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. 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.

Parents’ perception of their children’s participation in physical activity

This paper describes parents' survey and interview responses about their children's participation in physical activity which were collected for the second part of a three phase project funded by the Commonwealth Department of Health and Family Services: Health Advancement Project through the auspices of ACHPER. In the first phase of the project, an extensive data base was compiled on children's participation in physical activity; the second phase investigated parents' and teachers' perceptions of their children's and students' participation in physical activity. The third phase, which is now underway, will use the first two phases to develop a set of resources with which to advocate for policy, programs and educational strategies to serve the needs of young people in Australia most effectively in relation to physical activity.

Raman spectroscopy of pyrite in marble from Chillagoe, Queensland

Samples of marble from Chillagoe, North Queensland have been analysed using scanning electron microscopy (SEM) with energy dispersive X-ray spectroscopy (EDS) and Raman spectroscopy. Different types of marble were studied including soft white marble, hard white marble and a black marble. In this work, we try to ascertain why the black marble has this colour. Chemical analyses provide evidence for the presence of minerals other calcite in the marble, including the pyrite mineral. Some of these chemical analyses correspond to pyrite minerals in the black marble. The Raman spectra of these crystals were obtained and the Raman spectrum corresponds to that of pyrite from the RRUFF data base. The combination of SEM with EDS and Raman spectroscopy enables the characterisation of the mineral pyrite in Chillagoe black marble.