Development and Internal Validation of Machine Learning to Predict Postoperative Worse Functional Status after Surgical Treatment for Thoracic Spinal Stenosis

Tun Liu; Jia Li; Huaguang Qi; Bin Guo; Songchuan Zhao; Baoping Zhang; Langbo Li; Gang Wu; Gang Wang

doi:10.12659/MSM.945310

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 Liu^12ABCE, Jia Li^2D, Huaguang Qi^3F, Bin Guo^2B, Songchuan Zhao^4CD, Baoping Zhang^2F, Langbo Li^5D, Gang Wu^2A, Gang Wang^1D*

DOI: 10.12659/MSM.945310

Med Sci Monit 2024; 30:e945310

Authors information Article notes Copyright and License information

Introduction Material and Methods Results and Evaluations Discussion Conclusions References

Related articles Order reprints Share article Share by email

View HTML version

Table 4 Comparison of performance of the best-performing regression models to predict postoperative JOA Score at the corresponding follow-up visits.

Models	30 Days after surgery			6 Months after surgery
Models	R2	RMSE	MAE	R2	RMSE	MAE
LightGBM	0.59	0.56	0.48	0.33	0.73	0.55
XGBoost	0.63	0.45	0.28	0.60	0.54	0.50

Naïve Bays	0.32	0.81	0.55	0.26	2.10	1.75
Elastic Net	0.62	0.54	0.51	0.52	0.56	0.52
JOA – Japanese orthopedic association; MAE – mean absolute error; R – coefficient of determination; RMSE – root mean square error.

Back to the Article

Development and Internal Validation of Machine Learning to Predict Postoperative Worse Functional Status after Surgical Treatment for Thoracic Spinal Stenosis

Your Privacy