A Machine Learning-Based Predictive Model of Return to Work After Sick Leave

Evaluation of the Accuracy of the Smart Work Injury Management (SWIM) System to Assist Case Managers in Predicting the Work Disability of Injured Workers

PURPOSE

Many countries have developed clinical decision-making support tools, such as the smart work injury management (SWIM) system in Hong Kong, to predict rehabilitation paths and address global issues related to work injury disability. This study aims to evaluate the accuracy of SWIM by comparing its predictions on real work injury cases to those made by human case managers, specifically with regard to the duration of sick leave and the percentage of permanent disability.

METHODS

The study analyzed a total of 442 work injury cases covering the period from 2012 to 2020, dividing them into non-litigated and litigated cases. The Kruskal-Wallis post hoc test with Bonferroni adjustment was used to evaluate the differences between the actual data, the SWIM predictions, and the estimations made by three case managers. The intra-class correlation coefficient was used to assess the inter-rater reliability of the case managers.

RESULTS

The study discovered that the predictions made by the SWIM model and a case manager possessing approximately 4 years of experience in case management exhibited moderate reliability in non-litigated cases. Nevertheless, there was no resemblance between SWIM's predictions regarding the percentage of permanent disability and those made by case managers.

CONCLUSION

The findings indicate that SWIM is capable of replicating the sick leave estimations made by a case manager with an estimated 4 years of case management experience, albeit with limitations in generalizability owing to the small sample size of case managers involved in the study.

IMPLICATIONS

These findings represent a significant advancement in enhancing the accuracy of CDMS for work injury cases in Hong Kong, signaling progress in the field.

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.

Exploring predictors of welfare dependency 1, 3, and 5 years after mental health-related absence in danish municipalities between 2010 and 2012 using flexible machine learning modelling

BACKGROUND

Using XGBoost (XGB), this study demonstrates how flexible machine learning modelling can complement traditional statistical modelling (multinomial logistic regression) as a sensitivity analysis and predictive modelling tool in occupational health research.

DESIGN

The study predicts welfare dependency for a cohort at 1, 3, and 5 years of follow-up using XGB and multinomial logistic regression (MLR). The models' predictive ability is evaluated using tenfold cross-validation (internal validation) and geographical validation (semi-external validation). In addition, we calculate and graphically assess Shapley additive explanation (SHAP) values from the XGB model to examine deviation from linearity assumptions, including interactions. The study population consists of all 20-54 years old on long-term sickness absence leave due to self-reported common mental disorders (CMD) between April 26, 2010, and September 2012 in 21 (of 98) Danish municipalities that participated in the Danish Return to Work program. The total sample of 19.664 observations is split geospatially into a development set (n = 9.756) and a test set (n = 9.908).

RESULTS

There were no practical differences in the XGB and MLR models' predictive ability. Industry, job skills, citizenship, unemployment insurance, gender, and period had limited importance in predicting welfare dependency in both models. On the other hand, welfare dependency history and reason for sickness absence were strong predictors. Graphical SHAP-analysis of the XGB model did not indicate substantial deviations from linearity assumptions implied by the multinomial regression model.

CONCLUSION

Flexible machine learning models like XGB can supplement traditional statistical methods like multinomial logistic regression in occupational health research by providing a benchmark for predictive performance and traditional statistical models' ability to capture important associations for a given set of predictors as well as potential violations of linearity.

TRIAL REGISTRATION

ISRCTN43004323.

Developing Action Plans Based on Machine Learning Analysis to Prevent Sick Leave in a Manufacturing Plant

OBJECTIVE

We aimed to develop action plans for employees' health promotion based on a machine learning model to predict sick leave at a Japanese manufacturing plant.

METHODS

A random forest model was developed to predict sick leave. We developed plans for workers' health promotion based on variable importance and partial dependence plots.

RESULTS

The model showed an area under the receiving operating characteristic curve of 0.882. The higher scores on the Brief Job Stress Questionnaire stress response, younger age, and certain departments were important predictors for sick leave due to mental disorders. We proposed plans to effectively use the Brief Job Stress Questionnaire and provide more support for younger workers and managers of high-risk departments.

CONCLUSIONS

We described a process of action plan development using a machine learning model, which may be beneficial for occupational health practitioners.

Combining Virtual Reality and Machine Learning for Leadership Styles Recognition

The aim of this study was to evaluate the viability of a new selection procedure based on machine learning (ML) and virtual reality (VR). Specifically, decision-making behaviours and eye-gaze patterns were used to classify individuals based on their leadership styles while immersed in virtual environments that represented social workplace situations. The virtual environments were designed using an evidence-centred design approach. Interaction and gaze patterns were recorded in 83 subjects, who were classified as having either high or low leadership style, which was assessed using the Multifactor leadership questionnaire. A ML model that combined behaviour outputs and eye-gaze patterns was developed to predict subjects' leadership styles (high vs low). The results indicated that the different styles could be differentiated by eye-gaze patterns and behaviours carried out during immersive VR. Eye-tracking measures contributed more significantly to this differentiation than behavioural metrics. Although the results should be taken with caution as the small sample does not allow generalization of the data, this study illustrates the potential for a future research roadmap that combines VR, implicit measures, and ML for personnel selection.

Comparison of predicted psychological distress among workers between artificial intelligence and psychiatrists: a cross-sectional study in Tsukuba Science City, Japan

OBJECTIVES

Psychological distress is a worldwide problem and a serious problem that needs to be addressed in the field of occupational health. This study aimed to use artificial intelligence (AI) to predict psychological distress among workers using sociodemographic, lifestyle and sleep factors, not subjective information such as mood and emotion, and to examine the performance of the AI models through a comparison with psychiatrists.

DESIGN

Cross-sectional study.

SETTING

We conducted a survey on psychological distress and living conditions among workers. An AI model for predicting psychological distress was created and then the results were compared in terms of accuracy with predictions made by psychiatrists.

PARTICIPANTS

An AI model of the neural network and six psychiatrists.

PRIMARY OUTCOME

The accuracies of the AI model and psychiatrists for predicting psychological distress.

METHODS

In total, data from 7251 workers were analysed to predict moderate and severe psychological distress. An AI model of the neural network was created and accuracy, sensitivity and specificity were calculated. Six psychiatrists used the same data as the AI model to predict psychological distress and conduct a comparison with the AI model.

RESULTS

The accuracies of the AI model and psychiatrists for predicting moderate psychological distress were 65.2% and 64.4%, respectively, showing no significant difference. The accuracies of the AI model and psychiatrists for predicting severe psychological distress were 89.9% and 85.5%, respectively, indicating that the AI model had significantly higher accuracy.

CONCLUSIONS

A machine learning model was successfully developed to screen workers with depressed mood. The explanatory variables used for the predictions did not directly ask about mood. Therefore, this newly developed model appears to be able to predict psychological distress among workers easily, regardless of their subjective views.

The future of research on work, safety, health and wellbeing: A guiding conceptual framework

Work plays a central role in health. A conceptual model can help frame research priorities and questions to explore determinants of workers' safety, health, and wellbeing. A previous conceptual model focused on the workplace setting to emphasize the role of conditions of work in shaping workers' safety, health and wellbeing. These conditions of work include physical, organizational, and psychosocial factors. This manuscript presents and discusses an updated and expanded conceptual model, placing the workplace and the conditions of work within the broader context of socio-political-economic environments and consequent trends in employment and labor force patterns. Social, political and economic trends, such as growing reliance on technology, climate change, and globalization, have significant implications for workers' day-to-day experiences. These structural forces in turn shape employment and labor patterns, with implications for the availability and quality of jobs; the nature of relationships between employers and workers; and the benefits and protections available to workers. Understanding these patterns will be critical for anticipating the consequences of future changes in the conditions of work, and ultimately help inform decision-making around policies and practices intended to protect and promote worker safety, health, and wellbeing. This model provides a structure for anticipating research needs in response to the changing nature of work, including the formation of research priorities, the need for expanded research methods and measures, and attention to diverse populations of enterprises and workers. This approach anticipates changes in the way work is structured, managed, and experienced by workers and can effectively inform policies and practices needed to protect and promote worker safety, health and wellbeing.

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).