2022, Article / Letter to editor (BMC Musculoskeletal Disorders, (2022))Background
While low back pain occurs in nearly everybody and is the leading cause of disability worldwide, we lack instruments to accurately predict persistence of acute low back pain. We aimed to develop and internally validate a machine learning model predicting non-recovery in acute low back pain and to compare this with current practice and ‘traditional’ prediction modeling.
Methods
Prognostic cohort-study in primary care physiotherapy. Patients (n = 247) with acute low back pain (≤ one month) consulting physiotherapists were included. Candidate predictors were assessed by questionnaire at baseline and (to capture early recovery) after one and two weeks. Primary outcome was non-recovery after three months, defined as at least mild pain (Numeric Rating Scale > 2/10). Machine learning models to predict non-recovery were developed and internally validated, and compared with two current practices in physiotherapy (STarT Back tool and physiotherapists’ expectation) and ‘traditional’ logistic regression analysis.
Results
Forty-seven percent of the participants did not recover at three months. The best performing machine learning model showed acceptable predictive performance (area under the curve: 0.66). Although this was no better than a’traditional’ logistic regression model, it outperformed current practice.
Conclusions
We developed two prognostic models containing partially different predictors, with acceptable performance for predicting (non-)recovery in patients with acute LBP, which was better than current practice. Our prognostic models have the potential of integration in a clinical decision support system to facilitate data-driven, personalized treatment of acute low back pain, but needs external validation first.
2020, Article / Letter to editor (BMC Musculoskeletal Disorders, vol. 21, iss. 1, (2020), pp. 163)BACKGROUND: Currently used performance measures for discrimination were not informative to determine the clinical benefit of predictor variables. The purpose was to evaluate if a former relevant predictor, kinesiophobia, remained clinically relevant to predict chronic occupational low back pain (LBP) in the light of a novel discriminative performance measure, Decision Curve Analysis (DCA), using the Net Benefit (NB). METHODS: Prospective cohort data (nn=n170) of two merged randomized trials with workers with LBP on sickleave, treated with Usual Care (UC) were used for the analyses. An existing prediction model for chronic LBP with the variables 'a clinically relevant change in pain intensity and disability status in the first 3 months', 'baseline measured pain intensity' and 'kinesiophobia' was compared with the same model without the variable 'kinesiophobia' using the NB and DCA. RESULTS: Both prediction models showed an equal performance according to the DCA and NB. Between 10 and 95% probability thresholds of chronic LBP risk, both models were of clinically benefit. There were virtually no differences between both models in the improved classification of true positive (TP) patients. CONCLUSIONS: This study showed that the variable kinesiophobia, which was originally included in a prediction model for chronic LBP, was not informative to predict chronic LBP by using DCA. DCA and NB have to be used more often to develop clinically beneficial prediction models in workers because they are more sensitive to evaluate the discriminate ability of prediction models.
2020, Article / Letter to editor (European Spine Journal, vol. 29, iss. 7, (2020), pp. 1660-1670)PURPOSE: To conduct a meta-analysis to describe clinical course of pain and disability in adult patients post-lumbar discectomy (PROSPERO: CRD42015020806). METHODS: Sensitive topic-based search strategy designed for individual databases was conducted. Patients (>n16 years) following first-time lumbar discectomy for sciatica/radiculopathy with no complications, investigated in inception (point of surgery) prospective cohort studies, were included. Studies including revision surgery or not published in English were excluded. Two reviewers independently searched information sources, assessed eligibility at title/abstract and full-text stages, extracted data, assessed risk of bias (modified QUIPs) and assessed GRADE. Authors were contacted to request raw data where data/variance data were missing. Meta-analyses evaluated outcomes at all available time points using the variance-weighted mean in random-effect meta-analyses. Means and 95% CIs were plotted over time for measurements reported on outcomes of leg pain, back pain and disability. RESULTS: A total of 87 studies (nn=n31,034) at risk of bias (49 moderate, 38 high) were included. Clinically relevant improvements immediately following surgery (>nMCID) for leg pain (0-10, mean before surgery 7.04, 50 studies, nn=n14,910 participants) and disability were identified (0-100, mean before surgery 53.33, 48 studies, nn=n15,037). Back pain also improved (0-10, mean before surgery 4.72, 53 studies, nn=n14,877). Improvement in all outcomes was maintained (to 7 years). Meta-regression analyses to assess the relationship between outcome data and a priori potential covariates found preoperative back pain and disability predictive for outcome. CONCLUSION: Moderate-level evidence supports clinically relevant immediate improvement in leg pain and disability following lumbar discectomy with accompanying improvements in back pain. These slides can be retrieved under Electronic Supplementary Material.