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.

A method and tool for 'cradle to grave' embodied carbon and energy impacts of UK buildings in compliance with the new TC350 standards

As operational impacts from buildings are reduced, embodied impacts are increasing. However, the latter are seldom calculated in the UK; when they are, they tend to be calculated after the building has been constructed, or are underestimated by considering only the initial materials stage. In 2010, the UK Government recommended that a standard methodology for calculating embodied impacts of buildings be developed for early stage design decisions. This was followed in 2011-12 by the publication of the European TC350 standards defining the 'cradle to grave' impact of buildings and products through a process Life Cycle Analysis. This paper describes a new whole life embodied carbon and energy of buildings (ECEB) tool, designed as a usable empirical-based approach for early stage design decisions for UK buildings. The tool complies where possible with the TC350 standards. Initial results for a simple masonry construction dwelling are given in terms of the percentage contribution of each life cycle stage. The main difficulty in obtaining these results is found to be the lack of data, and the paper suggests that the construction and manufacturing industries now have a responsibility to develop new data in order to support this task. © 2013 The Authors. Published by Elsevier B.V. All rights reserved.