Support vector machine based aphasia classification of transcranial magnetic stimulation language mapping in brain tumor patients

• Published in: NeuroImage clinical Vol. 29; p. 102536
• Main Authors: Wang, Ziqian, Dreyer, Felix, Pulvermüller, Friedemann, Ntemou, Effrosyni, Vajkoczy, Peter, Fekonja, Lucius S., Picht, Thomas
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Inc 01.01.2021; Elsevier
• Subjects: Aphasia - etiology; Brain Mapping; Brain Neoplasms - diagnostic imaging; Glioma; Humans; Language; Machine learning; Magnetic Resonance Imaging; Radiology; Regular; Retrospective Studies; Stroke; Support Vector Machine; Transcranial Magnetic Stimulation; Transcranial magnetic stimulation; ROC; MNI; VAS; IQR; SVM; Support vector machine; AAL; ER; Machine Learning; ROI; AUC; RFE; AAT; BAS; Language; Glioma; TMS; rTMS; visual analogue scale; Berlin aphasia score; recursive feature elimination; interquartile range; transcranial magnetic stimulation; area under receiver operating characteristic curve; receiver operating characteristic; ML; repetitive transcranial magnetic stimulation; Montreal neurological institute; Aachen aphasia test; support vector machine; error rate; region of interest; automated anatomical labeling; Machine learning
• ISSN: 2213-1582; 2213-1582
• DOI: 10.1016/j.nicl.2020.102536

[Display omitted] •First study using machine learning to classify rTMS language mapping results in tumor patients.•Analysis of 90 patients reveals rTMS-induced error patterns in aphasic/non-aphasic patients.•Increased vulnerability of right pars triangularis to rTMS in aphasic patients with left gliomas. Repetitive TMS (rTMS) allows for non-invasive and transient disruption of local neuronal functioning. We used machine learning approaches to assess whether brain tumor patients can be accurately classified into aphasic and non-aphasic groups using their rTMS language mapping results as input features. Given that each tumor affects the subject-specific language networks differently, resulting in heterogenous rTMS functional mappings, we propose the use of machine learning strategies to classify potential patterns of rTMS language mapping results. We retrospectively included 90 patients with left perisylvian world health organization (WHO) grade II-IV gliomas that underwent presurgical navigated rTMS language mapping. Within our cohort, 29 of 90 (32.2%) patients suffered from at least mild aphasia as shown in the Aachen Aphasia Test based Berlin Aphasia Score (BAS). After spatial normalization to MNI 152 of all rTMS spots, we calculated the error rate (ER) in each stimulated cortical area (28 regions of interest, ROI) by automated anatomical labeling parcellation (AAL3) and IIT. We used a support vector machine (SVM) to classify significant areas in relation to aphasia. After feeding the ROIs into the SVM model, it revealed that in addition to age (w = 2.98), the ERs of the left supramarginal gyrus (w = 3.64), left inferior parietal gyrus (w = 2.28) and right pars triangularis (w = 1.34) contributed more than other features to the model. The model’s sensitivity was 86.2%, the specificity was 82.0%, the overall accuracy was 85.5% and the AUC was 89.3%. Our results demonstrate an increased vulnerability of right inferior pars triangularis to rTMS in aphasic patients due to left perisylvian gliomas. This finding points towards a functional relevant involvement of the right pars triangularis in response to aphasia. The tumor location feature, specified by calculating overlaps with white and grey matter atlases, did not affect the SVM model. The left supramarginal gyrus as a feature improved our SVM model the most. Additionally, our results could point towards a decreasing potential for neuroplasticity with age.