Abstract
PURPOSE: Non-specific low back pain (NLBP) is a common clinical condition that affects approximately 60-80% of adults worldwide. However, there is currently a lack of scientific prediction and evaluation systems in clinical practice. The purpose of this study was to analyze the risk factors of NLBP and construct a risk prediction model. METHODS: We collected baseline data from 707 patients who met the inclusion criteria and were treated at the Sixth Hospital of Ningbo from December 2020 to December 2022. Logistic regression and LASSO regression were used to screen independent risk factors that influence the onset of NLBP and to construct a risk prediction model. The sensitivity and specificity of the model were evaluated by tenfold cross-validation, and internal validation was performed in the validation set. RESULTS: Age, gender, BMI, education level, marital status, exercise frequency, history of low back pain, labor intensity, working posture, exposure to vibration sources, and psychological status were found to be significantly associated with the onset of NLBP. Using these 11 predictive factors, a nomogram was constructed, and the area under the ROC curve of the training set was 0.835 (95% CI 0.756-0.914), with a sensitivity of 0.771 and a specificity of 0.800. The area under the ROC curve of the validation set was 0.762 (95% CI 0.665-0.858), with a sensitivity of 0.800 and a specificity of 0.600, indicating that the predictive value of the model for the diagnosis of NLBP was high. In addition, the calibration curve showed a high degree of consistency between the predicted and actual survival probabilities. CONCLUSION: We have developed a preliminary predictive model for NLBP and constructed a nomogram to predict the onset of NLBP. The model demonstrated good performance and may be useful for the prevention and treatment of NLBP in clinical practice.