A DWI-based radiomics-clinical machine learning model to preoperatively predict the futile recanalization after endovascular treatment of acute basilar artery occlusion patients. Issue 161 (April 2023)

• Record Type: Journal Article
• Authors: Luo, Yuqi; Sun, Xuan; Kong, Xin; Tong, Xu; Xi, Fengjun; Mao, Yu; Miao, Zhongrong; Ma, Jun
• Is Part Of: European journal of radiology. Issue 161(2023)
• Publication Date: 2023-04
• Subjects: Basilar artery occlusion -- Futile recanalization -- Endovascular treatment -- Radiomics; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2023.110731
• Languages: English
• ISSNs: 0720-048X

Abstract

Abstract: Objective: To develop an effective machine learning model to preoperatively predict the occurrence of futile recanalization (FR) of acute basilar artery occlusion (ABAO) patients with endovascular treatment (EVT). Materials and Methods: Data from 132 ABAO patients (109 male [82.6 %]; mean age ± standard deviation, 59.1 ± 12.5 years) were randomly divided into the training (n = 106) and test cohort (n = 26) with a ratio of 8:2. FR is defined as a poor outcome [modified Rankin Scale (mRS) 4–6] despite a successful recanalization [modified Thrombolysis in Cerebral Infarction (mTICI) ≥ 2b]. A total of 1130 radiomics features were extracted from diffusion-weighted imaging (DWI) images. The least absolute shrinkage and selection operator (LASSO) regression method was applicated to select features. Support vector machine (SVM) was applicated to construct radiomics and clinical models. Finally, a radiomics-clinical model that combined clinical with radiomics features was developed. The models were evaluated by receiver operating characteristic (ROC) curve and decision curve. Results: The area under the receiver operating characteristic (ROC) curve (AUC) of the radiomics-clinical model was 0.897 (95 % confidence interval, 0.837–0.958) in the training cohort and 0.935 (0.833–1.000) in the test cohort. The AUC of the radiomics model was 0.887 (0.824–0.951) in the training cohort and 0.840 (0.680–1.000) in the test cohort. The AUC of the clinical model was 0.746 (0.652–0.840) in the training cohort and 0.766 (0.569–0.964) in the test cohort. The AUC of the radiomics-clinical model was significantly larger than the clinical model (p = 0.016). A radiomics-clinical nomogram was developed. The decision curve analysis indicated its clinical usefulness. Conclusion: The DWI-based radiomics-clinical machine learning model achieved satisfactory performance in predicting the FR of ABAO patients preoperatively.