Refine
Document Type
- Article (2)
Language
- English (2) (remove)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- low back pain (2) (remove)
Institute
Publisher
- MDPI (2)
The aim of this study was to compare three sensorimotor training forms in patients with chronic low back pain to determine their effects on the reduction of pain-related impairment and changes in posturography. Over two weeks, during the multimodal pain therapy (MMPT) period, six sessions of sensorimotor physiotherapy or training in the Galileo® or Posturomed® (n = 25 per group) were performed. A significant reduction in pain-related impairment after the intervention phase was shown across all groups (time effect: p < 0.001; ηp2 = 0.415). There was no change in postural stability (time effect: p = 0.666; ηp2 = 0.003), but there was a significant improvement in the peripheral vestibular system (time effect: p = 0.014; ηp2 = 0.081). An interaction effect was calculated for the forefoot-hindfoot ratio (p = 0.014; ηp2 = 0.111). Only the Posturomed® group showed an improvement in anterior-posterior weight distribution (heel load: 47% vs. 49%). These findings suggest that these forms of sensorimotor training in the context of MMPT are suitable for reducing pain-related impairment. Posturography demonstrated stimulation of a subsystem, but no improvement in postural stability.
(1) Background: Predicting chronic low back pain (LBP) is of clinical and economic interest as LBP leads to disabilities and health service utilization. This study aims to build a competitive and interpretable prediction model; (2) Methods: We used clinical and claims data of 3837 participants of a population-based cohort study to predict future LBP consultations (ICD-10: M40.XX-M54.XX). Best subset selection (BSS) was applied in repeated random samples of training data (75% of data); scoring rules were used to identify the best subset of predictors. The rediction accuracy of BSS was compared to randomforest and support vector machines (SVM) in the validation data (25% of data); (3) Results: The best subset comprised 16 out of 32 predictors. Previous occurrence of LBP increased the odds for future LBP consultations (odds ratio (OR) 6.91 [5.05; 9.45]), while concomitant diseases reduced the odds (1 vs. 0, OR: 0.74 [0.57; 0.98], >1 vs. 0: 0.37 [0.21; 0.67]). The area-under-curve (AUC) of BSS was acceptable (0.78 [0.74; 0.82]) and comparable with SVM (0.78 [0.74; 0.82]) and randomforest (0.79 [0.75; 0.83]); (4) Conclusions: Regarding prediction accuracy, BSS has been considered competitive with established machine-learning approaches. Nonetheless, considerable misclassification is inherent and further refinements are required to improve predictions.