Utilizing artificial intelligence and electroencephalography to assess expertise on a simulated neurosurgical task.

Virtual reality surgical simulators have facilitated surgical education by providing a safe training environment. Electroencephalography (EEG) has been employed to assess neuroelectric activity during surgical performance. Machine learning (ML) has been applied to analyze EEG data split into frequency bands. Although EEG is widely used in fields requiring expert performance, it has yet been used to classify surgical expertise. Thus, the goals of this study were to (a) develop an ML model to accurately differentiate skilled and less-skilled performance using EEG data recorded during a simulated surgery, (b) explore the relative importance of each EEG bandwidth to expertise, and (c) analyze differences in EEG band powers between skilled and less-skilled individuals. We hypothesized that EEG recordings during a virtual reality surgery task would accurately predict the expertise level of the participant. Twenty-one participants performed three simulated brain tumor resection procedures on the NeuroVR™ platform (CAE Healthcare, Montreal, Canada) while EEG data was recorded. Participants were divided into 2 groups. The skilled group was composed of five neurosurgeons and five senior neurosurgical residents (PGY4-6), and the less-skilled group was composed of six junior residents (PGY1-3) and five medical students. A total of 13 metrics from EEG frequency bands and ratios (e.g., alpha, theta/beta ratio) were generated. Seven ML model types were trained using EEG activity to differentiate between skilled and less-skilled groups. The artificial neural network achieved the highest testing accuracy of 100% (AUROC = 1.0). Model interpretation via Shapley analysis identified low alpha (8-10 Hz) as the most important metric for classifying expertise. Skilled surgeons displayed higher (p = 0.044) low-alpha than the less-skilled group. Furthermore, skilled surgeons displayed significantly lower TBR (p = 0.048) and significantly higher beta (13-30 Hz, p = 0.049), beta 1 (15-18 Hz, p = 0.014), and beta 2 (19-22 Hz, p = 0.015), thus establishing these metrics as important markers of expertise. ACGME CORE COMPETENCIES: Practice-Based Learning and Improvement.

MR spectroscopic imaging predicts early response to anti-angiogenic therapy in recurrent glioblastoma.

BACKGROUND: Determining failure to anti-angiogenic therapy in recurrent glioblastoma (GBM) (rGBM) remains a challenge. The purpose of the study was to assess treatment response to bevacizumab-based therapy in patients with rGBM using MR spectroscopy (MRS). METHODS: We performed longitudinal MRI/MRS in 33 patients with rGBM to investigate whether changes in N-acetylaspartate (NAA)/Choline (Cho) and Lactate (Lac)/NAA from baseline to subsequent time points after treatment can predict early failures to bevacizumab-based therapies. RESULTS: After stratifying based on 9-month survival, longer-term survivors had increased NAA/Cho and decreased Lac/NAA levels compared to shorter-term survivors. ROC analyses for intratumoral NAA/Cho correlated with survival at 1 day, 2 weeks, 8 weeks, and 16 weeks. Intratumoral Lac/NAA ROC analyses were predictive of survival at all time points tested. At the 8-week time point, 88% of patients with decreased NAA/Cho did not survive 9 months; furthermore, 90% of individuals with an increased Lac/NAA from baseline did not survive at 9 months. No other metabolic ratios tested significantly predicted survival. CONCLUSIONS: Changes in metabolic levels of tumoral NAA/Cho and Lac/NAA can serve as early biomarkers for predicting treatment failure to anti-angiogenic therapy as soon as 1 day after bevacizumab-based therapy. The addition of MRS to conventional MR methods can provide better insight into how anti-angiogenic therapy affects tumor microenvironment and predict patient outcomes.