Objective: The aim of this study was to investigate the feasibility of muscle CT radiomics in identifying gout.
Materials And Methods: A total of 30 gout patients and 20 non-gout cases with CT examinations of ankles were analyzed by using the methods of CT radiomics. CT radiomics features of the soleus muscle were extracted using the software of a 3D slicer, and then gout cases and non-gout cases were compared. The radiomics features that were significantly different between the two groups were then processed with machine learning methods. Receiver operating characteristic curve analysis was used to evaluate the diagnostic performance.
Results: Five CT radiomics features were significantly different between gout cases and non-gout cases (P < 0.05). In the logic regression, the AUC, sensitivity, specificity, and accuracy were 0.738, 77% (46/60), 70% (28/40), and 74% (74/100), respectively. In the Random forest, Xgboost, and support vector machine analysis, the accuracy was 0.901, 0.833, and 0.875, respectively.
Conclusion: From this study, it can be concluded that muscle CT radiomics is feasible in identifying gout.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.2174/0115734056313937240816070503 | DOI Listing |
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!