Machine Learning Models for Low Back Pain Detection and Factor Identification: Insights From a 6-Year Nationwide
YoungMin Bhak1, Tae-Keun Ahn2, Thomas A Peterson3
1Department of Biomedical Engineering, College of Information and Biotechnology, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea.
None:
This study aimed to enhance performance, identify additional predictors, and improve the interpretability of biopsychosocial machine learning models for low back pain (LBP). Using survey data from a 6-year nationwide study involving 17,609 adults aged ≥50 years (Korea National Health and Nutrition Examination Survey), we explored 119 factors to detect LBP in individuals who reported experiencing LBP for at least 30 days within the previous 3 months. Our primary model, model 1, employed eXtreme Gradient Boosting (XGBoost) and selected primary factors (PFs) based on their feature importance scores. To extend this, we introduced additional factors, such as lumbar X-ray findings, physical activity, sitting time, and nutrient intake levels, which were available only during specific survey periods, into models 2 to 4. Model performance was evaluated using the area under the curve, with predicted probabilities explained by SHapley Additive exPlanations. Eleven PFs were identified, and model 1 exhibited an enhanced area under the curve .8 (.77-.84, 95% confidence interval). The factors had varying impacts across individuals, underscoring the need for personalized assessment. Hip and knee joint pain were the most significant PFs. High levels of physical activity were found to have a negative association with LBP, whereas a high intake of omega-6 was found to have a positive association. Notably, we identified factor clusters, including hip joint pain and female sex, potentially linked to osteoarthritis. In summary, this study successfully developed effective XGBoost models for LBP detection, thereby providing valuable insight into LBP-related factors. Comprehensive LBP management, particularly in women with osteoarthritis, is crucial given the presence of multiple factors. PERSPECTIVE: This article introduces XGBoost models designed to detect LBP and explores the multifactorial aspects of LBP through the application of SHapley Additive exPlanations and network analysis on the 4 developed models. The utilization of this analytical system has the potential to aid in devising personalized management strategies to address LBP.
