Gilchrist, I. D. | Search bioRxiv

bioRxiv2020

Pre-movement changes in sensorimotor beta oscillations predict motor adaptation drive.

Beta frequency oscillations in scalp electroencephalography (EEG) recordings over the primary motor cortex have been associated with the preparation and execution of voluntary movements. Here, we test whether changes in beta frequency are related to the preparation of adapted movements in human, and whether such effects generalise to other species (cat). Eleven healthy adult humans performed a joystick visuomotor adaptation task. Beta (15-25Hz) scalp EEG signals recorded over the motor cortex during a pre-movement preparatory phase were, on average, significantly reduced in amplitude during early adaptation trials compared to baseline or late adaptation trials (p=0.01). The changes in beta were not related to measurements of reaction time or duration of the reach. We also recorded LFP activity within the primary motor cortex of three cats during a prism visuomotor adaptation task. Analysis of these signals revealed similar reductions in motor cortical LFP beta frequencies during early adaptation. This effect was also present when controlling for any influence of the reaction time and reaching duration. Overall, the results are consistent with a reduction in pre-movement beta oscillations predicting an increase in adaptive drive in upcoming task performance when motor errors are largest in magnitude and the rate of adaptation is greatest.

neuroscience↗

bioRxiv2018

A machine learning approach to intensive care discharge.

ObjectiveThe primary objective is to develop an automated method for detecting patients that are ready for discharge from intensive care. DesignWe used two datasets of routinely collected patient data to test and improve upon a set of previously proposed discharge criteria. SettingBristol Royal Infirmary general intensive care unit (GICU). PatientsTwo cohorts derived from historical datasets: 1870 intensive care patients from GICU in Bristol, and 7592 from MIMIC-III (a publicly available intensive care dataset). ResultsIn both cohorts few successfully discharged patients met all of the discharge criteria. Both a random forest and a logistic classifier, trained using multiple-source cross-validation, demonstrated improved performance over the original criteria and generalised well between the cohorts. The classifiers showed good agreement on which features were most predictive of readiness-for-discharge, and these were generally consistent with clinical experience. By weighting the discharge criteria according to feature importance from the logistic model we showed improved performance over the original criteria, while retaining good interpretability. ConclusionsOur findings indicate the feasibility of the proposed approach to ready-for-discharge classification, which could complement other risk models of specific adverse outcomes in a future decision support system. Avenues for improvement to produce a clinically useful tool are identified. Strengths and Limitations of this studyO_LITraining data from multiple source domains is leveraged to produce general classifiers. C_LIO_LIThe restrictive feature representation tested could be expanded to better exploit the richness of available data and boost performance. C_LIO_LIOur approach has the potential to streamline the discharge process in cases where patient C_LIO_LIphysiology makes them clear candidates for a de-escalation of care. C_LIO_LIHigh-risk patients would require additional levels of decision support to facilitate complex discharge planning. C_LI

physiology↗