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.

An evaluation of the neocognitron

We describe a sequence of experiments investigating the strengths and limitations of Fukushima's neocognitron as a handwritten digit classifier. Using the results of these experiments as a foundation, we propose and evaluate improvements to Fukushima's original network in an effort to obtain higher recognition performance. The neocognitron's performance is shown to be strongly dependent on the choice of selectivity parameters and we present two methods to adjust these variables. Performance of the network under the more effective of the two new selectivity adjustment techniques suggests that the network fails to exploit the features that distinguish different classes of input data. To avoid this shortcoming, the network's final layer cells were replaced by a nonlinear classifier (a multilayer perceptron) to create a hybrid architecture. Tests of Fukushima's original system and the novel systems proposed in this paper suggest that it may be difficult for the neocognitron to achieve the performance of existing digit classifiers due to its reliance upon the supervisor's choice of selectivity parameters and training data. These findings pertain to Fukushima's implementation of the system and should not be seen as diminishing the practical significance of the concept of hierarchical feature extraction embodied in the neocognitron. © 1997 IEEE.

A critical evaluation of written discharge advice for people with mild traumatic brain injury : what should we be looking for?

Objective: To formally evaluate the written discharge advice for people with mild traumatic brain injury (mTBI). Methods: Eleven publications met the inclusion criteria: (1) intended for adults; (2) ≤two A4 pages; (3) published in English; (4) freely accessible; and (5) currently used (or suitable for use) in Australian hospital emergency departments or similar settings. Two independent raters evaluated the content and style of each publication against established standards. The readability of the publication, the diagnostic term(s) contained in it and a modified Patient Literature Usefulness Index (mPLUI) were also evaluated. Results: The mean content score was 19.18 ± 8.53 (maximum = 31) and the mean style score was 6.8 ± 1.34 (maximum = 8). The mean Flesch-Kincaid reading ease score was 66.42 ± 4.3. The mean mPLUI score was 65.86 ± 14.97 (maximum = 100). Higher scores on these metrics indicate more desirable properties. Over 80% of the publications used mixed diagnostic terminology. One publication scored optimally on two of the four metrics and highly on the others. Discussion: The content, style, readability and usefulness of written mTBI discharge advice was highly variable. The provision of written information to patients with mTBI is advised, but this variability in materials highlights the need for evaluation before distribution. Areas are identified to guide the improvement of written mTBI discharge advice.

Learnings, case studies and guidelines for establishing shared and collaborative service delivery in the non-government sector: Evaluation of the Multi-Tenant Service Centre (MTSC) Pilots Project

This report presents learnings, case studies, guidelines and resources for non-government organisations that are planning to implement shared or collaborative arrangements with other agencies. It summarises results from an evaluation of the implementation phase of the Multi-Tenant Service Centre (MTSC) Pilots Project, which was completed in June 2008. This evaluation shows that developing and implementing shared and collaborative arrangements is a complex process that presents many risks, challenges and barriers to success, but can have many potential benefits for non government organisations. As this report makes clear, there is no ‘one size fits all’ approach to this process. The MTSC Pilots Project was conducted by the Department of Communities (DoC), Queensland Government, as part of its Strengthening Non-Government Organisations strategy. The objective of the MTSC Pilots initiative was to co-locate separate service providers in an appropriately located centre, operating with effective and transparent management, which enabled service providers to improve client services. Three MTSC consortiums in Mackay, Caboolture and Toowoomba were selected as the pilots over a four year period from 2006 – 2010.

Evaluation of channel congestion in dedicated short-range communication networks

This thesis presents a novel idea for an adaptive prioritized cross-layer design (APCLD) control algorithm to achieve comprehensive channel congestion control for vehicular safety communication based on DSRC technology. An appropriate evaluation metric and two control parameters have been established. Simulation studies have evaluated the DSRC network performance in different traffic scenario and under different channel conditions. The APCLD algorithm is derived from the results of the simulation analysis.

Making stories matter: Using participatory new media storytelling and evaluation to serve marginalised and regional communities

In this chapter, we draw on our experiences facilitating community storytelling workshops in regional Queensland in partnership with the Queensland branch of Oral History Association of Australia (OHAA Qld) in order to develop a best practice model for promoting creative approaches to recording oral narratives using digital tools, informed by creative writing practice and embedded evaluation (Klaebe 2012 & 2013). These experiences offer an insight into how creative approaches to training can facilitate the sharing and preservation of stories in regional communities.