Abstract
OBJECTIVE: Failure to understand long-term quality of life and functional outcomes hinders effective decision making and prognostication. Therefore, the study aims to predict and analyse the unfavorable outcomes (FOs) in elderly patients undergoing lumbar fusion surgery. METHODS: Consecutive 382 patients who underwent lumbar fusion surgery for lumbar degenerative disease from March 2019 to July 2022 were enrolled in this study. The risk factors were selected by the least absolute shrinkage and selection operator method (LASSO) regression. Then, a nomogram prediction model was established to predict unfavorable outcomes (UFOs) by using the risk factors selected from LASSO regression. The performance of the model was assessed by the calibration curve and receiver operating characteristic (ROC) curve. The decision curve analysis (DCA) and clinical impact curve (CIC) were used to evaluate the clinical utility of the model. RESULTS: Finally, 147 of 382 patients showed UFOs. After splitting data in a 70 - 30 fashion, 267 patients were included in the training set. Ten potential risk factors were selected according to the LASSO regression, that identified the predictor to establish nomogram model. The area under the curve (AUC) value was 0.828, and the calibration curve gained from this prediction model suggested good predictive accuracy between the predicted probability and actual probability. In the validation set, the AUC for the model was 0.858. Likewise, the calibration curve gained from this prediction model suggested good predictive accuracy between the predicted probability and actual probability. And the results of DCA and CIC demonstrated that the model showed good clinical practicability in the validation set. CONCLUSION: This nomogram model has good predictive performance and clinical practicability, which could provide a certain basis for predicting UFOs in elderly patients undergoing lumbar fusion surgery.