Load-sensitive dynamic workflow re-orchestration and optimisation for faster patient healthcare.

Hospital waiting times are considerably long, with no signs of reducing any-time soon. A number of factors including population growth, the ageing population and a lack of new infrastructure are expected to further exacerbate waiting times in the near future. In this work, we show how healthcare services can be modelled as queueing nodes, together with healthcare service workflows, such that these workflows can be optimised during execution in order to reduce patient waiting times. Services such as X-ray, computer tomography, and magnetic resonance imaging often form queues, thus, by taking into account the waiting times of each service, the workflow can be re-orchestrated and optimised. Experimental results indicate average waiting time reductions are achievable by optimising workflows using dynamic re-orchestration.

ECG biometric using multilayer perceptron and radial basis function neural networks.

This paper proposes a new method to identify people using Electrocardiogram (ECG), particularly the QRS complex which has been proven to be stable against heart rate variability and convenient to be used alone as a biometric feature. 324 QRS complexes are extracted from ECGs of 18 subjects in Physionet's MIT-BIH Normal Sinus Rhythm Database (NSRDB). Multilayer Perceptron (MLP) and Radial Basis Function (RBF) neural networks are used to classify those QRS complexes. If the training data are chosen carefully to cover a wide range of input values (i.e. QRS complexes), then the classification accuracy rates can reach above 98% using MLP and 97% using RBF.

Real-time wearable telecardiology from representative signals.

Electrocardiograms and other similar techniques (e.g. Photoplethysmograph) are very effective tools for the detection of cardiac abnormalities. Automated analyses of ECG signals may be used for this purpose, but due to their complexity--often involving a Neural Network or Principal Component Analysis--the signal needs to be transmitted to be analysed on a powerful device. Thus, even if signals are compressed before being sent, a significant amount of non-critical information is transmitted, unnecessarily consuming bandwidth and resulting in delays. This is problematic as lives may depend on how fast and accurately an ECG signal can be analysed. We present here a fast, simple and accurate technique that works in real time to detect some ECG abnormalities. We base our analysis on correlations of the time sequence with a Representative Signal (RS) to detect abnormal behaviour. We have implemented this scheme on a standard, inexpensive portable device, so abnormalities may be automatically detected immediately on the device itself, without the need for transmission.