Initial classification of low back and leg pain based on objective functional testing: a pilot study of machine learning applied to diagnostics

Objective The five-repetition sit-to-stand (5R-STS) test was designed to capture objective functional impairment and thus provided an adjunctive dimension in patient assessment. The clinical interpretability and confounders of the 5R-STS remain poorly understood. In clinical use, it became apparent that 5R-STS performance may differ between patients with lumbar disk herniation (LDH), lumbar spinal stenosis (LSS) with or without low-grade spondylolisthesis, and chronic low back pain (CLBP). We seek to evaluate the extent of diagnostic information contained within 5R-STS testing. Methods Patients were classified into gold standard diagnostic categories based on history, physical examination, and imaging. Crude and adjusted comparisons of 5R-STS performance were carried out among the three diagnostic categories. Subsequently, a machine learning algorithm was trained to classify patients into the three categories using only 5R-STS test time and patient age, gender, height, and weight. Results From two prospective studies, 262 patients were included. Significant differences in crude and adjusted test times were observed among the three diagnostic categories. At internal validation, classification accuracy was 96.2% (95% CI 87.099.5%). Classification sensitivity was 95.7%, 100%, and 100% for LDH, LSS, and CLBP, respectively. Similarly, classification specificity was 100%, 95.7%, and 100% for the three diagnostic categories. Conclusion 5R-STS performance differs according to the etiology of back and leg pain, even after adjustment for demographic covariates. In combination with machine learning algorithms, OFI can be used to infer the etiology of spinal back and leg pain with accuracy comparable to other diagnostic tests used in clinical examination. Graphic abstract These slides can be retrieved under Electronic Supplementary Material.

[1]  V. Staartjes,et al.  Gender differences in degenerative spine surgery: Do female patients really fare worse? , 2018, European Spine Journal.

[2]  V. Staartjes,et al.  Letter to the Editor. Class imbalance in machine learning for neurosurgical outcome prediction: are our models valid? , 2018, Journal of neurosurgery. Spine.

[3]  Gary S Collins,et al.  Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement , 2015, BMC Medicine.

[4]  S. Lord,et al.  Kinect-Based Five-Times-Sit-to-Stand Test for Clinical and In-Home Assessment of Fall Risk in Older People , 2015, Gerontology.

[5]  V. Staartjes,et al.  Is elective degenerative lumbar spine surgery in older adults safe in a short-stay clinic? Data from an institutional registry , 2018, European Geriatric Medicine.

[6]  Allen L. Ho,et al.  Objective measures of functional impairment for degenerative diseases of the lumbar spine: a systematic review of the literature. , 2019, The spine journal : official journal of the North American Spine Society.

[7]  Lala Septem Riza,et al.  frbs: Fuzzy Rule-Based Systems for Classification and Regression in R , 2015 .

[8]  G. Collins,et al.  Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement , 2015, BMJ : British Medical Journal.

[9]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[10]  K. Schaller,et al.  The need for an objective outcome measurement in spine surgery--the timed-up-and-go test. , 2014, The spine journal.

[11]  V. Staartjes,et al.  The five-repetition sit-to-stand test: evaluation of a simple and objective tool for the assessment of degenerative pathologies of the lumbar spine. , 2018, Journal of neurosurgery. Spine.

[12]  G. Guyatt,et al.  The 6-minute walk: a new measure of exercise capacity in patients with chronic heart failure. , 1985, Canadian Medical Association journal.

[13]  Patrick C. Staples,et al.  Machine Learning and Neurosurgical Outcome Prediction: A Systematic Review. , 2018, World neurosurgery.

[14]  Sunil Munakomi Letter to the Editor. Reappraising role of clinical evaluations in degenerative lumbar spine pathologies. , 2019, Journal of Neurosurgery : Spine.

[15]  K. Schaller,et al.  Validity and Reliability of a Measurement of Objective Functional Impairment in Lumbar Degenerative Disc Disease: The Timed Up and Go (TUG) Test. , 2016, Neurosurgery.

[16]  Karl Schaller,et al.  Pre- and postoperative correlation of patient-reported outcome measures with standardized Timed Up and Go (TUG) test results in lumbar degenerative disc disease , 2016, Acta Neurochirurgica.

[17]  V. Staartjes,et al.  Can objective functional impairment in lumbar degenerative disease be reliably assessed at home using the five-repetition sit-to-stand test? A prospective study , 2019, European Spine Journal.

[18]  S. Kon,et al.  The five-repetition sit-to-stand test as a functional outcome measure in COPD , 2013, Thorax.

[19]  V. Staartjes,et al.  Machine learning-based preoperative predictive analytics for lumbar spinal stenosis. , 2019, Neurosurgical focus.

[20]  Ludmila I. Kuncheva,et al.  Fuzzy Classifier Design , 2000, Studies in Fuzziness and Soft Computing.

[21]  K. Schaller,et al.  Patients' Preference of the Timed Up and Go Test or Patient-Reported Outcome Measures Before and After Surgery for Lumbar Degenerative Disk Disease. , 2017, World neurosurgery.

[22]  Gustavo E. A. P. A. Batista,et al.  A study of the behavior of several methods for balancing machine learning training data , 2004, SKDD.

[23]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .