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.

Smart Work Injury Management (SWIM) System: A Machine Learning Approach for the Prediction of Sick Leave and Rehabilitation Plan.

As occupational rehabilitation services are part of the public medical and health services in Hong Kong, work-injured workers are treated along with other patients and are not considered a high priority for occupational rehabilitation services. The idea of a work trial arrangement in the private market occurred to meet the need for a more coordinated occupational rehabilitation practice. However, there is no clear service standard in private occupational rehabilitation services nor concrete suggestions on how to offer rehabilitation plans to injured workers. Electronic Health Records (EHRs) data can provide a foundation for developing a model to improve this situation. This project aims at using a machine-learning-based approach to enhance the traditional prediction of disability duration and rehabilitation plans for work-related injury and illness. To help patients and therapists to understand the machine learning result, we also developed an interactive dashboard to visualize machine learning results. The outcome is promising. Using the variational autoencoder, our system performed better in predicting disability duration. We have around 30% improvement compared with the human prediction error. We also proposed further development to construct a better system to manage the work injury case.

The Effectiveness of Virtual Reality-Based Interventions in Rehabilitation Management of Breast Cancer Survivors: Systematic Review and Meta-analysis.

BACKGROUND: Breast cancer survivors (BCSs) can present with various physical and psychological symptoms and functional deficits that impact their quality of life. Virtual reality (VR) technology is being used in breast cancer rehabilitation management to improve the emotional, cognitive, and physical well-being of BCSs. OBJECTIVE: This systematic review aimed to examine the effectiveness of VR-based interventions on health-related outcomes in BCSs. A meta-analysis was conducted to evaluate the effectiveness of VR-based interventions in the rehabilitation management of BCSs. METHODS: A systematic search was conducted on PubMed, Web of Science, EMBASE, CINAHL with Full Text, the Cochrane Central Register of Controlled Trials, CNKI, WanFang, VIP, and CBM, from inception to May 25, 2021. The inclusion criteria of the selected studies were as follows: (1) adults diagnosed with breast cancer; (2) any type of VR-based interventions (immersive and nonimmersive virtual environment); (3) comparison of traditional rehabilitation methods; (4) outcomes including pain, depression, anxiety, fatigue, cognitive function, shoulder range of motion (ROM), hand grip strength, lymphedema, cybersickness symptoms, fear of movement, bleeding, effusion, and flap necrosis, both during and after treatment; and (5) randomized controlled trials (RCTs), case-controlled trials, and quasi-experimental studies. The Cochrane Collaboration Tool was used to evaluate the risk of bias. Review Manager version 5.3 (Cochrane Collaboration) was used to conduct the meta-analysis. The mean difference (MD) and SDs with 95% CIs were used to calculate continuous variables. RESULTS: Twelve articles were included in this systematic review, of which 10 contributed information to the meta-analysis. A total of 604 participants were analyzed. The statistical analysis showed significant results for flexion (standard mean difference [SMD] 1.79; 95% CI 0.55 to 3.03; P=.005), extension (SMD 1.54; 95% CI 0.83 to 2.25; P<.001), abduction (MD 17.53; 95% CI 14.33 to 20.72; P<.001), adduction (MD 15.98; 95% CI 14.02 to 17.94; P<.001), internal rotation (MD 7.12; 95% CI 5.54 to 8.70; P<.001), external rotation (SMD 0.96; 95% CI 0.62 to 1.29; P<.001), anxiety (MD -6.47; 95% CI -7.21 to -5.73; P<.001), depression (MD -4.27; 95% CI -4.64 to -3.91; P<.001), pain (MD -1.32; 95% CI -2.56 to -0.09; P=.04), and cognitive function (MD 8.80; 95% CI 8.24 to 9.36; P<.001). The meta-analysis indicated little to no difference in hand grip strength (MD 1.96; 95% CI -0.93 to 4.85; P=.18). CONCLUSIONS: Findings of this review noted a weak but consistent positive association between VR-based interventions and outcomes. However, these results must be interpreted with caution due to the limited number of controlled trials analyzed, small sample sizes, and poor methodological quality. Well-designed, large, high-quality trials may have a significant impact on our confidence in the results. Future studies should identify specific aspects that improve the clinical impact of VR-based interventions on major outcomes in BCSs in the clinical setting. TRIAL REGISTRATION: PROSPERO International Prospective Register of Systematic Reviews CRD42021250727; https://tinyurl.com/2p89rmnk.

A Mobile-based Virtual Reality Speech Rehabilitation App for Patients With Aphasia After Stroke: Development and Pilot Usability Study.

BACKGROUND: Stroke has the highest disability-adjusted life-years lost in any disease, and approximately one-third of the patients get aphasia. Computers and tablets are innovative and aid in intensive treatments in speech rehabilitation for patients with aphasia. However, mechanical training limits the help to patients. OBJECTIVE: This study aims to provide a framework for an integrated virtual reality (VR) app to provide speech rehabilitation for patients with aphasia. METHODS: The content was generated through an in-depth literature review and discussion with experienced rehabilitation physicians and occupational therapists. We then conducted a 2-round Delphi study with 15 experts from hospitals and universities to rate the content using a 5-point Likert scale. The app was developed by an interdisciplinary team involving VR, medical science of rehabilitation, and therapeutic rehabilitation. Pilot usability testing of this novel app was conducted among 5 patients with aphasia, 5 healthy volunteers, 5 medical staff, and 2 VR experts. RESULTS: We designed 4 modules of speech rehabilitation: oral expression, auditory comprehension, cognition, and comprehensive application. Our VR-based interactive and intelligent app was developed to provide an alternative option for patients with aphasia. Pilot usability testing revealed user satisfaction with the app. CONCLUSIONS: This study designed and tested a novel VR-based app for speech rehabilitation specifically adapted to patients with aphasia. This will guide other studies to develop a similar program or intelligent system in a clinical setting.

A single vectored thermal pulsation treatment for meibomian gland dysfunction increases mean comfortable contact lens wearing time by approximately 4 hours per day.

PURPOSE: To evaluate the effect of a single vectored thermal pulsation (VTP) treatment in contact lens wearers with meibomian gland dysfunction (MGD) and dry eye symptoms. METHODS: The prospective, nonsignificant risk, open-label, randomized, multi-center clinical trial included 55 soft contact lens (SCL) wearers with MGD and evaporative dry eye. Subjects were randomized to the single VTP treatment group or an untreated control. The controls received a crossover VTP treatment at 3 months (crossover treatment group). Primary effectiveness measures were meibomian gland secretion (MGS) score and Standard Patient Evaluation of Eye Dryness (SPEED) that were evaluated at baseline, at 1 and 3 months post-VTP treatment, and at 1 month post-VTP treatment in the crossover treatment group. Exploratory variables included fluorescein tear break-up time (TBUT), lid wiper epitheliopathy (LWE), lid parallel conjunctival folds (LIPCOF), ocular surface staining, frequency of over-the-counter (OTC) drop use, and hours of comfortable contact lens wear. RESULTS: At 3 months, the treatment group showed significantly greater mean change from baseline in MGS (12.4±9.1 vs 1.4±6.4, p<0.0001), SPEED (-8.4±4.7 vs -0.7±4.4, p<0.0001) and significantly greater improvement in exploratory variables (TBUT, LWE, and frequency of OTC drop use) relative to the controls. Mean comfortable contact lens wearing time increased by 4.0±3.9 hours at 1 month. This was sustained for 3 months with no change in the control group. The crossover treatment group demonstrated similar results to the treatment group at 1 month post-VTP. CONCLUSION: In SCL wearers with MGD, a single VTP treatment significantly improved mean meibomian gland function and significantly reduced dry eye signs and symptoms compared to an untreated control. The treatment increased mean comfortable lens wearing time by 4 hours (approximately doubling the pretreatment findings). This was sustained for up to 3 months post-treatment on average.