Autoencoder, Long and Short Term Memory, and Neural Turning Machines. Stage two will also include the development of an interactive dashboard and website to query the trained machine learning model. Stage three: to field test the SWIM system.

CONCLUSION

SWIM ia secure and centralized cloud platform containing a set of management tools for data storage, data analytics, and machine learning. When it is fully developed, SWIM can provide a more accurate prediction model for the cost of work injuries and advice on medical care and RTW interventions to all RTW stakeholders.

ETHICS

The project has been approved by the Ethics Committee for Human Subjects at the Hong Kong Polytechnic University and is funded by the Innovation and Technology Commission (Grant # ITS/249/18FX).