Word Memory Test Predicts Recovery in Claimants With Work-Related Head Injury.

OBJECTIVE: To investigate the predictive validity of the Word Memory Test (WMT), a verbal memory neuropsychological test developed as a performance validity measure to assess memory, effort, and performance consistency. DESIGN: Cohort study with 1-year follow-up. SETTING: Workers' compensation rehabilitation facility. PARTICIPANTS: Participants included workers' compensation claimants with work-related head injury (N=188; mean age, 44y; 161 men [85.6%]). INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Outcome measures for determining predictive validity included days to suspension of wage replacement benefits during the 1-year follow-up and work status at discharge in claimants undergoing rehabilitation. Analysis included multivariable Cox and logistic regression. RESULTS: Better WMT performance was significantly but weakly correlated with younger age (r=-.30), documented brain abnormality (r=.28), and loss of consciousness at the time of injury (r=.25). Claimants with documented brain abnormalities on diagnostic imaging scans performed better (∼9%) on the WMT than those without brain abnormalities. The WMT predicted days receiving benefits (adjusted hazard ratio, 1.13; 95% confidence interval, 1.04-1.24) and work status outcome at program discharge (adjusted odds ratio, 1.62; 95% confidence interval, 1.13-2.34). CONCLUSIONS: Our results provide evidence for the predictive validity of the WMT in workers' compensation claimants. Younger claimants and those with more severe brain injuries performed better on the WMT. It may be that financial incentives or other factors related to the compensation claim affected the performance.

Development of a computer-based clinical decision support tool for selecting appropriate rehabilitation interventions for injured workers.

PURPOSE: To develop a classification algorithm and accompanying computer-based clinical decision support tool to help categorize injured workers toward optimal rehabilitation interventions based on unique worker characteristics. METHODS: Population-based historical cohort design. Data were extracted from a Canadian provincial workers' compensation database on all claimants undergoing work assessment between December 2009 and January 2011. Data were available on: (1) numerous personal, clinical, occupational, and social variables; (2) type of rehabilitation undertaken; and (3) outcomes following rehabilitation (receiving time loss benefits or undergoing repeat programs). Machine learning, concerned with the design of algorithms to discriminate between classes based on empirical data, was the foundation of our approach to build a classification system with multiple independent and dependent variables. RESULTS: The population included 8,611 unique claimants. Subjects were predominantly employed (85 %) males (64 %) with diagnoses of sprain/strain (44 %). Baseline clinician classification accuracy was high (ROC = 0.86) for selecting programs that lead to successful return-to-work. Classification performance for machine learning techniques outperformed the clinician baseline classification (ROC = 0.94). The final classifiers were multifactorial and included the variables: injury duration, occupation, job attachment status, work status, modified work availability, pain intensity rating, self-rated occupational disability, and 9 items from the SF-36 Health Survey. CONCLUSIONS: The use of machine learning classification techniques appears to have resulted in classification performance better than clinician decision-making. The final algorithm has been integrated into a computer-based clinical decision support tool that requires additional validation in a clinical sample.

What is the rate of functional improvement during occupational rehabilitation in workers' compensation claimants?

OBJECTIVES: We examined the rate of functional change (using performance measures and a self-report questionnaire) during interdisciplinary occupational rehabilitation in workers' compensation claimants with a variety of musculoskeletal conditions. We also estimated the rate of improvement that could be considered clinically important and examined factors associated with rate of functional improvement. METHODS: A prospective cohort design was used, with data collected before and after claimants participated in an interdisciplinary occupational rehabilitation program. A consecutive sample was formed of claimants admitted between July 2005 and June 2007. Measures included performance-based functional measures (functional capacity evaluation, FCE) and a self-report questionnaire (pain disability index, PDI). RESULTS: The sample included 582 compensation claimants with a variety of musculoskeletal conditions. The majority of claimants experienced functional improvement during rehabilitation. Claimants with the outcome status 'Return-to-Work Pre-accident' had the highest rate of functional change (up to 5 kg/week on floor to waist lifting, ~7 points/week on the PDI). CONCLUSION: The clinically important rate of functional change appears to be 5 kg/week on FCE floor-to-waist lifting and 7 points/week on the PDI (scored out of 100). Rate of functional change appears to be multifactorial, with a variety of physical, demographic, clinical, and environmental factors explaining rate of change.

Changing to an outcome-focused program improves return to work outcomes.

OBJECTIVES: The purposes of this study were to: (1) evaluate the effectiveness of changing a Return to Work (RTW) program's focus to one that was "outcome-focused", and (2) to determine which factors collected in the facility's database were most predictive of RTW. METHODS: A total of 13,428 client files were extracted from Millard Health's database which included data on two cohorts of subjects: those in the program before and after the change in focus had been made. This was to determine whether significant improvements in outcomes were achieved. Variables that were hypothesized to be predictive of RTW were selected based on previous published literature. Analyses included ANOVA's, logistic regression analysis and Pearson correlation. RESULTS: Statistically significant improvements in RTW, total temporary disability claims, client satisfaction, efficiency of services and scores on the Perceived Disability Index (PDI), Short Form-36 (SF-36) and Visual Analogue Scale (VAS) for perceived pain were found. Variables that were predictive of RTW included: more efficient services, completion of a worksite visit, having the worker participate in the visit, availability of modified duties from the employer, fewer absences from the program and better scores on the PDI, SF-36 and VAS. The most predictive variable of RTW was sores on the PDI indicating lower levels of perceived disability. CONCLUSIONS: Changing to an outcome-focused program improved various outcomes in this RTW program. Several factors predict the outcome of RTW and these should be considered in treatment planning.