ABSTRACT
Objective:To investigate the performance of a predictive model based on fat suppression (FS)-T2WI sequence combined with machine learning in the differential diagnosis of brucellar spondylitis (BS) and tuberculous spondylitis (TS).Methods:The clinical and imaging data of 74 patients with BS and 81 patients with TS diagnosed clinically or pathologically in the First Affiliated Hospital of Xinjiang Medical University from January 2017 to January 2022 were retrospectively analyzed, and all patients underwent spinal magnetic resonance imaging (MRI) examination before treatment. Patients were randomly divided into a training group ( n = 123) and a testing group ( n = 32) in an 8 ∶ 2 allocation ratio, and radiomics feature extraction and dimensionality reduction analysis were performed on FS-T2WI sequence images. Four machine learning algorithms, including K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF) and logistic regression (LR), were used to construct a radiomics model, and receiver operating characteristic (ROC) curve was used to analyze the differential diagnostic performance of each model for BS and TS. Results:A total of 1 409 radiomics features were extracted, and 7 related features were screened and included for identification of BS and TS, among which the Maximum2DDiameterColumn feature value showed a strong correlation, and there was a statistically significant difference between BS and TS patients ( P < 0.001). In the testing group, the area under the ROC curve (AUC) value of the SVM model for identifying BS and TS was 0.886, with a sensitivity of 0.53, a specificity of 0.88, and a diagnostic accuracy of 0.81; in the training group, the AUC value of the SVM model for identifying BS and TS was 0.811, the sensitivity was 0.68, the specificity was 0.72, and the diagnostic accuracy of the model was 0.78. Conclusion:The prediction model based on FS-T2WI sequence combined with machine learning can be used to identify BS and TS, and the diagnostic performance of SVM model is prominent and stable.
ABSTRACT
Objective:To explore the influence of childhood abuse experience on relapse tendency of compulsory drug abusers, and the intermediary role of resilience and depression between them.Methods:A total of 261 drug abusers were investigated with childhood trauma questionnaire(CTQ), the Connor-Davidson resilience scale (CD-RISC), self-rating depression scale (SDS) and relapse tendency psychological questionnaire.All data processing and analysis were carried out by SPSS 25.0 software.Correlation analysis, Bootstrap analysis and other methods were used to test the mediating effect.Results:The scores of childhood abuse treatment, resilience, depression and relapse tendency were 44.690±18.550, 60.210±22.790, 48.370±12.450, and 15.300±9.833 respectively.Childhood abuse was negatively correlated with resilience( r=-0.396, P<0.01), and positively correlated with depression and relapse tendency( r=0.584, 0.298, P<0.01).Resilience was negatively correlated with depression and relapse tendency( r=-0.558, -0.147, P<0.05).Depression had a significant positive correlation with relapse tendency( r=0.286, P<0.01).Childhood abuse could directly predict the tendency of relapse( β=0.202, P<0.01), and it could also affect the tendency of relapse through the mediation of depression( β=0.082, 95% CI=0.007-0.165) and the chain mediation of resilience and depression( β=0.029, 95% CI=0.002-0.064). Conclusion:The experience of childhood abuse leads to the decrease of resilience of strong abstinence personnel and increases the level of depression, which finally increases the tendency of relapse.