“
“A useful patient admission prediction model that helps the emergency department of a hospital admit patients efficiently is of great importance. It not only improves the care quality PXD101 purchase provided by the emergency department but also reduces waiting time of patients. This paper proposes an automatic prediction method for patient admission based on a fuzzy min-max neural network (FMM) with rules extraction. The FMM neural network forms a set of hyperboxes by learning through data samples, and the learned knowledge is used for prediction. In addition to providing predictions, decision rules are extracted from the FMM hyperboxes to provide an explanation for each prediction. In order to simplify the

structure of FMM and the decision rules, an optimization method that simultaneously maximizes prediction accuracy and minimizes the number of FMM hyperboxes is proposed.

Specifically, a genetic algorithm is formulated to find the optimal configuration of the decision rules. The experimental results using a large data set consisting of 450740 real patient records reveal that the proposed method achieves comparable or even better prediction accuracy than state-of-the-art classifiers with the additional ability to extract a set of explanatory rules to justify its predictions.”
“Nonconvulsive status epilepticus (NCSE) is common in patients with coma with a prevalence between 5% and 48%. Patients in deep coma may exhibit epileptiform EEG patterns, such as generalized periodic spikes, and there is an ongoing debate about the relationship of these patterns and NCSE. The purposes of this review are (i) to discuss the various EEG

patterns found in coma, its fluctuations, selleck chemicals and transitions and (ii) to propose modified criteria for NCSE in coma. Classical coma patterns such as diffuse polymorphic delta activity, spindle coma, alpha theta coma, low output voltage, or burst suppression do not reflect NCSE. Any ictal patterns with a typical spatiotemporal evolution or epileptiform discharges faster than 2.5 Hz in a comatose patient reflect nonconvulsive seizures or NCSE and should be treated. Generalized periodic diacharges or lateralized periodic discharges (GPDs/LPDs) with a frequency of less than 2.5 Hz or rhythmic discharges (RDs) faster than 0.5 Hz are the borderland of NCSE in coma. In these cases, at least one of the additional LGX818 order criteria is needed to diagnose NCSE (a) subtle clinical ictal phenomena, (b) typical spatiotemporal evolution, or (c) response to antiepileptic drug treatment. There is currently no consensus about how long these patterns must be present to qualify for NCSE, and the distinction from nonconvulsive seizures in patients with critical illness or in comatose patients seems arbitrary. The Salzburg Consensus Criteria for NCSE [1] have been modified according to the Standardized Terminology of the American Clinical Neurophysiology Society [21 and validated in three different cohorts, with a sensitivity of 97.2%, a specificity of 95.