Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging.

Specific brain structures (gray matter regions and white matter tracts) play a dominant role in determining cognitive decline and explain the heterogeneity in cognitive aging. Identification of these structures is crucial for screening of older adults at risk of cognitive decline. Using deep learning models augmented with a model-interpretation technique on data from 1432 Mayo Clinic Study of Aging participants, we identified a subset of brain structures that were most predictive of individualized cognitive trajectories and indicative of cognitively resilient vs. vulnerable individuals. Specifically, these structures explained why some participants were resilient to the deleterious effects of elevated brain amyloid and poor vascular health. Of these, medial temporal lobe and fornix, reflective of age and pathology-related degeneration, and corpus callosum, reflective of inter-hemispheric disconnection, accounted for 60% of the heterogeneity explained by the most predictive structures. Our results are valuable for identifying cognitively vulnerable individuals and for developing interventions for cognitive decline.

Quantitative analysis of visually reviewed normal scalp EEG predicts seizure freedom following anterior temporal lobectomy.

OBJECTIVE: Anterior temporal lobectomy (ATL) is a widely performed and successful intervention for drug-resistant temporal lobe epilepsy (TLE). However, up to one third of patients experience seizure recurrence within 1 year after ATL. Despite the extensive literature on presurgical electroencephalography (EEG) and magnetic resonance imaging (MRI) abnormalities to prognosticate seizure freedom following ATL, the value of quantitative analysis of visually reviewed normal interictal EEG in such prognostication remains unclear. In this retrospective multicenter study, we investigate whether machine learning analysis of normal interictal scalp EEG studies can inform the prediction of postoperative seizure freedom outcomes in patients who have undergone ATL. METHODS: We analyzed normal presurgical scalp EEG recordings from 41 Mayo Clinic (MC) and 23 Cleveland Clinic (CC) patients. We used an unbiased automated algorithm to extract eyes closed awake epochs from scalp EEG studies that were free of any epileptiform activity and then extracted spectral EEG features representing (a) spectral power and (b) interhemispheric spectral coherence in frequencies between 1 and 25 Hz across several brain regions. We analyzed the differences between the seizure-free and non-seizure-free patients and employed a Naïve Bayes classifier using multiple spectral features to predict surgery outcomes. We trained the classifier using a leave-one-patient-out cross-validation scheme within the MC data set and then tested using the out-of-sample CC data set. Finally, we compared the predictive performance of normal scalp EEG-derived features against MRI abnormalities. RESULTS: We found that several spectral power and coherence features showed significant differences correlated with surgical outcomes and that they were most pronounced in the 10-25 Hz range. The Naïve Bayes classification based on those features predicted 1-year seizure freedom following ATL with area under the curve (AUC) values of 0.78 and 0.76 for the MC and CC data sets, respectively. Subsequent analyses revealed that (a) interhemispheric spectral coherence features in the 10-25 Hz range provided better predictability than other combinations and (b) normal scalp EEG-derived features provided superior and potentially distinct predictive value when compared with MRI abnormalities (>10% higher F1 score). SIGNIFICANCE: These results support that quantitative analysis of even a normal presurgical scalp EEG may help prognosticate seizure freedom following ATL in patients with drug-resistant TLE. Although the mechanism for this result is not known, the scalp EEG spectral and coherence properties predicting seizure freedom may represent activity arising from the neocortex or the networks responsible for temporal lobe seizure generation within vs outside the margins of an ATL.

Leveraging electrophysiologic correlates of word encoding to map seizure onset zone in focal epilepsy: Task-dependent changes in epileptiform activity, spectral features, and functional connectivity.

OBJECTIVE: Verbal memory dysfunction is common in focal, drug-resistant epilepsy (DRE). Unfortunately, surgical removal of seizure-generating brain tissue can be associated with further memory decline. Therefore, localization of both the circuits generating seizures and those underlying cognitive functions is critical in presurgical evaluations for patients who may be candidates for resective surgery. We used intracranial electroencephalographic (iEEG) recordings during a verbal memory task to investigate word encoding in focal epilepsy. We hypothesized that engagement in a memory task would exaggerate local iEEG feature differences between the seizure onset zone (SOZ) and neighboring tissue as compared to wakeful rest ("nontask"). METHODS: Ten participants undergoing presurgical iEEG evaluation for DRE performed a free recall verbal memory task. We evaluated three iEEG features in SOZ and non-SOZ electrodes during successful word encoding and compared them with nontask recordings: interictal epileptiform spike (IES) rates, power in band (PIB), and relative entropy (REN; a functional connectivity measure). RESULTS: We found a complex pattern of PIB and REN changes in SOZ and non-SOZ electrodes during successful word encoding compared to nontask. Successful word encoding was associated with a reduction in local electrographic functional connectivity (increased REN), which was most exaggerated in temporal lobe SOZ. The IES rates were reduced during task, but only in the non-SOZ electrodes. Compared with nontask, REN features during task yielded marginal improvements in SOZ classification. SIGNIFICANCE: Previous studies have supported REN as a biomarker for epileptic brain. We show that REN differences between SOZ and non-SOZ are enhanced during a verbal memory task. We also show that IESs are reduced during task in non-SOZ, but not in SOZ. These findings support the hypothesis that SOZ and non-SOZ respond differently to task and warrant further exploration into the use of cognitive tasks to identify functioning memory circuits and localize SOZ.

SEEG4D: a tool for 4D visualization of stereoelectroencephalography data.

Epilepsy is a prevalent and serious neurological condition which impacts millions of people worldwide. Stereoelectroencephalography (sEEG) is used in cases of drug resistant epilepsy to aid in surgical resection planning due to its high spatial resolution and ability to visualize seizure onset zones. For accurate localization of the seizure focus, sEEG studies combine pre-implantation magnetic resonance imaging, post-implant computed tomography to visualize electrodes, and temporally recorded sEEG electrophysiological data. Many tools exist to assist in merging multimodal spatial information; however, few allow for an integrated spatiotemporal view of the electrical activity. In the current work, we present SEEG4D, an automated tool to merge spatial and temporal data into a complete, four-dimensional virtual reality (VR) object with temporal electrophysiology that enables the simultaneous viewing of anatomy and seizure activity for seizure localization and presurgical planning. We developed an automated, containerized pipeline to segment tissues and electrode contacts. Contacts are aligned with electrical activity and then animated based on relative power. SEEG4D generates models which can be loaded into VR platforms for viewing and planning with the surgical team. Automated contact segmentation locations are within 1 mm of trained raters and models generated show signal propagation along electrodes. Critically, spatial-temporal information communicated through our models in a VR space have potential to enhance sEEG pre-surgical planning.

Data-driven retrieval of population-level EEG features and their role in neurodegenerative diseases.

Electrophysiologic disturbances due to neurodegenerative disorders such as Alzheimer's disease and Lewy Body disease are detectable by scalp EEG and can serve as a functional measure of disease severity. Traditional quantitative methods of EEG analysis often require an a-priori selection of clinically meaningful EEG features and are susceptible to bias, limiting the clinical utility of routine EEGs in the diagnosis and management of neurodegenerative disorders. We present a data-driven tensor decomposition approach to extract the top 6 spectral and spatial features representing commonly known sources of EEG activity during eyes-closed wakefulness. As part of their neurologic evaluation at Mayo Clinic, 11 001 patients underwent 12 176 routine, standard 10-20 scalp EEG studies. From these raw EEGs, we developed an algorithm based on posterior alpha activity and eye movement to automatically select awake-eyes-closed epochs and estimated average spectral power density (SPD) between 1 and 45 Hz for each channel. We then created a three-dimensional (3D) tensor (record × channel × frequency) and applied a canonical polyadic decomposition to extract the top six factors. We further identified an independent cohort of patients meeting consensus criteria for mild cognitive impairment (30) or dementia (39) due to Alzheimer's disease and dementia with Lewy Bodies (31) and similarly aged cognitively normal controls (36). We evaluated the ability of the six factors in differentiating these subgroups using a Naïve Bayes classification approach and assessed for linear associations between factor loadings and Kokmen short test of mental status scores, fluorodeoxyglucose (FDG) PET uptake ratios and CSF Alzheimer's Disease biomarker measures. Factors represented biologically meaningful brain activities including posterior alpha rhythm, anterior delta/theta rhythms and centroparietal beta, which correlated with patient age and EEG dysrhythmia grade. These factors were also able to distinguish patients from controls with a moderate to high degree of accuracy (Area Under the Curve (AUC) 0.59-0.91) and Alzheimer's disease dementia from dementia with Lewy Bodies (AUC 0.61). Furthermore, relevant EEG features correlated with cognitive test performance, PET metabolism and CSF AB42 measures in the Alzheimer's subgroup. This study demonstrates that data-driven approaches can extract biologically meaningful features from population-level clinical EEGs without artefact rejection or a-priori selection of channels or frequency bands. With continued development, such data-driven methods may improve the clinical utility of EEG in memory care by assisting in early identification of mild cognitive impairment and differentiating between different neurodegenerative causes of cognitive impairment.

Phase-Amplitude Coupling Localizes Pathologic Brain with Aid of Behavioral Staging in Sleep.

Low frequency brain rhythms facilitate communication across large spatial regions in the brain and high frequency rhythms are thought to signify local processing among nearby assemblies. A heavily investigated mode by which these low frequency and high frequency phenomenon interact is phase-amplitude coupling (PAC). This phenomenon has recently shown promise as a novel electrophysiologic biomarker, in a number of neurologic diseases including human epilepsy. In 17 medically refractory epilepsy patients undergoing phase-2 monitoring for the evaluation of surgical resection and in whom temporal depth electrodes were implanted, we investigated the electrophysiologic relationships of PAC in epileptogenic (seizure onset zone or SOZ) and non-epileptogenic tissue (non-SOZ). That this biomarker can differentiate seizure onset zone from non-seizure onset zone has been established with ictal and pre-ictal data, but less so with interictal data. Here we show that this biomarker can differentiate SOZ from non-SOZ interictally and is also a function of interictal epileptiform discharges. We also show a differential level of PAC in slow-wave-sleep relative to NREM1-2 and awake states. Lastly, we show AUROC evaluation of the localization of SOZ is optimal when utilizing beta or alpha phase onto high-gamma or ripple band. The results suggest an elevated PAC may reflect an electrophysiology-based biomarker for abnormal/epileptogenic brain regions.

A Contextual-Bandit-Based Approach for Informed Decision-Making in Clinical Trials.

Clinical trials are conducted to evaluate the efficacy of new treatments. Clinical trials involving multiple treatments utilize the randomization of treatment assignments to enable the evaluation of treatment efficacies in an unbiased manner. Such evaluation is performed in post hoc studies that usually use supervised-learning methods that rely on large amounts of data collected in a randomized fashion. That approach often proves to be suboptimal in that some participants may suffer and even die as a result of having not received the most appropriate treatments during the trial. Reinforcement-learning methods improve the situation by making it possible to learn the treatment efficacies dynamically during the course of the trial, and to adapt treatment assignments accordingly. Recent efforts using multi-arm bandits, a type of reinforcement-learning method, have focused on maximizing clinical outcomes for a population that was assumed to be homogeneous. However, those approaches have failed to account for the variability among participants that is becoming increasingly evident as a result of recent clinical-trial-based studies. We present a contextual-bandit-based online treatment optimization algorithm that, in choosing treatments for new participants in the study, takes into account not only the maximization of the clinical outcomes as well as the patient characteristics. We evaluated our algorithm using a real clinical trial dataset from the International Stroke Trial. We simulated the online setting by sequentially going through the data of each participant admitted to the trial. Two bandits (one for each context) were created, with four choices of treatments. For a new participant in the trial, depending on the context, one of the bandits was selected. Then, we took three different approaches to choose a treatment: (a) a random choice (i.e., the strategy currently used in clinical trial settings), (b) a Thompson sampling-based approach, and (c) a UCB-based approach. Success probabilities of each context were calculated separately by considering the participants with the same context. Those estimated outcomes were used to update the prior distributions within the bandit corresponding to the context of each participant. We repeated that process through the end of the trial and recorded the outcomes and the chosen treatments for each approach. We also evaluated a context-free multi-arm-bandit-based approach, using the same dataset, to showcase the benefits of our approach. In the context-free case, we calculated the success probabilities for the Bernoulli sampler using the whole clinical trial dataset in a context-independent manner. The results of our retrospective analysis indicate that the proposed approach performs significantly better than either a random assignment of treatments (the current gold standard) or a multi-arm-bandit-based approach, providing substantial gains in the percentage of participants who are assigned the most suitable treatments. The contextual-bandit and multi-arm bandit approaches provide 72.63% and 64.34% gains, respectively, compared to a random assignment.

Characterizing the electrophysiological abnormalities in visually reviewed normal EEGs of drug-resistant focal epilepsy patients.

Routine scalp EEG is essential in the clinical diagnosis and management of epilepsy. However, a normal scalp EEG (based on expert visual review) recorded from a patient with epilepsy can cause delays in diagnosis and clinical care delivery. Here, we investigated whether normal EEGs might contain subtle electrophysiological clues of epilepsy. Specifically, we investigated (i) whether there are indicators of abnormal brain electrophysiology in normal EEGs of epilepsy patients, and (ii) whether such abnormalities are modulated by the side of the brain generating seizures in focal epilepsy. We analysed awake scalp EEG recordings of age-matched groups of 144 healthy individuals and 48 individuals with drug-resistant focal epilepsy who had normal scalp EEGs. After preprocessing, using a bipolar montage of eight channels, we extracted the fraction of spectral power in the alpha band (8-13 Hz) relative to a wide band of 0.5-40 Hz within 10-s windows. We analysed the extracted features for (i) the extent to which people with drug-resistant focal epilepsy differed from healthy subjects, and (ii) whether differences within the drug-resistant focal epilepsy patients were related to the hemisphere generating seizures. We then used those differences to classify whether an EEG is likely to have been recorded from a person with drug-resistant focal epilepsy, and if so, the epileptogenic hemisphere. Furthermore, we tested the significance of these differences while controlling for confounders, such as acquisition system, age and medications. We found that the fraction of alpha power is generally reduced (i) in drug-resistant focal epilepsy compared to healthy controls, and (ii) in right-handed drug-resistant focal epilepsy subjects with left hemispheric seizures compared to those with right hemispheric seizures, and that the differences are most prominent in the frontal and temporal regions. The fraction of alpha power yielded area under curve values of 0.83 in distinguishing drug-resistant focal epilepsy from healthy and 0.77 in identifying the epileptic hemisphere in drug-resistant focal epilepsy patients. Furthermore, our results suggest that the differences in alpha power are greater when compared with differences attributable to acquisition system differences, age and medications. Our findings support that EEG-based measures of normal brain function, such as the normalized spectral power of alpha activity, may help identify patients with epilepsy even when an EEG does not contain any epileptiform activity, recorded seizures or other abnormalities. Although alpha abnormalities are unlikely to be disease-specific, we propose that such abnormalities may provide a higher pre-test probability for epilepsy when an individual being screened for epilepsy has a normal EEG on visual assessment.

Electrophysiological Correlates of Brain Health Help Diagnose Epilepsy and Lateralize Seizure Focus.

The absence of epileptiform activity in a scalp electroencephalogram (EEG) recorded from a potential epilepsy patient can cause delays in clinical care delivery. Here we present a machine-learning-based approach to find evidence for epilepsy in scalp EEGs that do not contain any epileptiform activity, according to expert visual review (i.e., "normal" EEGs). We found that deviations in the EEG features representing brain health, such as the alpha rhythm, can indicate the potential for epilepsy and help lateralize seizure focus, even when commonly recognized epileptiform features are absent. Hence, we developed a machine-learning-based approach that utilizes alpha-rhythm-related features to classify 1) whether an EEG was recorded from an epilepsy patient, and 2) if so, the seizure-generating side of the patient's brain. We evaluated our approach using "normal" scalp EEGs of 48 patients with drug-resistant focal epilepsy and 144 healthy individuals, and a naive Bayes classifier achieved area under ROC curve (AUC) values of 0.81 and 0.72 for the two classification tasks, respectively. These findings suggest that our methodology is useful in the absence of interictal epileptiform activity and can enhance the probability of diagnosing epilepsy at the earliest possible time.

Predicting Short-term MCI-to-AD Progression Using Imaging, CSF, Genetic Factors, Cognitive Resilience, and Demographics.

In the Alzheimer's disease (AD) continuum, the prodromal state of mild cognitive impairment (MCI) precedes AD dementia and identifying MCI individuals at risk of progression is important for clinical management. Our goal was to develop generalizable multivariate models that integrate high-dimensional data (multimodal neuroimaging and cerebrospinal fluid biomarkers, genetic factors, and measures of cognitive resilience) for identification of MCI individuals who progress to AD within 3 years. Our main findings were i) we were able to build generalizable models with clinically relevant accuracy (~93%) for identifying MCI individuals who progress to AD within 3 years; ii) markers of AD pathophysiology (amyloid, tau, neuronal injury) accounted for large shares of the variance in predicting progression; iii) our methodology allowed us to discover that expression of CR1 (complement receptor 1), an AD susceptibility gene involved in immune pathways, uniquely added independent predictive value. This work highlights the value of optimized machine learning approaches for analyzing multimodal patient information for making predictive assessments.

Deep-learning for seizure forecasting in canines with epilepsy.

OBJECTIVE: This paper introduces a fully automated, subject-specific deep-learning convolutional neural network (CNN) system for forecasting seizures using ambulatory intracranial EEG (iEEG). The system was tested on a hand-held device (Mayo Epilepsy Assist Device) in a pseudo-prospective mode using iEEG from four canines with naturally occurring epilepsy. APPROACH: The system was trained and tested on 75 seizures collected over 1608 d utilizing a genetic algorithm to optimize forecasting hyper-parameters (prediction horizon (PH), median filter window length, and probability threshold) for each subject-specific seizure forecasting model. The trained CNN models were deployed on a hand-held tablet computer and tested on testing iEEG datasets from four canines. The results from the iEEG testing datasets were compared with Monte Carlo simulations using a Poisson random predictor with equal time in warning to evaluate seizure forecasting performance. MAIN RESULTS: The results show the CNN models forecasted seizures at rates significantly above chance in all four dogs (p  < 0.01, with mean 0.79 sensitivity and 18% time in warning). The deep learning method presented here surpassed the performance of previously reported methods using computationally expensive features with standard machine learning methods like logistic regression and support vector machine classifiers. SIGNIFICANCE: Our findings principally support the feasibility of deploying trained CNN models on a hand-held computational device (Mayo Epilepsy Assist Device) that analyzes streaming iEEG data for real-time seizure forecasting.

Unsupervised machine-learning classification of electrophysiologically active electrodes during human cognitive task performance.

Identification of active electrodes that record task-relevant neurophysiological activity is needed for clinical and industrial applications as well as for investigating brain functions. We developed an unsupervised, fully automated approach to classify active electrodes showing event-related intracranial EEG (iEEG) responses from 115 patients performing a free recall verbal memory task. Our approach employed new interpretable metrics that quantify spectral characteristics of the normalized iEEG signal based on power-in-band and synchrony measures. Unsupervised clustering of the metrics identified distinct sets of active electrodes across different subjects. In the total population of 11,869 electrodes, our method achieved 97% sensitivity and 92.9% specificity with the most efficient metric. We validated our results with anatomical localization revealing significantly greater distribution of active electrodes in brain regions that support verbal memory processing. We propose our machine-learning framework for objective and efficient classification and interpretation of electrophysiological signals of brain activities supporting memory and cognition.

Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy.

OBJECTIVE: An ability to map seizure-generating brain tissue, i.e. the seizure onset zone (SOZ), without recording actual seizures could reduce the duration of invasive EEG monitoring for patients with drug-resistant epilepsy. A widely-adopted practice in the literature is to compare the incidence (events/time) of putative pathological electrophysiological biomarkers associated with epileptic brain tissue with the SOZ determined from spontaneous seizures recorded with intracranial EEG, primarily using a single biomarker. Clinical translation of the previous efforts suffers from their inability to generalize across multiple patients because of (a) the inter-patient variability and (b) the temporal variability in the epileptogenic activity. APPROACH: Here, we report an artificial intelligence-based approach for combining multiple interictal electrophysiological biomarkers and their temporal characteristics as a way of accounting for the above barriers and show that it can reliably identify seizure onset zones in a study cohort of 82 patients who underwent evaluation for drug-resistant epilepsy. MAIN RESULTS: Our investigation provides evidence that utilizing the complementary information provided by multiple electrophysiological biomarkers and their temporal characteristics can significantly improve the localization potential compared to previously published single-biomarker incidence-based approaches, resulting in an average area under ROC curve (AUC) value of 0.73 in a cohort of 82 patients. Our results also suggest that recording durations between 90 min and 2 h are sufficient to localize SOZs with accuracies that may prove clinically relevant. SIGNIFICANCE: The successful validation of our approach on a large cohort of 82 patients warrants future investigation on the feasibility of utilizing intra-operative EEG monitoring and artificial intelligence to localize epileptogenic brain tissue. Broadly, our study demonstrates the use of artificial intelligence coupled with careful feature engineering in augmenting clinical decision making.

Visually validated semi-automatic high-frequency oscillation detection aides the delineation of epileptogenic regions during intra-operative electrocorticography.

OBJECTIVE: To test the utility of a novel semi-automated method for detecting, validating, and quantifying high-frequency oscillations (HFOs): ripples (80-200 Hz) and fast ripples (200-600 Hz) in intra-operative electrocorticography (ECoG) recordings. METHODS: Sixteen adult patients with temporal lobe epilepsy (TLE) had intra-operative ECoG recordings at the time of resection. The computer-annotated ECoG recordings were visually inspected and false positive detections were removed. We retrospectively determined the sensitivity, specificity, positive and negative predictive value (PPV/NPV) of HFO detections in unresected regions for determining post-operative seizure outcome. RESULTS: Visual validation revealed that 2.81% of ripple and 43.68% of fast ripple detections were false positive. Inter-reader agreement for false positive fast ripple on spike classification was good (ICC = 0.713, 95% CI: 0.632-0.779). After removing false positive detections, the PPV of a single fast ripple on spike in an unresected electrode site for post-operative non-seizure free outcome was 85.7 [50-100%]. Including false positive detections reduced the PPV to 64.2 [57.8-69.83%]. CONCLUSIONS: Applying automated HFO methods to intraoperative electrocorticography recordings results in false positive fast ripple detections. True fast ripples on spikes are rare, but predict non-seizure free post-operative outcome if found in an unresected site. SIGNIFICANCE: Semi-automated HFO detection methods are required to accurately identify fast ripple events in intra-operative ECoG recordings.

Seizure Forecasting and the Preictal State in Canine Epilepsy.

The ability to predict seizures may enable patients with epilepsy to better manage their medications and activities, potentially reducing side effects and improving quality of life. Forecasting epileptic seizures remains a challenging problem, but machine learning methods using intracranial electroencephalographic (iEEG) measures have shown promise. A machine-learning-based pipeline was developed to process iEEG recordings and generate seizure warnings. Results support the ability to forecast seizures at rates greater than a Poisson random predictor for all feature sets and machine learning algorithms tested. In addition, subject-specific neurophysiological changes in multiple features are reported preceding lead seizures, providing evidence supporting the existence of a distinct and identifiable preictal state.