Skip to main content
Fig. 4 | BMC Medicine

Fig. 4

From: Multimodal-based machine learning strategy for accurate and non-invasive prediction of intramedullary glioma grade and mutation status of molecular markers: a retrospective study

Fig. 4

The fivefold cross-validation results in the ATRX genotype prediction task. a The comparison results of the proposed ATRX-Mind with the mainstream machine learning models. b The ROC curves of ATRX-Mind when inputting features of the SAG phase (left), TRA phase (middle), and SAG combined with TRA phase (right). c The ROC curves of ATRX-Mind when the features of the SAG phase-clinical baseline (left), TRA phase-clinical baseline (middle), and SAG phase-TRA phase-clinical baseline (right) are inputted. ATRX, alpha thalassemia/mental retardation syndrome X-linked; AUC, area under the curve; ROC, receiver operating characteristic; SAG, sagittal; TRA, transverse

Back to article page

BMC Medicine

ISSN: 1741-7015

Contact us