Non-redundant association rules between diseases and medications: an automated method for knowledge base construction.

BACKGROUND: The widespread use of electronic health records (EHRs) has generated massive clinical data storage. Association rules mining is a feasible technique to convert this large amount of data into usable knowledge for clinical decision making, research or billing. We present a data driven method to create a knowledge base linking medications to pathological conditions through their therapeutic indications from elements within the EHRs. METHODS: Association rules were created from the data of patients hospitalised between May 2012 and May 2013 in the department of Cardiology at the University Hospital of Strasbourg. Medications were extracted from the medication list, and the pathological conditions were extracted from the discharge summaries using a natural language processing tool. Association rules were generated along with different interestingness measures: chi square, lift, conviction, dependency, novelty and satisfaction. All medication-disease pairs were compared to the Summary of Product Characteristics, which is the gold standard. A score based on the other interestingness measures was created to filter the best rules, and the indices were calculated for the different interestingness measures. RESULTS: After the evaluation against the gold standard, a list of accurate association rules was successfully retrieved. Dependency represents the best recall (0.76). Our score exhibited higher exactness (0.84) and precision (0.27) than all of the others interestingness measures. Further reductions in noise produced by this method must be performed to improve the classification precision. CONCLUSIONS: Association rules mining using the unstructured elements of the EHR is a feasible technique to identify clinically accurate associations between medications and pathological conditions.

Improving computer security by health smart card.

The University hospitals of Strasbourg have worked for several years on the computer security of the medical data and have of this fact be the first to use the Health Care Professional Smart Card (CPS). This new tool must provide security to the information processing systems and especially to the medical data exchanges between the partners who collaborate to the care of the Beyond the purely data-processing aspects of the functions of safety offered by the CPS, safety depends above all on the practices on the users, their knowledge concerning the legislation, the risks and the stakes, of their adhesion to the procedures and protections installations. The aim of this study is to evaluate this level of knowledge, the practices and the feelings of the users concerning the computer security of the medical data, to check the relevance of the step taken, and if required, to try to improve it. The survey by questionnaires involved 648 users. The practices of users in terms of data security are clearly improved by the implementation of the security server and the use of the CPS system, but security breaches due to bad practices are not however completely eliminated. That confirms that is illusory to believe that data security is first and foremost a technical issue. Technical measures are of course indispensable, but the greatest efforts are required after their implementation and consist in making the key players [2], i.e. users, aware and responsible. However, it must be stressed that the user-friendliness of the security interface has a major effect on the results observed. For instance, it is highly probable that the bad practices continued or introduced upon the implementation of the security server and CPS scheme are due to the complicated nature or functional defects of the proposed solution, which must therefore be improved. Besides, this is only the pilot phase and card holders can be expected to become more responsible as time goes by, along with the gradual national implementation of the CPS project and the introduction of new functions using electronic signatures and encryption.

Nitric oxide donors for patients undergoing IVF. A prospective, double-blind, randomized, placebo-controlled trial.

BACKGROUND: Nitric oxide (NO) is involved in local control of the uterine cycle and in preparation of the uterus for pregnancy. NO donors, acting as vasodilating agents, may therefore have possible therapeutic uses, for example they may be of benefit to patients with a history of implantation failure. In a prospective, comparative, randomized, placebo-controlled study, we assessed the efficacy of nitroglycerin (NTG) administered to 138 IVF patients with a history of implantation failure. METHODS: Controlled ovarian stimulation was performed with long agonist protocol combined with recombinant FSH. Embryos were transferred on day 2 or 3 after oocyte retrieval. Eligible patients were those who had at least two 'good quality' embryos. The NTG patch was administered the day before embryo transfer and continued until either the results of the pregnancy test were known or until menstruation occurred. RESULTS: Ovarian response, implantation rate and pregnancy rate were comparable between both groups. No difference was observed in uterine Doppler findings, particularly the mean pulsatility index. CONCLUSIONS: NTG treatment the day before embryo transfer was no more effective than placebo in improving the implantation or pregnancy rates in a population of IVF patients with a previous history of implantation failures.