Abstract
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.
Similar content being viewed by others
References
Lane R, Desjardins S. Canada, population and public health branch. Strategic policy directorate. Policy research division. Economic burden of illness in Canada, 1998. Ottawa: Health Canada; 2002.
Hadler NM. Occupational musculoskeletal disorders. 3rd ed. Philadelphia: Lippincott Williams & Wilkins; 2005.
Martin BI, Deyo RA, Mirza SK, et al. Expenditures and health status among adults with back and neck problems. JAMA. 2008;299:656–64.
Frank JW, Kerr MS, Brooker AS, et al. Disability resulting from occupational low back pain. Part I: what do we know about primary prevention? A review of the scientific evidence on prevention before disability begins. SPINE. 1996;21:2908–17.
Shaw WS, van der Windt DA, Main CJ, Loisel P, Linton SJ. Early patient screening and intervention to address individual-level occupational factors (“blue flags”) in back disability. J Occup Rehabil. 2009;19:64–80.
Steenstra IA, Ibrahim SA, Franche RL, Hogg-Johnson S, Shaw WS, Pransky GS. Validation of a risk factor-based intervention strategy model using data from the readiness for return to Work Cohort Study. J Occup Rehabil. 2009;20:394–405.
Shaw WS, Linton SJ, Pransky G. Reducing sickness absence from work due to low back pain: how well do intervention strategies match modifiable risk factors? J Occup Rehabil. 2006;16:591–605.
Haldorsen EM. The right treatment to the right patient at the right time. Occup Environ Med. 2003;60:235–6.
Dahm KT, Brurberg KG, Jamtvedt G, Hagen KB. Advice to rest in bed versus advice to stay active for acute low-back pain and sciatica. Cochrane Database Syst Rev. 2010;6:CD007612.
van Tulder MW, Tuut M, Pennick V, Bombardier C, Assendelft WJ. Quality of primary care guidelines for acute low back pain. SPINE. 2004;29:E357–62.
AAMPG Group. Evidence-based management of acute musculoskeletal pain: a guide for clinicians. Bowen Hills: Australian Government National Health and Medical Research Council; 2004.
Sinclair SJ, Hogg-Johnson SH, Mondloch MV, Shields SA. The effectiveness of an early active intervention program for workers with soft-tissue injuries. The Early Claimant Cohort Study. SPINE. 1997;22:2919–31.
Cassidy JD, Carroll LJ, Cote P, Frank J. Does multidisciplinary rehabilitation benefit whiplash recovery? Results of a population-based incidence cohort study. SPINE (Phila Pa 1976). 2007;32:126–31.
McIntosh G, Frank J, Hogg-Johnson S, Bombardier C, Hall H. Prognostic factors for time receiving workers’ compensation benefits in a cohort of patients with low back pain. SPINE. 2000;25:147–57.
van Tulder M, Becker A, Bekkering T, et al. Chapter 3. European guidelines for the management of acute nonspecific low back pain in primary care. Eur Spine J. 2006;15(Suppl 2):S169–91.
Schaafsma F, Schonstein E, Whelan KM, Ulvestad E, Kenny DT, Verbeek JH. Physical conditioning programs for improving work outcomes in workers with back pain. Cochrane Database Syst Rev. 2010;20:CD001822.
van Oostrom SH, Driessen MT, de Vet HC, et al. Workplace interventions for preventing work disability. Cochrane Database Syst Rev. 2009;15:CD006955
Karjalainen K, Malmivaara A, van Tulder M, et al. Multidisciplinary biopsychosocial rehabilitation for subacute low back pain among working age adults. Cochrane Database Syst Rev. 2003;2:CD002193.
Gross DP, Haws C, Niemelainen R. What is the rate of functional improvement during occupational rehabilitation in workers’ compensation claimants? J Occup Rehabil. 2012;22:292–300.
Gross DP, Battie MC. Predicting timely recovery and recurrence following multidisciplinary rehabilitation in patients with compensated low back pain. SPINE. 2005;30:235–40.
Sandstrom J, Esbjornsson E. Return to work after rehabilitation. The significance of the patient’s own prediction. Scand J Rehabil Med. 1986;18:29–33.
Steenstra IA, Knol DL, Bongers PM, Anema JR, van Mechelen W, de Vet HC. What works best for whom? An exploratory, subgroup analysis in a randomized, controlled trial on the effectiveness of a workplace intervention in low back pain patients on return to work. SPINE (Phila Pa 1976). 2009;34:1243–9.
Gatchel RJ, Polatin PB, Noe C, Gardea M, Pulliam C, Thompson J. Treatment- and cost-effectiveness of early intervention for acute low -back pain patients: a one-year prospective study. J Occup Rehab. 2003;13:1–9.
Hill JC, Whitehurst DG, Lewis M, et al. Comparison of stratified primary care management for low back pain with current best practice (STarT Back): a randomised controlled trial. Lancet. 2011;378:1560–71.
Occupational injuries and diseases in Alberta: 2004–2008: Government of Alberta Employment and Immigration; 2009.
WorkSafeBC website Accessed January 15, 2013, at http://www2.worksafebc.com/Topics/Ergonomics/BackPainBasics.asp.
Vranceanu AM, Barsky A, Ring D. Psychosocial aspects of disabling musculoskeletal pain. J Bone Joint Surg Am. 2009;91:2014–8.
Noonan J, Wagner SL. A biopsychosocial perspective on the management of work-related musculoskeletal disorders. AAOHN J. 2010;58:105–14.
Nicholas MK, George SZ. Psychologically informed interventions for low back pain: an update for physical therapists. Phys Ther. 2011;91:765–76.
Miciak M, Gross DP, Joyce A. A review of the psychotherapeutic ‘common factors’ model and its application in physical therapy: the need to consider general effects in physical therapy practice. Scand J Caring Sci. 2012;26:394–403
Nicholas MK, Linton SJ, Watson PJ, Main CJ. Early identification and management of psychological risk factors (“yellow flags”) in patients with low back pain: a reappraisal. Phys Ther. 2011;91:737–53.
Fritz JM, Beneciuk JM, George SZ. Relationship between categorization with the STarT back screening tool and prognosis for people receiving physical therapy for low back pain. Phys Ther. 2011;91:722–32.
Clinical Prediction Rules: A Physical Therapy Reference. USBMIS, Inc. Accessed January 15, 2013, at http://itunes.apple.com/us/app/clinical-prediction-rules/id439974538?mt=8.
Souza NM, Sebaldt RJ, Mackay JA, et al. Computerized clinical decision support systems for primary preventive care: a decision-maker-researcher partnership systematic review of effects on process of care and patient outcomes. Implement Sci. 2011;6:87.
Sahota N, Lloyd R, Ramakrishna A, et al. Computerized clinical decision support systems for acute care management: a decision-maker-researcher partnership systematic review of effects on process of care and patient outcomes. Implement Sci. 2011;6:91.
Roshanov PS, Misra S, Gerstein HC, et al. Computerized clinical decision support systems for chronic disease management: a decision-maker-researcher partnership systematic review. Implement Sci. 2011;6:92.
Hemens BJ, Holbrook A, Tonkin M, et al. Computerized clinical decision support systems for drug prescribing and management: a decision-maker-researcher partnership systematic review. Implement Sci. 2011;6:89.
Blackmore CC, Mecklenburg RS, Kaplan GS. Effectiveness of clinical decision support in controlling inappropriate imaging. Journal of the American College of Radiology : JACR. 2011;8:19–25.
Lin L, Jen-Hwa H, Sheng ORL. A decision support system for lower back pain diagnosis: uncertainty management and clinical evaluations. Decis Support Syst. 2006;42:1152–69.
Position of the American Dietetic Association. Nutrition, aging, and the continuum of care. J Am Diet Assoc. 2000;100:580–95.
Stephens B, Gross DP. The influence of a continuum of care model on the rehabilitation of compensation claimants with soft tissue disorders. SPINE. 2007;32:2898–904.
Frank JW, Brooker AS, DeMaio SE, et al. Disability resulting from occupational low back pain. Part II: what do we know about secondary prevention? A review of the scientific evidence on prevention after disability begins. SPINE. 1996;21:2918–29.
Ikezawa Y, Battie MC, Beach J, Gross D. Do clinicians working within the same context make consistent return-to-work recommendations? J Occup Rehabil. 2010;20:367–77.
Gross DP, Battie MC, Cassidy JD. The prognostic value of functional capacity evaluation in patients with chronic low back pain: part 1: timely return to work. SPINE. 2004;29:914–9.
Gross DP, Battie MC, Asante AK. The Patient-Specific Functional Scale: validity in workers’ compensation claimants. Arch Phys Med Rehabil. 2008;89:1294–9.
Gross DP, Battie MC. Recovery expectations predict recovery in workers with back pain but not other musculoskeletal conditions. J Spinal Disord Tech. 2010;23:451–6.
Gross DP, Batti MC. Does functional capacity evaluation predict recovery in workers compensation claimants with upper extremity disorders? Occup Environ Med. 2006;63:404–10.
Canadian Standards Association. Coding of work injury or disease information. ON, Canada: Mississauga; 2003.
National Occupational Classification: Occupational descriptions: Human Resources Development Canada; 2001.
Finch E, Brooks D, Stratford P, Mayo N. Physical rehabilitation outcome measures: a guide to enhanced clinical decision making. 2nd ed. Toronto: Canadian Physiotherapy Association; 2002.
Pollard CA. Preliminary validity study of the pain disability index. Percept Mot Skills. 1984;59:974.
Gronblad M, Jarvinen E, Hurri H, Hupli M, Karaharju EO. Relationship of the Pain Disability Index (PDI) and the Oswestry Disability Questionnaire (ODQ) with three dynamic physical tests in a group of patients with chronic low-back and leg pain. Clin J Pain. 1994;10:197–203.
Tait RC, Pollard CA, Margolis RB, Duckro PN, Krause SJ. The Pain Disability Index: psychometric and validity data. Arch Phys Med Rehabil. 1987;68:438–41.
Kang SW, Lee WN, Moon JH, Chun SI. Correlation of spinal mobility with the severity of chronic lower back pain. Yonsei Med J. 1995;36:37–44.
Gronblad M, Hurri H, Kouri JP. Relationships between spinal mobility, physical performance tests, pain intensity and disability assessments in chronic low back pain patients. Scand J Rehabil Med. 1997;29:17–24.
Chibnall JT, Tait RC. The Pain Disability Index: factor structure and normative data. Arch Phys Med Rehabil. 1994;75:1082–6.
McHorney CA, Ware JE Jr, Raczek AE. The MOS 36-Item Short-Form Health Survey (SF-36): II. Psychometric and clinical tests of validity in measuring physical and mental health constructs. Med Care. 1993;31:247–63.
Ware JE, Gandek B. The SF-36 Health Survey: development and use in mental health research at the IQLOA project. Int J Mental Health. 1994;23:73.
Grevitt M, Khazim R, Webb J, Mulholland R, Shepperd J. The short form-36 health survey questionnaire in spine surgery. J Bone Joint Surg Br. 1997;79:48–52.
Guilfoyle MR, Seeley H, Laing RJ. The Short Form 36 health survey in spine disease–validation against condition-specific measures. Br J Neurosurg. 2009;23:401–5.
Krousel-Wood MA, McCune TW, Abdoh A, Re RN. Predicting work status for patients in an occupational medicine setting who report back pain. Arch Fam Med. 1994;3:349–55.
Chen C, Hogg-Johnson S, Smith P. The recovery patterns of back pain among workers with compensated occupational back injuries. Occup Environ Med. 2007;64:534–40.
Kotsiantis SB. Supervised machine learning: a review of classification techniques. Informatica. 2007;37:249–68.
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321–57.
Batista GEAPA, Prati RC, Monard MC. A study of the behavior of several methods for balancing machine learning training data. In: ACM SIGKDD explorations newsletter—special issue on learning from imbalanced datasets; 2004. p. 20–9.
Hall MA. Correlation-based feature selection for discrete and numeric class machine learning. In: 17th international conference on machine learning. Stanford, CA; 2000. p. 359–66.
Gutlein M. Large scale attribute selection using wrappers. [Masters’ Thesis]. Freiburg: Albert-Ludwigs-Universitat; 2006.
Cohen WW. Fast effective rule induction. In: Twelve international conference of machine learning (ICML-95); 1995. p. 115–23.
Duma M, Twala B, Marwala T, Newamondo FV. Improving the performance of the ripper in insurance risk classification—A Comparitive Study using feature selection. In: 8th international conference on informatics in control, automation and robotics. Noordwikerhout, The Netherlands; 2011. p. 203–10.
Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the fourteenth international joint conference on artificial intelligence; 1995; San Mateo, California: Morgan Kaufmann; 1995. p. 1137–43.
Holmes G, Donkin A, Witten IH. Weka: a machine learning workbench. In: Second Australia and New Zealand conference on intelligent information systems; Brisbane, Australia; 1994. p. 357–61.
Witten IH, Frank E, Hall MA. Data mining: practical machine learning tools and techniques. Part III: The weka data mining workbench, 3rd edn. San Francisco, USA: Morgan Kaufmann; 2011.
Franche RL, Cullen K, Clarke J, Irvin E, Sinclair S, Frank J. Workplace-based return-to-work interventions: a systematic review of the quantitative literature. J Occup Rehabil. 2005;15:607–31.
Franche RL, Severin CN, Hogg-Johnson S, Cote P, Vidmar M, Lee H. The impact of early workplace-based return-to-work strategies on work absence duration: a 6-month longitudinal study following an occupational musculoskeletal injury. J Occup Environ Med. 2007;49:960–74.
Acknowledgments
The Workers’ Compensation Board of Alberta facilitated data collection and provided funding in support of this research.
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Gross, D.P., Zhang, J., Steenstra, I. et al. Development of a Computer-Based Clinical Decision Support Tool for Selecting Appropriate Rehabilitation Interventions for Injured Workers. J Occup Rehabil 23, 597–609 (2013). https://doi.org/10.1007/s10926-013-9430-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10926-013-9430-4