Stephens, K. A. | bioRxiv Science

bioRxiv2020

Spontaneous activity changes in large-scale cortical networks in older adults couple to distinct hemodynamic morphology

Neurovascular coupling is a dynamic core mechanism supporting brain energy demand. Therefore, even spontaneous changes in neural activity are expected to evoke a vascular hemodynamic response (HDR). Here, we developed a novel procedure for estimating transient states in intrinsic activity of neural networks based on source-localized electroencephalogram in combination with HDR estimation based on simultaneous rapid-acquisition functional magnetic resonance imaging. We demonstrate a readily apparent spatiotemporal correspondence between electrophysiological and HDR signals, describing for the first time how features of neurovascular coupling may differ among large-scale brain networks. In the default mode network, the HDR pattern in our older adult participants was associated with a surrogate marker of cerebrovascular deterioration and predicted alterations in temporal structure of fast intrinsic electrophysiological activity linked to memory decline. These results show the potential of our technique for making inferences about neural and vascular processes in higher-level cognitive networks in healthy and at-risk populations.

neuroscience↗

bioRxiv2020

Leveraging UMLS-driven NLP to enhance identification of influenza predictors derived from electronic medical record data

ObjectiveMultiple clinical prediction rules have been developed, but lack validation. This study aims to identify a set of prediction algorithms for influenza, based on electronic health record (EHR) structured data and clinical notes derived data using Unified Medical Language System (UMLS) driven natural language processing (NLP). Materials and MethodsData were extracted from an enterprise-wide data warehouse for all patients who tested positive for influenza and were seen in ambulatory care between 2009 and 2019 (N = 7,278). A text processing pipeline was used to analyze chart notes for UMLS terms for symptoms of interest to improve data quality completeness. Three models, which step up complexity of the dataset and predictors, were tested with least absolute shrinkage and selection operator (LASSO)-selected parameters to identify predictors for influenza. Receiver operating characteristic (ROC) curves compared test accuracy across the three models. ResultsThree models identified 7, 8, and 10 predictors, and the most complex model performed best. The addition of the UMLS-driven NLP symptoms data improved data quality (false negatives) and increased the number of significant predictors. NLP also increased the strength of the models, as did the addition of two-way predictor interactions. DiscussionThe EHR is a feasible source for offering rapidly accessible datasets for influenza related prediction research that was used to produce a prediction model for influenza. Combining data collected in routine care with data science methods improved a prediction model for influenza, and in the future, could be used to drive diagnostics at the point of care.

bioinformatics↗