Article
Refine
Year of publication
- 2021 (14) (remove)
Document Type
- Article (14) (remove)
Has Fulltext
- yes (14)
Is part of the Bibliography
- no (14)
Keywords
- - (10)
- cognitive function (2)
- dementia (2)
- physical activity (2)
- AgeWell.de (1)
- Aufgabenneuverteilung (1)
- Dementia (1)
- Demenz (1)
- Inhaltsanalyse (1)
- RCT (1)
- SARS-CoV-2 infections (1)
- ambulante Versorgung (1)
- amiloride-sensitive sodium channel ENaC (1)
- area deprivation (1)
- association study (1)
- best subset selection (1)
- calibration (1)
- chronic disease (1)
- cluster-randomized controlled trial (1)
- content analysis (1)
- control measures (1)
- cortisol (1)
- cystic fibrosis (1)
- education (1)
- general practitioner (1)
- income (1)
- interprofessional health care (1)
- interprofessionelle Zusammenarbeit (1)
- intervention (1)
- lifestyle (1)
- longitudinal cohort study (1)
- low back pain (1)
- machine learning (1)
- macrovascular disease (1)
- mediation (1)
- mental illness (1)
- metabolome (1)
- modifier gene (1)
- moving study (1)
- multivariate regression analysis (1)
- oral contraceptives (1)
- outpatient care (1)
- patient-reported outcome (1)
- phenotyping (1)
- population-based imaging (1)
- population-based studies (1)
- prevention (1)
- primary care (1)
- quality of life (1)
- questionnaire development (1)
- radiomics (1)
- record linkage (1)
- routine surveillance data (1)
- schools and pre-schools (1)
- study protocol (1)
- task shifting (1)
- telemedicine (1)
- trial (1)
- whole-body magnetic resonance imaging (1)
Institute
- Institut für Community Medicine (14) (remove)
Publisher
- MDPI (7)
- Frontiers Media S.A. (2)
- Public Library of Science (PLoS) (2)
- BMJ Publishing Group (1)
- Hogrefe (1)
(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.