AMJ

EEG is a valuable diagnosis tool in the field of epileptic seizure detection. However, determining the discriminative characteristics that represent the inherent behaviours of the EEG signals properly and distinguishing a transient seizure from background activity accurately still remain a great challenge in epilepsy diagnosis. The feasibility and effectiveness of using a novel seizure detection paradigm, which pertains to an improved wavelet neural network model, were highlighted in this study.

Picture by Photo Extremist

Currently there are no studies which have investigated artificial intelligence applications which have been trained in a commercial environment for real-world assessment of Home Medicine Review (HMR) patients. This study gauges the capacity of multiple classification ripple down rules (MCRDR) to detect potential Drug Related Problems(DRPs) using commercial software with real patient data.

Picture by Freedigitalphotos

The results of this study suggest that extracting feature quality information can assist the learning process and improve classification accuracy. On the other hand, relying exclusively on the feature quality information might potentially decrease the classification performance (e.g., using feature reduction). Therefore, authors recommend a hybrid approach that uses feature quality information to direct the learning process by highlighting the more informative features, but at the same time not restricting the learning process to explore other features.

Picture by Easterbilby

The accuracy of existing stroke prediction methods, based on statistical characteristics of certain physiological variables such as blood pressure, glucose, is unsatisfactory due to vague understandings of effects and function domains of those physiological determinants. In this study the authors propose the use of trend patterns of physiological time series data as new key features in predicting 3-month stroke outcomes.

Picture by Schmector

This study reports the evaluation of a clinician-driven rule-based gazetteer method for classifying radiological evidence. The team delineate avenues for the improvement and use of a clinician-driven rule-based classifier in the context of free-text radiology report classifications

Picture by Sebastian Anthony

Managing stochastic activity durations, handling uncertainty in the arrival process of patients, and coordination of multiple activities are key challenges to effective surgery planning and scheduling. Authors propose a two stage prediction based methodology for surgery scheduling to address the above limitations by employing predicted workload and surgery duration, waitlist and perioperative information, and NEST-compliance driven optimisation.

Picture by Kitschweb

This paper evaluates automatic feature extraction for the automatic machine learning classification of documents from a wide range of tumour streams within a single application. The authors identified salient factors in the composition of machine learning systems and demonstrated the achievement of high classification performances, with the potential to improve workflows for the coding of cancer notifiable free-text death certificates.

Picture by Mac Users Guide

The last twelve months have seen Artificial Intelligence (AI) research pushed beyond its boundaries. Google is dabbling in deep learning to build the Google Brain and teach machines to think and learn like humans. Semantic technologies are working harder than ever to take on the challenge of enhancing big data analytics. Translating research from labs to everyday use in hospitals and medical practice still remains one of the greatest challenges for AI in the health research community.

Picture by Trostle

Clarification on “Neonatal sepsis and multiple skin abscess in a newborn with Down's syndrome: A case report”

Picture by Freedigitalphotos

What matters in medicine.

Picture by Freedigitalphotos