Cost-effectiveness of public health interventions against human influenza pandemics in France: a methodological contribution from the FLURESP European Commission project.

BACKGROUND: The FLURESP project is a public health project funded by the European Commission with the objective to design a methodological approach in order to compare the cost-effectiveness of existing public health measures against human influenza pandemics in four target countries: France, Italy, Poland and Romania. This article presents the results relevant to the French health system using a data set specifically collected for this purpose. METHODS: Eighteen public health interventions against human influenza pandemics were selected. Additionally, two public-health criteria were considered: 'achieving mortality reduction ≥40%' and 'achieving morbidity reduction ≥30%'. Costs and effectiveness data sources include existing reports, publications and expert opinions. Cost distributions were taken into account using a uniform distribution, according to the French health system. RESULTS: Using reduction of mortality as an effectiveness criterion, the most cost-effective options was 'implementation of new equipment of Extracorporeal membrane oxygenation (ECMO) equipment'. Targeting vaccination to health professionals appeared more cost-effective than vaccination programs targeting at risk populations. Concerning antiviral distribution programs, curative programs appeared more cost-effective than preventive programs. Using reduction of morbidity as effectiveness criterion, the most cost-effective option was 'implementation of new equipment ECMO'. Vaccination programs targeting the general population appeared more cost-effective than both vaccination programs of health professionals or at-risk populations. Curative antiviral programs appeared more cost-effective than preventive distribution programs, whatever the pandemic scenario. CONCLUSION: Intervention strategies against human influenza pandemics impose a substantial economic burden, suggesting a need to develop public-health cost-effectiveness assessments across countries.

Time-to-event analysis with artificial neural networks: an integrated analytical and rule-based study for breast cancer.

This paper presents an analysis of censored survival data for breast cancer specific mortality and disease-free survival. There are three stages to the process, namely time-to-event modelling, risk stratification by predicted outcome and model interpretation using rule extraction. Model selection was carried out using the benchmark linear model, Cox regression but risk staging was derived with Cox regression and with Partial Logistic Regression Artificial Neural Networks regularised with Automatic Relevance Determination (PLANN-ARD). This analysis compares the two approaches showing the benefit of using the neural network framework especially for patients at high risk. The neural network model also has results in a smooth model of the hazard without the need for limiting assumptions of proportionality. The model predictions were verified using out-of-sample testing with the mortality model also compared with two other prognostic models called TNG and the NPI rule model. Further verification was carried out by comparing marginal estimates of the predicted and actual cumulative hazards. It was also observed that doctors seem to treat mortality and disease-free models as equivalent, so a further analysis was performed to observe if this was the case. The analysis was extended with automatic rule generation using Orthogonal Search Rule Extraction (OSRE). This methodology translates analytical risk scores into the language of the clinical domain, enabling direct validation of the operation of the Cox or neural network model. This paper extends the existing OSRE methodology to data sets that include continuous-valued variables.

Prediction of persistence of combined evidence-based cardiovascular medications in patients with acute coronary syndrome after hospital discharge using neural networks.

In the PREVENIR-5 study, artificial neural networks (NN) were applied to a large sample of patients with recent first acute coronary syndrome (ACS) to identify determinants of persistence of evidence-based cardiovascular medications (EBCM: antithrombotic + beta-blocker + statin + angiotensin converting enzyme inhibitor-ACEI and/or angiotensin-II receptor blocker-ARB). From October 2006 to April 2007, 1,811 general practitioners recruited 4,850 patients with a mean time of ACS occurrence of 24 months. Patient profile for EBCM persistence was determined using automatic rule generation from NN. The prediction accuracy of NN was compared with that of logistic regression (LR) using Area Under Receiver-Operating Characteristics-AUROC. At hospital discharge, EBCM was prescribed to 2,132 patients (44%). EBCM persistence rate, 24 months after ACS, was 86.7%. EBCM persistence profile combined overweight, hypercholesterolemia, no coronary artery bypass grafting and low educational level (Positive Predictive Value = 0.958). AUROC curves showed better predictive accuracy for NN compared to LR models.

Development of a rule based prognostic tool for HER 2 positive breast cancer patients.

A three stage development process for the production of a hierarchical rule based prognosis tool is described. The application for this tool is specific to breast cancer patients that have a positive expression of the HER 2 gene. The first stage is the development of a Bayesian classification neural network to classify for cancer specific mortality. Secondly, low-order Boolean rules are extracted form this model using an Orthogonal Search based Rule Extraction (OSRE) algorithm. Further to these rules additional information is gathered from the Kaplan-Meier survival estimates of the population, stratified by the categorizations of the input variables. Finally, expert knowledge is used to further simplify the rules and to rank them hierarchically in the form of a decision tree. The resulting decision tree groups all observations into specific categories by clinical profile and by event rate. The practical clinical value of this decision support tool will in future be tested by external validation with additional data from other clinical centres.