How to improve opportunistic screening by using EMRs and other data. The prevalence of undetected diabetes mellitus in target population in Croatia.

OBJECTIVES: Opportunistic screening for type 2 diabetes (T2D) has not been adopted as part of routine practice. The aim of the study was to investigate the yield of opportunistic target screening for T2D in Croatia and to evaluate the process of screening by using data from electronic medical record. STUDY DESIGN: We conducted opportunistic screening in 23 general practitioners (GPs) in a population of 13,344 patients aged 45-70 years. METHODS: First, after excluding patients with T2D, patients with risk factors for T2D were derived from the electronic medical record and GP's assessment during the preconsultation phase. Second, those with data about normoglycemia in past three years were excluded. Remaining patients started the consultation phase during their usual visit, when they were offered capillary fasting plasma glucose testing in the next consultation. RESULTS: Prevalence of T2D was 10.9% (new 1.4%). A total of 5568 (46.1%) patients had risks and 2849 (51.2%) had data about normoglycemia in the last three years. Using those data, number needed to invite to screening (NNI) was reduced to half: from 46.1% to 22.5%. One hundred eighty-four patients were screened positive for T2D in two capillary fasting plasma glucose tests (yield 9.8%). Number needed to screen (NNS) in order to detect one T2D was 10.3 patients. Among risks for T2D, overweight was the best predictive factor for undiagnosed T2D (odds ratio [OR]: 2.11, confidence interval [CI]:1.41-3.15, P < .001). Logistic regression showed that in targeted population, overweight patients with a family history in fold were 2.5 times more likely to have T2D (OR: 2.54, CI 1.78-.61, P < .001). CONCLUSIONS: Total yield in targeted population was 1,4%. By using data about normoglycemia from EMRs, NNI was reduced by half and NNS was 10.3 patients. Our findings suggest the model for improvement in opportunistic screening.

[ACCUSTOMING TO HELICOBACTER PYLORI BACTERIUM IN FAMILY PRACTICE].

Today, antibiotic resistance of Helicobacter pylori (HP) is a worldwide problem. The 'test and treat' strategy is the recommended approach in family medicine, as family medicine doctors make decisions on treating gastrointestinal conditions without endoscopic findings or HP testing. In treatment strategy, family medicine doctor has to answer several questions: whether the patient has HP infection, is it necessary to evaluate HP infection, which diagnostic test to use in evaluation of HP infection, should he proscribe antibiotic, and which antibiotic to prescribe. In this article, we present three common clinical cases to determine which approach to use in daily practice: dyspepsia, gastroesophageal reflux disease (GERD), and extragastric diseases associated with HP infection. Serology test, stool antigen test and urea breath test are described. It is required from family medicine doctors not only to rationalize antibiotic prescription but also to eradicate HP infection at the same time. We need to have in mind that disease is a result of the host-agent (bacterium) interaction that varies in time and possible damage/impairment from the disease.

Implementation and deployment of healthcare management information system.

In the following article we present development of the Management Information System, an implementation of our own Data Warehouse, build on top of the existing Healthcare Information System. We discuss requirements and phases of development of the system, we present the structure of the system, the experiences with end users and obstacles that we met, as well as possible improvements end extensions of the system. The system is designed as a framework that works with workload measurement sub-systems, which are defined as multidimensional arrays, and are observed through different units of time. Each of the axis has several hierarchical structures build on top of it. Setting up the system is a difficult task, because it requires a good knowledge of organisational structure of a particular hospital. We used an incremental approach in defining the organisational structure. On top of the framework we build a user customisable graphical user interface, which enables different types of end users to efficiently use the system.

The development and testing of information system for community nursing.

The paper presents the development and testing of information system (IS) for community nursing (CN). The goal of IS is to support CN practice and to encourage research and development in the field. The development was based on analysis of CN process. Principal functions of CN were analysed. The logical data model and corresponding user interface were designed. A special emphasis in the development process was put on testing in practice and users' training. The developed IS will: increase work efficiency, introduce process-oriented nursing doctrine, support integrated treatment of the subjects and enable data comparison and exchange. An important subsidary goal of the IS development and usage is the harmonisation of concepts and terminology used in Slovenia with those used in the EU. In this framework International Classification of Nursing Practice (ICNP) which was translated into Slovene was introduced and tested.

From legacy systems towards modern health information systems.

This article describes an approach of transferring legacy hospital information system to a modern HIS, which would support requirements of modern information age. There are several reasons, which force us to perform such a migration: from the weakness of design of legacy system to the need of covering new technologies (such as Inter/intranet) and new business conditions. The transition should be gradual, therefore a multilevel approach to the data is suggested, enabling us the transition, as well as including of the new, upcoming standards. The process of transition was started by the system covering the doctor's work. Responses to this part were very positive; therefore, we estimate that we are on the right way. We, however, know that the transitions will be neither fast nor cheap and this is the reason we shall have to find some more solutions.

Induction of decision trees and Bayesian classification applied to diagnosis of sport injuries.

Machine learning techniques can be used to extract knowledge from data stored in medical databases. In our application, various machine learning algorithms were used to extract diagnostic knowledge which may be used to support the diagnosis of sport injuries. The applied methods include variants of the Assistant algorithm for top-down induction of decision trees, and variants of the Bayesian classifier. The available dataset was insufficient for reliable diagnosis of all sport injuries considered by the system. Consequently, expert-defined diagnostic rules were added and used as pre-classifiers or as generators of additional training instances for diagnoses for which only few training examples were available. Experimental results show that the classification accuracy and the explanation capability of the naive Bayesian classifier with the fuzzy discretization of numerical attributes were superior to other methods and estimated as the most appropriate for practical use.