Classification of Patients with Alzheimer's Disease and Dementia with Lewy Bodies using Resting EEG Selected Features at Sensor and Source Levels: A Proof-of-Concept Study.

BACKGROUND: Early differentiation between Alzheimer's disease (AD) and Dementia with Lewy Bodies (DLB) is important for accurate prognosis, as DLB patients typically show faster disease progression. Cortical neural networks, necessary for human cognitive function, may be disrupted differently in DLB and AD patients, allowing diagnostic differentiation between AD and DLB. OBJECTIVE: This proof-of-concept study assessed whether the application of machine learning techniques to data derived from resting-state electroencephalographic (rsEEG) rhythms (discriminant sensor power, 19 electrodes) and source connectivity (between five cortical regions of interest) allowed differentiation between DLB and AD. METHODS: Clinical, demographic, and rsEEG datasets from DLB patients (N=30), AD patients (N=30), and control seniors (NOld, N=30), matched for age, sex, and education, were taken from our international database. Individual (delta, theta, alpha) and fixed (beta) rsEEG frequency bands were included. The rsEEG features for the classification task were computed at both sensor and source levels. The source level was based on eLORETA freeware toolboxes for estimating cortical source activity and linear lagged connectivity. Fluctuations of rsEEG recordings (band-pass waveform envelopes of each EEG rhythm) were also computed at both sensor and source levels. After blind feature reduction, rsEEG features served as input to support vector machine (SVM) classifiers. Discrimination of individuals from the three groups was measured with standard performance metrics (accuracy, sensitivity, and specificity). RESULTS: The trained SVM two-class classifiers showed classification accuracies of 97.6% for NOld vs. AD, 99.7% for NOld vs. DLB, and 97.8% for AD vs. DLB. Three-class classifiers (AD vs. DLB vs. NOld) showed classification accuracy of 94.79%. CONCLUSION: These promising preliminary results should encourage future prospective and longitudinal cross-validation studies using higher resolution EEG techniques and harmonized clinical procedures to enable the clinical application of these machine learning techniques.

Forecasting Seizure Freedom After Epilepsy Surgery Assessing Concordance Between Noninvasive and StereoEEG Findings.

BACKGROUND: Accurate localization of the probable Epileptogenic Zone (EZ) from presurgical studies is crucial for achieving good prognosis in epilepsy surgery. OBJECTIVE: To evaluate the degree of concordance at a sublobar localization derived from noninvasive studies (video electroencephalography, EEG; magnetic resonance imaging, MRI; 18-fluorodeoxyglucose positron emission tomography FDG-PET, FDG-PET) and EZ estimated by stereoEEG, in forecasting seizure recurrence in a long-term cohort of patients with focal drug-resistant epilepsy. METHODS: We selected patients with a full presurgical evaluation and with postsurgical outcome at least 1 yr after surgery. Multivariate Cox regression analysis for seizure freedom (Engel Ia) was performed. RESULTS: A total of 74 patients were included, 62.2% were in Engel class Ia with a mean follow-up of 2.8 + 2.4 yr after surgery. In the multivariate analysis for Engel Ia vs >Ib, complete resection of the EZ found in stereoEEG (hazard ratio, HR: 0.24, 95%CI: 0.09-0.63, P = .004) and full concordance between FDG-PET and stereoEEG (HR: 0.11, 95%CI: 0.02-0.65, P = .015) portended a more favorable outcome. Most of our results were maintained when analyzing subgroups of patients. CONCLUSION: The degree of concordance between noninvasive studies and stereoEEG may help to forecast the likelihood of cure before performing resective surgery, particularly using a sublobar classification and comparing the affected areas in the FDG-PET with EZ identified with stereoEEG.