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.

Evaluation of the In Situ Ichthyoplankton Imaging System (ISIIS): comparison with the traditional (bongo net) sampler

Plankton and larval fish sampling programs often are limited by a balance between sampling frequency (for precision) and costs. Advancements in sampling techniques hold the potential to add considerable efficiency and, therefore, add sampling frequency to improve precision. We compare a newly developed plankton imaging system, In Situ Ichthyoplankton Imaging System (ISIIS), with a bongo sampler, which is a traditional plankton sampling gear developed in the 1960s. Comparative sampling was conducted along 2 transects ~30–40 km long. Over 2 days, we completed 36 ISIIS tow-yo undulations and 11 bongo oblique tows, each from the surface to within 10 m of the seafloor. Overall, the 2 gears detected comparable numbers of larval fishes, representing similar taxonomic compositions, although larvae captured with the bongo were capable of being identified to lower taxonomic levels, especially larvae in the small (<5 mm), preflexion stages. Size distributions of the sampled larval fishes differed considerably between these 2 sampling methods, with the size range and mean size of larval fishes larger with ISIIS than with the bongo sampler. The high frequency and fine spatial scale of ISIIS allow it to add considerable sampling precision (i.e., more vertical sections) to plankton surveys. Improvements in the ISIIS technology (including greater depth of field and image resolution) should also increase taxonomic resolution and decrease processing time. When coupled with appropriate net sampling (for the purpose of collecting and verifying the identification of biological samples), the use of ISIIS could improve overall survey design and simultaneously provide detailed, process-oriented information for fisheries scientists and oceanographers.

Evaluation of the economic costs and benefits of methods for reducing nutrient loads to the Gulf of Mexico: Topic 6 Report for the Integrated Assessment on Hypoxia in the Gulf of Mexico.

In this report we analyze the Topic 5 report’s recommendations for reducing nitrogen losses to the Gulf of Mexico (Mitsch et al. 1999). We indicate the relative costs and cost-effectiveness of different control measures, and potential benefits within the Mississippi River Basin. For major nonpoint sources, such as agriculture, we examine both national and basin costs and benefits. Based on the Topic 2 economic analysis (Diaz and Solow 1999), the direct measurable dollar benefits to Gulf fisheries of reducing nitrogen loads from the Mississippi River Basin are very limited at best. Although restoring the ecological communities in the Gulf may be significant over the long term, we do not currently have information available to estimate the benefits of such measures to restore the Gulf’s long-term health. For these reasons, we assume that measures to reduce nitrogen losses to the Gulf will ultimately prove beneficial, and we concentrate on analyzing the cost-effectiveness of alternative reduction strategies. We recognize that important public decisions are seldom made on the basis of strict benefit–cost analysis, especially when complete benefits cannot be estimated. We look at different approaches and different levels of these approaches to identify those that are cost-effective and those that have limited undesirable secondary effects, such as reduced exports, which may result in lost market share. We concentrate on the measures highlighted in the Topic 5 report, and also are guided by the source identification information in the Topic 3 report (Goolsby et al. 1999). Nonpoint sources that are responsible for the bulk of the nitrogen receive most of our attention. We consider restrictions on nitrogen fertilizer levels, and restoration of wetlands and riparian buffers for denitrification. We also examine giving more emphasis to nitrogen control in regions contributing a greater share of the nitrogen load.