| 1. |
- Liew, Bernard X. W., et al.
(författare)
-
Clinical predictive modelling of post-surgical recovery in individuals with cervical radiculopathy : a machine learning approach
- 2020
-
Ingår i: Scientific Reports. - : Nature Publishing Group. - 2045-2322. ; 10:1
-
Tidskriftsartikel (refereegranskat)abstract
- Prognostic models play an important role in the clinical management of cervical radiculopathy (CR). No study has compared the performance of modern machine learning techniques, against more traditional stepwise regression techniques, when developing prognostic models in individuals with CR. We analysed a prospective cohort dataset of 201 individuals with CR. Four modelling techniques (stepwise regression, least absolute shrinkage and selection operator [LASSO], boosting, and multivariate adaptive regression splines [MuARS]) were each used to form a prognostic model for each of four outcomes obtained at a 12 month follow-up (disability-neck disability index [NDI]), quality of life (EQ5D), present neck pain intensity, and present arm pain intensity). For all four outcomes, the differences in mean performance between all four models were small (difference of NDI<1 point; EQ5D<0.1 point; neck and arm pain<2 points). Given that the predictive accuracy of all four modelling methods were clinically similar, the optimal modelling method may be selected based on the parsimony of predictors. Some of the most parsimonious models were achieved using MuARS, a non-linear technique. Modern machine learning methods may be used to probe relationships along different regions of the predictor space.
|
|
| 2. |
- Peolsson, Anneli, et al.
(författare)
-
Neurological outcomes after surgery and postoperative rehabilitation for cervical radiculopathy due to disc disease: a 2-year-follow-up of a randomized clinical trial
- 2023
-
Ingår i: Scientific Reports. - : NATURE PORTFOLIO. - 2045-2322. ; 13:1
-
Tidskriftsartikel (refereegranskat)abstract
- Reports on neurological outcomes in patients with cervical radiculopathy (CR) undergoing surgery and postoperative rehabilitation are important to inform prognosis. This 2-year-follow-up of a randomized clinical trial aimed to compare secondary neurological outcomes between structured postoperative rehabilitation and a standard approach after surgery for CR. A secondary aim was to increase knowledge about recovery of neurological impairments in relation to patient-reported neck disability. Neurological outcomes included assessment of sensibility, motor function, arm reflexes and the Spurling test. A total of 153 and 135 participants (>70% response rate) completed the clinical examination. Between-group differences, changes over time, and associations between persistent neurological impairments and the Neck Disability Index were investigated. No between-group differences were reported (p>0.07), and neurological impairments in sensibility, motor function, and a positive Spurling test decreased over time in both groups (p<0.04). Persistent impairments in sensibility and reflex arm were most frequent at follow-up, whereas, a persistent positive Spurling test, and impairments in motor function were associated with higher NDI score. Neurological outcomes improved over time in patients undergoing surgery for CR with no between-group differences., However, persistent neurological impairments were common, and associated with poorer outcome for patient-reported neck disability.Clinical registration: clinicaltrial.gov NCT01547611, 08/03/2012, Title: Outcome of physiotherapy after surgery for cervical disc disease: a prospective multi-centre trial.
|
|
| 3. |
- Peolsson, Anneli, et al.
(författare)
-
Postoperative structured rehabilitation in patients undergoing surgery for cervical radiculopathy: a 2-year follow-up of a randomized controlled trial
- 2019
-
Ingår i: Journal of Neurosurgery. - : AMER ASSOC NEUROLOGICAL SURGEONS. - 1547-5654 .- 1547-5646. ; 31:1, s. 60-69
-
Tidskriftsartikel (refereegranskat)abstract
- OBJECTIVE Information about postoperative rehabilitation for cervical radiculopathy (CR) is scarce. The aim of this study was to investigate the additional benefits of structured postoperative rehabilitation (SPT), which was performed in all patients, compared with a pragmatic standard postoperative approach (SA), in which rehabilitation was used as needed and patients sought physiotherapy on their own without a referral, in patients with MRI evidence of disc herniation and concomitant clinical signs who underwent surgery for CR. METHODS Patients (n = 202) were randomized to receive SPT or SA. Included key variables in the present study were primary and selected secondary outcomes of a prospective randomized controlled multicenter study. The main outcome was the Neck Disability Index (NDI) score. The NDI score, pain variables, self-efficacy, and health-related quality of life were investigated at baseline and 3, 6, 12, and 24 months postoperatively. RESULTS SPT provided no additional benefits over SA (p = 0.08 to p = 0.99) at the postoperative 2-year follow-up. Both groups improved over time (p amp;lt; 0.0001), with no reported adverse effects. CONCLUSIONS One can conclude that SPT offered no additional benefits over SA; however, patients tolerated postoperative neck exercises without any negative side effects. These findings are important for the development of future active and neck-specific post-operative rehabilitation interventions for patients with CR.
|
|
