Design, construction and evaluation of systems to predict risk in obstetrics.

We present a systematic, practical approach to developing risk prediction systems, suitable for use with large databases of medical information. An important part of this approach is a novel feature selection algorithm which uses the area under the receiver operating characteristic (ROC) curve to measure the expected discriminative power of different sets of predictor variables. We describe this algorithm and use it to select variables to predict risk of a specific adverse pregnancy outcome: failure to progress in labour. Neural network, logistic regression and hierarchical Bayesian risk prediction models are constructed, all of which achieve close to the limit of performance attainable on this prediction task. We show that better prediction performance requires more discriminative clinical information rather than improved modelling techniques. It is also shown that better diagnostic criteria in clinical records would greatly assist the development of systems to predict risk in pregnancy.

Laboratory-scale fluidized bed rig for high-temperature tube wastage studies

As part of a study of the wear of candidate heat exchanger tube materials for use in fluidized bed combustors, two similar laboratory-scale rigs have been built and characterized. Specimens of selected alloys are carried on counter-rotating rotors immersed in a fluidized bed, and are exposed to particle impact velocities of up to approximately 3 ms-1 at temperatures up to 1000°C. The performance of this design of apparatus has been investigated in detail. The effects of several experimental variables have been studied, including angle of particle impact, specimen speed, position of the rotor within the fluidized bed, duration of exposure, bed material particle size, degradation of the bed material, degree of fluidization of the bed, and size of specimen. In many cases the results obtained with steel specimens at elevated temperatures are similar to those observed with polymeric specimens at low temperatures.