Power and distribution of evoked gamma oscillations in brain aging and cognitive performance.

AIMS: Gamma oscillations (≈25-100 Hz) are believed to play an essential role in cognition, and aberrant gamma oscillations occur in brain aging and neurodegeneration. This study examined age-related changes in visually evoked gamma oscillations at two different time points 5 years apart and tested the hypothesis that the power of gamma oscillations correlated to cognitive skills. METHODS: The cohort consists of elderly males belonging to the Metropolit 1953 Danish Male Birth Cohort (first visit, N=124; second visit, N=88) over a 5-year period from 63 to 68 years of age. Cognitive functions were assessed using a neuropsychological test battery measuring global cognition, intelligence, memory, and processing speed. The power of steady-state visual evoked potentials (SSVEP) was measured at 8 Hz (alpha) and 36 Hz (gamma) frequencies using EEG scalp electrodes. RESULTS: Over the 5-year period cognitive performance remained relatively stable while the power of visually evoked gamma oscillations shifted from posterior to anterior brain regions with increasing age. A higher-than-average cognitive score was correlated with higher gamma power in parieto-occipital areas and lower in frontocentral areas, i.e., preserved distribution of the evoked activity. CONCLUSIONS: Our data reveal that the distribution of visually evoked gamma activity becomes distributed with age. Preserved posterior-occipital gamma power in participants with a high level of cognitive performance is consistent with a close association between the ability to produce gamma oscillations and cognition. The data may contribute to our understanding of the mechanisms that link evoked gamma activity and cognition in the aging brain.

CARRNN: A Continuous Autoregressive Recurrent Neural Network for Deep Representation Learning From Sporadic Temporal Data.

Learning temporal patterns from multivariate longitudinal data is challenging especially in cases when data is sporadic, as often seen in, e.g., healthcare applications where the data can suffer from irregularity and asynchronicity as the time between consecutive data points can vary across features and samples, hindering the application of existing deep learning models that are constructed for complete, evenly spaced data with fixed sequence lengths. In this article, a novel deep learning-based model is developed for modeling multiple temporal features in sporadic data using an integrated deep learning architecture based on a recurrent neural network (RNN) unit and a continuous-time autoregressive (CAR) model. The proposed model, called CARRNN, uses a generalized discrete-time autoregressive (AR) model that is trainable end-to-end using neural networks modulated by time lags to describe the changes caused by the irregularity and asynchronicity. It is applied to time-series regression and classification tasks for Alzheimer's disease progression modeling, intensive care unit (ICU) mortality rate prediction, human activity recognition, and event-based digit recognition, where the proposed model based on a gated recurrent unit (GRU) in all cases achieves significantly better predictive performance than the state-of-the-art methods using RNNs, GRUs, and long short-term memory (LSTM) networks.

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients.

Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. SARS-CoV-2 positive cases from the United Kingdom Biobank was used for external validation. The ML models predicted the risk of death (Receiver Operation Characteristics-Area Under the Curve, ROC-AUC) of 0.906 at diagnosis, 0.818, at hospital admission and 0.721 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. Common risk factors, included age, body mass index and hypertension, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. We provide access to an online risk calculator based on these findings.