Prediction of Postoperative Speech Dysfunctions in Neurosurgery Based on Cortico-Cortical Evoked Potentials and Machine Learning Technology.

Intraoperative recording of cortico-cortical evoked potentials (CCEPs) enables studying effective connections between various functional areas of the cerebral cortex. The fundamental possibility of postoperative speech dysfunction prediction in neurosurgery based on CCEP signal variations could serve as a basis to develop the criteria for the physiological permissibility of intracerebral tumors removal for maximum preservation of the patients' quality of life. The aim of the study was to test the possibility of predicting postoperative speech disorders in patients with glial brain tumors by using the CCEP data recorded intraoperatively before the stage of tumor resection. Materials and Methods: CCEP data were reported for 26 patients. To predict the deterioration of speech functions in the postoperative period, we used four options for presenting CCEP data and several machine learning models: a random forest of decision trees, logistic regression, and support vector machine method with different types of kernels: linear, radial, and polynomial. Twenty variants of models were trained: each in 300 experiments with resampling. A total of 6000 tests were performed in the study. Results: The prediction quality metrics for each model trained in 300 tests with resampling were averaged to eliminate the influence of "successful" and "unsuccessful" data grouping. The best result with F1-score = 0.638 was obtained by the support vector machine with a polynomial kernel. In most tests, a high sensitivity score was observed, and in the best model, it reached a value of 0.993; the specificity of the best model was 0.370. Conclusion: This pilot study demonstrated the possibility of predicting speech dysfunctions based on CCEP data taken before the main stage of glial tumors resection; the data were processed using traditional machine learning methods. The best model with high sensitivity turned out to be insufficiently specific. Further studies will be aimed at assessing the changes in CCEP during the operation and their relationship with the development of postoperative speech deficit.

[Broca's area intraoperative mapping with cortico-cortical evoked potentials]. / Intraoperatsionnoe kartirovanie rechevoi zony Broka metodom registratsii kortiko-kortikal'nykh vyzvannykh potentsialov.

OBJECTIVE: Mapping of effective speech connections between the frontal and temporal lobes with cortico-cortical evoked potentials. MATERIAL AND METHODS: There were 3 patients with brain tumors in the left frontoparietal region. The neoplasms were localized in the dominant hemisphere near cortical speech centers and pathways. Cortico-cortical evoked potentials were intraoperatively recorded in response to bipolar stimulation with a direct current delivered through the subdural electrodes (single rectangular biphasic impulses with duration of 300 µs and frequency of 1 Hz). Stimulation intensity was gradually increased from 2 mA within 3-4 mA. Registration was carried out by averaging ECoG (30-50 stimuli in each session) in the 300-ms epoch after stimulus. Direct cortical stimulation was used to validate the results of cortico-cortical speech mapping with cortico-cortical evoked potentials. RESULTS: In our cases, we obtained cortico-cortical evoked potentials from inferior frontal gyrus after stimulation of superior temporal gyrus. In one case, this effective relationship was unidirectional, in the other two patients reciprocal. Mean latency of N1 peak was 65 ms (range 49.6-90 ms), mean amplitude 71 µV (range 50-100 µV). Cortico-cortical mapping data were confirmed by detection of Broca's area in 2 out of 3 cases out during direct cortical stimulation with maximum amplitude of N1 wave. «Awake craniotomy¼ protocol was applied. In one case, Broca's area was not detected during direct stimulation. No postoperative speech impairment was noted. CONCLUSION: Initial results of cortical mapping with cortico-cortical evoked potentials in a small sample confirmed its practical significance for analysis of cortical projections of effective speech communications between the frontal and temporal lobes. Further study of this method in large samples is required.

Development of a motor and somatosensory evoked potentials-guided spinal cord Injury model in non-human primates.

Background Nonhuman primates (NHP) may provide the most adequate (in terms of neuroanatomy and neurophysiology) model of spinal cord injury (SCI) for testing regenerative therapies, but bioethical considerations exclude their use in severe SCI. New Method A reproducible model of SCI at the lower thoracic level has been developed in Rhesus macaques. The model comprises surgical resection of 25% of the spinal cord in the projection of the dorsal funiculus and dorsolateral corticospinal pathways, controlled via registration of intraoperative evoked potentials (EPs). The animals were evaluated using the modified Hindlimb score, MRI, SSEP, and MEP over a time period of 8-12 weeks post-SCI, followed by histological examination. Results Complete disappearance of intraoperative EPs from distal hindlimb muscles without restoration within two weeks post-SCI was an indicator for irreversible disruption of the abovementioned pathways. As a result, controlled damage to the spinal cord was achieved in three NHPs, clinically manifested as irreversible lower monoplegia. No significant functional restoration was observed in these NHPs up to 12 weeks post-SCI. Demyelination of the damaged ascending tracts was detected. Disturbances in pelvic organ function were not observed in all animals. Comparison with existing methods The new method of EPs-guided SCI allows a more controlled and irreversible damage to the spinal cord compared with contusion and other transection approaches. Conclusions This method to induce complete SCI in NHP is well tolerated, reproducible and ethically acceptable: these are valuable attributes in a preclinical model that will hopefully help advance testing of new regenerative therapies in SCI.