26 September 2024 : Database Analysis
Development and Internal Validation of Machine Learning to Predict Postoperative Worse Functional Status after Surgical Treatment for Thoracic Spinal Stenosis
Tun Liu12ABCE, Jia Li2D, Huaguang Qi3F, Bin Guo2B, Songchuan Zhao4CD, Baoping Zhang2F, Langbo Li5D, Gang Wu2A, Gang Wang1D*DOI: 10.12659/MSM.945310
Med Sci Monit 2024; 30:e945310
Table 2 Performance metrics of all the predictive machine learning models at the corresponding follow-up visits.
| Models | 30-Day worse function status | 6-Month worse function status | ||||||
|---|---|---|---|---|---|---|---|---|
| Model A | Model B | Model A | Model B | |||||
| Accuracy (%) | AUC | Accuracy (%) | AUC | Accuracy (%) | AUC | Accuracy (%) | AUC | |
| LightGBM | 81.71 | 0.70 | 84.04 | 0.76 | 75.17 | 0.68 | 84.10 | 0.78 |
| XGBoost | 69.94 | 0.61 | 88.17 | 0.83 | 68.10 | 0.53 | 81.08 | 0.73 |
| Random forest | 85.40 | 0.72 | 80.90 | 0.72 | 81.34 | 0.70 | 78.96 | 0.71 |
| Naïve Bays | 76.83 | 0.64 | 86.48 | 0.80 | 70.84 | 0.64 | 86.03 | 0.80 |
| AUC – area under the curve; ML – machine learning. In , preoperative variables were used to predict postoperative worse function status. In , preoperative variables and intraoperative variables were implemented in the model to predict postoperative worse function status. | ||||||||