Habib Benali

TL;DR: A novel Bayesian strategy to deal with structure learning is proposed, which converts the problem of model selection into that of parameter estimation, and uses non-informative priors and asymptotic results to yield a posterior probability for independence graph supports in closed form.

TL;DR: This work adapted a method classically used in speech and speaker recognition, based on MelFrequency Cepstral Coefficient extraction and Gaussian Mixture Model to detect recently diagnosed and pharmacologically treated PD patients, and classified early PD subjects from controls with an accuracy of 83%, using recordings obtained with a professional microphone.

TL;DR: This paper develops a threefold extension to previous works on the estimation of the blood oxygen level-dependent response to a stimulus, as measured in functional magnetic resonance imaging (fMRI) data, considering asynchronous event-related paradigms account for different trial types and integrate several fMRI sessions into the estimation.

TL;DR: VAP occurs less often than previously described in patients after TBI and has a detrimental effect on ICU LOS, but not on mortality and neurological outcome, and is not associated with increased mortality or worse neurological outcome.