Articles catalogue

• Main screen for work, structured by activity types : for patients - in the left and for experts, working in Occupational Health Services (OHSs) - in the right area;
• Passport – professional data screen – constant administrative-passport data and professional characteristics;
• “Health Condition” screen - current health and medical information;
• Information inquire and health indicators;

Keywords: Electronic Patient Record (EPR), Occupational Health Services, Medical Information System (MIS), OHS specialists

 full article

 български

This paper describes, from a practitioner’s point of view, the concepts, methods and tools involved in the design of a practical and potentially low cost distributed information system, with web-based capabilities, for monitoring glaucoma.

Our experience with existing Hospital Information Systems (HISs) found them unsuitable in the very important monitoring process of patients with glaucoma. Actual Electronic Patient Record (EPR) schemes are more to do with management and appointment simple aspects than with clinical and decision-making processes. In a closer relationship to the specific of the affection, we found that demographic patient databases, usually known as Patient Administration Systems (PASs), have not been designed for being shared or concurrently exploited by different programs or even several replicas of the same program.

Many of the early deficiencies in the process of following-up glaucoma patients by dozens of different ophthalmologists in many independent offices from different clinics (with heterogeneous information recording, not very well managed by the existing office capabilities) could only be solved by specifying, designing and implementing a new EPR scheme in a mixed distributed environment, based on a distributed database as a demographic core (or PAS) of patients with glaucoma. A specialized health record management system, with core functionality in monitoring glaucoma, and core data organized as a distributed database system, has been designed in a bottom-up manner to meet the immediate needs. Its pilot implementation was intentionally kept flexible, taking in account developing standards, to accommodate any anticipated future requirements. Among many other benefits, the new EPR allowed medical doctors (ophthalmologists) to view and modify patient information and records in a safe, flexible and efficient manner. Improvements in all the managerial and decisional aspects (regarding costs and time delays) could also be remarked rapidly.

Keywords: medical databases, Electronic Patient Record (EPR), glaucoma management

 full article

 Român

Keywords: Biomedical Informatics, Bioinformatics, Medical Informatics, Neuroinformatics

 full article

 Español

Possibilities of introduction of distance learning in medical curriculum are the title of project which has been realizing at Department of Medical Informatics, Medical Faculty since year 2002. The Project is approved by Federal and Cantonal ministries of science and education. The purpose of this project is to support improvement educational process at biomedical faculties using contemporary methods, methodologies and information technologies in accordance with strategy and objectives given by Bologna declaration. The pilot project is realized during three years, the theoretical and practical parts of the subject Medical Informatics are adapted to modern concepts of education using world trends of distance learning. One group of students from the Medical Faculty was involved in this project, which was finalized by electronic registration of an exam and electronic testing on 20 June 2005, in public in the Physiological amphitheatre of the Medical faculty in Sarajevo. In this article we have given description of the project and phases of its realization, and basic adventages and disadvantages we have noticed so far.

Keywords: distance learning, biomedicine, medical curriculum

 full article

 Na bosanskom

In this paper, a new web solution for administering allergies, asthma and rhinitis in a pan-European level is described. The proposed system was designed to provide: professionals with easy workload and access educational and informational material; sufferers with personalised management tools and educational sources; and citizens with rich informational material. The IREMMA system architecture embeds the existing information networks and data sources on allergy by offering high data integration and multi-modal access to its users, through a multi-service tool and high-distributed architecture. Hence, IREMMA sets the ground for establishing a wide integrated network for environmental monitoring and diffusion of health information. User feedback was collected through extensive pilot trials with real users and the results were used to improve the IREMMA services and the designing and the content specification.

Keywords: telematic services, allergies, environmental monitoring, web applications

 full article

 Greek

Formalization of medical guidelines by means of a general GLIF graphic model is demonstrated in the formalized 2003 European Guidelines on Cardiovascular Disease Prevention and 2003 ESH/ESC Hypertension Guidelines. It leads a user through the decision algorithm in diagnostics of several diseases, total cardiovascular risk estimation and appropriate treatment. Moreover, it can show both the basic information and the appropriate part of guidelines (GL) complete text concerning the selected GLIF model element. The formalization of GL can function as a feedback for authors to remove uncertainties and information inconsistencies in GL. Estimation of the total cardiovascular risk and selection of a drug class is easier compared to a time consuming manipulation with tables of paper guidelines. It offers to physicians a system for a decision support and it checks their decision algorithms in comparison with those of GL. It could serve as a tool for an audit of physicians work by their professional society using the automatic system, preferably with a direct data access from a structured electronic health record in future. Computer GL presentation has the potential for an easier GL knowledge implementation than the classical paper GL form and thus to improve the primary care of cardiovascular diseases.

Keywords: GLIF model, formalization of guidelines, prevention of cardiovascular diseases

 full article

 Česky

Myocardial revascularization belongs among the most frequent cardiosurgery operations. Perioperative and longterm survival depend on the patency of the graft used and the anastomotic quality. Haemodynamical characteristics measured during a coronary artery bypass graft (CABG) surgery help verify anastomotic quality and also affect longterm graft patency. During CABG surgery (on a heart bypass machine with extracorporal circulation), a surgeon measures blood flow through the bypass at the time the cross clamp is applied to the ascending aorta (blood is not flowing through coronary vessels, rather through the bypass) and later at the same place after removal of the cross clamp. The aim of this article is to find a statistical model for prediction of blood flow through the bypass after removal of the cross clamp based on the blood flow value when the cross clamp is placed on the aorta. When this prediction is good, we will be able to decrease a number of measurements with keeping whole information about an object.

Keywords: myocardial revascularization, prediction of blood flow and blood pressure, multiple regression, nonlinear regression model, linearization, linear regression model with constraints, outlier, leverage

 full article

 Česky

Machine learning techniques are methods that given a training set of examples infer a model for the categories of the data, so that new (unknown) examples could be assigned to one or more categories by pattern matching within the model. The data from follow-up studies with repeated collection of the same type of data are very suitable for this analysis. Machine learning algorithms belonging to a variety of paradigms have been applied to knowledge discovery on medical data. All the used algorithms belong to the supervised learning paradigm. Several algorithms have been tested, trying to cover most of the kinds of supervised learning. Two kinds of experiments have been carried out. The first is intended to discover associations between attributes. The second kind is intended to test prediction of future disorders. For the experiments in this paper the data used was from the twenty years lasting primary preventive longitudinal study of the risk factors (RF) of atherosclerosis in middle aged men. Study is named STULONG (LONGitudinal STUdy). The results show that some methods predict some disorders better than others, so it is interesting to use all the algorithms at a time and consider the result confidence based upon the known tendency of each method. The machine learning algorithms have been also used in the prediction of death cause, obtaining poor results in this case, maybe due to the small amount of information (entries) of this type in the dataset.

Keywords: knowledge discovery, supervised machine learning, biomedical data mining, risk factors of atherosclerosis

 full article

 Česky

 Español

Family practice was the first privatized part of the health care system in Croatia. Recently, 84 % of family practices are privatized. Other 16% of them left within health centers. In order to assess current status of use of the information and communication technology (ICT) in family practice, physicians specializing in the family medicine, being also the postgraduate students of the University of Zagreb, School of Medicine in the year 2004/05, have been surveyed. The sample consisted of 159 physicians. Some kind of information system (IS) exists in 62 % of family practices under lease, 42 % within health centers, and 91 % of completely private offices. Having IS in their offices, physicians use it primarily for administration: reporting, prescriptions, sick leaves, referrals and for billing. Usage of ICT in medical work, electronic medical records, was found at about 50 % of physicians. Doing research based on information stored in e-format, is conducting by 31 % of physicians. Based on e-information 35 % of physicians evaluate their work. About using e-sources of medical knowledge (bibliographic data bases, e-journals): 86 % physicians from private offices, 79% physicians working within health centers, 60 % physicians from offices under lease. Satisfaction with current information system is small (19 %). Their information needs are covered partially. 32 % of physicians said they can get enough information by using their information system. 40 % of physicians feel that ICT gave more efficiency to their work, and 25 % of physicians feel their patients are more satisfied since the IS was put into function. Considering different types of practices – young physicians working in health centers are less satisfied with their ISs than the other two groups of physicians coming from private practice. Data security was practiced by using a password, physical protection, and by daily archiving of data .

Keywords: information system, family practice, electronic medical record, Internet, computer security, bibliographic databases, consumer satisfaction

 full article

 Hrvatski

The electrocardiogram (ECG) is one of the most common ways to record, in an non-invasive manner, a patient’s cardiac activity. Once recorded the information can be pre-processed and subsequently analyzed to assess if the patient is suffering from any forms of cardiac abnormality which may require clinical intervention. In the current study we investigate ways in which more can be obtained from the ECG through analysis of the diagnostic properties of body surface potential maps (BSPM). A set of 192 lead BSPMs recorded from a mixture of 116 normal and abnormal subjects (59 normal vs 57 old myocardial infarction) were analyzed. For each patient, diagnostic features were obtained by calculating isointegral measurements from the QRS, STT, and entire QRST segments. These isointegrals provide a measure of the mean distribution of potential during ventricular depolarization, repolarisation, and a combination of both, respectively. For each isointegral type, 192 discrete measurements, and hence 192 features, were obtained; these correspond with the 192 leads recorded. Subsequent to this a signal-to-noise ratio-based feature ranking methodology was applied to select subsets of the best three, six and ten measurements (features) from the 192 available for each isointegral. These subsets of features were then applied to four different classifiers Naïve Bayes (NB), support vector machine (SVM), multi-layer perceptron (MLP) and random forest (RF) and in each application ten-fold cross validation was employed. It was found that when using the subsets of features obtained from the STT or QRST isointegrals, classification results in excess of 80% were attainable. This was in contrast to the results obtained using the QRS isointegral features where poorer performance (between 62.9% and 74.1%) was observed. The results from this study have illustrated that, for the studied dataset, the mean distribution of potentials during ventricular depolarization, and during ventricular repolarization and depolarization combined possessed greater diagnostic information. Overall it was concluded that this approach to BSPM analysis does provide a useful means for illustrating the usefulness of various features in diagnostic classification.

Key words: electrocardiogram, body surface potential map, myocardial infarction, feature selection

 full article

Ranked model in the form of linear transformation of multivariate feature vectors on a line can reflect a causal order between liver diseases. A priori medical knowledge about order between liver diseases and clinical data sets has been used in the definition of the convex and piecewise linear (CPL) criterion function. The linear ranked transformations have been designed here through minimization of such CPL criterion functions.

Keywords: sequential patterns, ranked linear transformations, convex and piecewise linear (CPL) criterion functions, linear separability of data sets, sequence of liver diseases

 full article

 Polski

The article focuses on object oriented technologies and the usage of these technologies, how to create an information system (IS) for applications in medicine, specifically in ophthalmology. The rapid evolution of medical data standards, concepts and technologies has created a problem – how to develop a system that would be flexible enough to work with evolving data. After the analysis of object-oriented technologies: Java 2 Platform, Enterprise Edition (J2EE) and Microsoft .NET and open source object-oriented data base management systems (OODBMS) we have proposed and created a system based on .NET and OODBMS db4o. Results include the developed system with proposed architecture and used techniques, also the advantages of object-oriented data bases (OODB), the systems’ possible interoperability with the National Electronic Health Record system. Developed IS should help medical specialists to reach important information from any computer in any hospital.

Keywords: object-oriented technology, object-oriented data base, information system, data storing standards

 full article

 Lithuanian

This paper deals with design of an automatic detector for classification of selected cardiac arrhythmias. The proposed algorithms employ the continuous wavelet transform (CWT) combined with an analysis of its contour envelopes. The CWT was used in a detector of R-waves, to distinguish between normal and abnormal beats, and for detection of atrial premature contractions (APCs) and premature ventricular contractions (PVCs). The algorithm was validated by extensive testing on the MIT/BIH database. Searching for a local maximum in wavelet contour envelopes efficiently detects R-peaks. The overall accuracy of its detection tested on 48 half-hour signals is 99.5%. Two types of classifications were tested: 1. classification based on the contour envelope and the detection of significant points with overall accuracy 94.6%, 96.1% for the sinus rhythm (SR), 30.4% APCs, 71.2% PVCs and 2. the localization of maximum of square modulus of CWT coefficients in the area of QRS complex for the determination of PVCs between SR, right bundle branch block (RBBB), APC and other narrow complex arrhythmias with the accuracy 96.8%.

Keywords: arrhythmias, ECG signal, wavelet transform, contours

 full article

 Česky

Background: The Czech Republic belongs to countries with high coronary heart disease (CHD) mortality. The aim was to analyze age, period and cohort specific CHD mortality in men from the Czech Republic.

Design and Methods: National data on mortality of men (30-74 yrs.) in the Czech Republic in 1980-2004 were explored. The Poisson regression model was applied to evaluate age, period and cohort effects on mortality.

Results: An adequate fit of CHD men's mortality provided the age-period-cohort model (p=0.121). The ratio of mortality of the age group 45-49 to 40-44 was by 17 % lower than that of the age group 40-44 to 35-39. The ratio of the relative risk of period 1995-1999 to 1990-1994 was by 19 % lower than that of the period 1990-1994 to 1985-1989. The ratios of the relative risks between adjoining birth cohort-groups were close to 1.

Conclusions: The fatal CHD risk in Czech men was significantly depended on age (the risk increasing with age), calendar period (the risk reduced in the recent years), and birth cohort (the risk decreasing with birth cohort). The crucial positive change in the CHD mortality trend was observed after the collapse of communism in 1989, and in men past age 40 years.

Keywords: coronary heart disease, cardiovascular, mortality, risk function

 full article

 Česky

The guideline knowledge representation system (GLIKREM) is based on a GLIF model which was published in a GLIF3.5 specification. GLIKREM contains some changes and extensions of the definition and implementation of the original GLIF model. The aim of this article is to give a description of GLIKREM, its construction, its implementation in XML, a realization of the data interface and use of the result model.

Keywords: knowledge representation, GLIF model, guidelines

 full article

 Česky