Diagnosis of Acute Versus Chronic Thoracolumbar Vertebral Compression Fractures Using CT Radiomics Based on Machine Learning: a Preliminary Study.

The purpose of this study is to evaluate the performance of radiomic models in acute thoracolumbar vertebral compression fractures (VCFs) and their impact on radiologists. In this monocentre retrospective study, eligible for inclusion were adults who underwent emergent thoracic/lumbar CT between May 2022 and November 2023 in our hospital diagnosed with thoracolumbar VCFs. The lesions were randomly divided at a ratio of 7:3 into a training set and test set. For external validation, consecutive patients who underwent emergent thoracic/lumbar CT between January 2022 and April 2022 were included. MRI and previous imaging were used as reference standard. The vertebral body area was manually segmented. Logistic regression was used to construct a CT radiomic model and a combined model, including Relief-selected radiomic features and clinical information. The radiologists' diagnosis with and without the models was recorded. The performance was assessed using receiver operating characteristic curves (ROC), calibration curves (CC) and decision curve analysis (DCA). Of 235 VCFs in 147 patients (median age, 73 years, 66 male) included, the diagnosis of acute VCFs was confirmed in 126. The area under the ROC of the CT radiomics model and the combined model in the external validation set were 0.883 (95% CI 0.777, 0.998) and 0.875 (95% CI 0.768, 0.982), respectively. CC and DCA showed good clinical application of the models. The less experienced reader achieved a higher accuracy with the help of the models (p = 0.027). The radiomic models showed high accuracy for diagnosing acute VCFs and helped radiologists improve the accuracy of diagnosis.