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.

Development of a nanoporous and multilayer drug-delivery platform for medical implants.

Biodegradable polymers can be applied to a variety of implants for controlled and local drug delivery. The aim of this study is to develop a biodegradable and nanoporous polymeric platform for a wide spectrum of drug-eluting implants with special focus on stent-coating applications. It was synthesized by poly(DL-lactide-co-glycolide) (PLGA 65:35, PLGA 75:25) and polycaprolactone (PCL) in a multilayer configuration by means of a spin-coating technique. The antiplatelet drug dipyridamole was loaded into the surface nanopores of the platform. Surface characterization was made by atomic force microscopy (AFM) and spectroscopic ellipsometry (SE). Platelet adhesion and drug-release kinetic studies were then carried out. The study revealed that the multilayer films are highly nanoporous, whereas the single layers of PLGA are atomically smooth and spherulites are formed in PCL. Their nanoporosity (pore diameter, depth, density, surface roughness) can be tailored by tuning the growth parameters (eg, spinning speed, polymer concentration), essential for drug-delivery performance. The origin of pore formation may be attributed to the phase separation of polymer blends via the spinodal decomposition mechanism. SE studies revealed the structural characteristics, film thickness, and optical properties even of the single layers in the triple-layer construct, providing substantial information for drug loading and complement AFM findings. Platelet adhesion studies showed that the dipyridamole-loaded coatings inhibit platelet aggregation that is a prerequisite for clotting. Finally, the films exhibited sustained release profiles of dipyridamole over 70 days. These results indicate that the current multilayer phase therapeutic approach constitutes an effective drug-delivery platform for drug-eluting implants and especially for cardiovascular stent applications.