Biomedical subjects

P Kokol

Publications and source records attributed to P Kokol.

30 records · Page 2Linked to original sources

PubMed1997

The limitations of decision trees and automatic learning in real world medical decision making.

The decision tree approach is one of the most common approaches in automatic learning and decision making. The automatic learning of decision trees and their use usually show very good results in various "theoretical" environments. But in real life it is often impossible to find the desired number of representative training objects for various reasons. The lack of possibilities to measure attribute values, high cost and complexity of such measurements, and unavailability of all attributes at the same time are the typical representatives. For this reason we decided to use the decision trees not for their primary task--the decision making--but for outlining the most important attributes. This was possible by using a well-known property of the decision trees--their knowledge representation, which can be easily understood by humans. In a delicate field of medical decision making, we cannot allow ourselves to make any inaccurate decisions and the "tips," provided by the decision trees, can be of a great assistance. Our main interest was to discover a predisposition to two forms of acidosis: the metabolic acidosis and respiratory acidosis, which can both have serious effects on child's health. We decided to construct different decision trees from a set of training objects. Instead of using a test set for evaluation of a decision tree, we asked medical experts to take a closer look at the generated trees. They examined and evaluated the decision trees branch by branch. Their comments show that trees generated from the available training set mainly have surprisingly good branches, but on the other hand, for some, no medical explanation could be found.

Acidosis↗

PubMed1996

A tool for software and hardware evaluation.

The proliferation of information technology has enormously eased the burden of computing for medical users. However, it has also created a confusing, difficult problem in evaluation and selection of appropriate software and hardware components. This paper presents an easy to use software tool based on Anderson's Ranking Methodology implemented in Excel 5 that enables one an objective evaluation and selection.

Computers↗

PubMed1995

Metaparadigm: a soft and situation oriented MIS design approach.

Every-day routine work performed by medical staff can be enormous, thus continuing education, diagnostic assistance, medical research or literature searches remains only an aspiration for them. The appearance of the computer-based information technology has initiated the possibility to significantly ease these routine activities and enable the medical staff to devote more time to enhanced creative work. However, only when medical staff can use computers reliably, effectively, democratically, easily, and in natural, intuitive fashion, medical information system (MIS) will be used enthusiastically and favourably. In that manner special attention must be dedicated to MIS design. The aim of our paper is to introduce the new (M)IS design approach called metaparadigm and show its applicability to MIS design. A metaparadigm is a holistic, participative and systemic approach, incorporating design activities needed to construct both the (M)IS design paradigm and the selected (M)IS. It is our deepest belief that metaparadigms employment can enhance many IS design weaknesses and result in the successful medical information systems design and use.

Computer Simulation↗

PubMed1995

METAMET--two leveled medical IS design approach.

New opportunities posed by the huge advancement of information technology, the self-image of medical users, and the so-called patient centered design results in the slogan: It is not enough to do more efficiently what we are doing now, but to confront difficult challenges in new ways. In that manner, we must first be able to design new medical information systems (MIS) using new approaches, and second, these new information systems should conform to very high "quality standards." Recent research shows that the quality of information systems (IS) is strongly related to the quality of the IS design process, and it is clear that both are fundamental issues in successful IS construction and use. In that manner, we invented a new MIS design methodology called METAMET. This paper will introduce this new methodology.

Information Systems↗

PubMed1995

ROSE: decision trees, automatic learning and their applications in cardiac medicine.

Computerized information systems, especially decision support systems, have acquired an increasingly important role in medical applications, particularly in those where important decisions must be made effectively and reliably. But the possibility of using computers in medical decision making is limited by many difficulties, including the complexity of conventional computer languages, methodologies, and tools. Thus a conceptual simple decision making model with the possibility of automating learning should be used. In this paper, we introduce a cardiological knowledge-based system based on the decision tree approach supporting the mitral valve prolapse determination. Prolapse is defined as the displacement of a bodily part from its normal position. The term mitral valve prolapse (PMV), therefore, implies that the mitral leaflets are displaced relative to some structure, generally taken to be the mitral annulus. The implications of the PMV are: disturbed normal laminar blood flow, turbulence of the blood flow, injury of the chordae tendinae, the possibility of thrombus's composition, bacterial endocarditis, and, finally, hemodynamic changes defined as mitral insufficiency and mitral regurgitation. Uncertainty persists about how it should be diagnosed and about its clinical importance. It is our deep belief that the echocardiography enables properly trained expert armed with proper criteria to evaluate PMV almost 100%. But, unfortunately, there are some problems concerned with the use of echocardiography. With this in mind, we have decided to start a research project aimed at finding new criteria and enabling the general practitioner to evaluate the PMV using conventional methods and to select potential patients from the general population. To empower doctors to perform needed activities, we have developed a computer tool called ROSE (computeRized prOlaps Syndrome dEtermination) based on algorithms of automatic learning. This tool supports the definition of new criteria and the selection of potential PMV-patients. The ROSE is based on concepts of decision trees and automatic learning. The decisions and learning process can be presented with an easily visualized two dimensional model; thus decision trees are straightforward to build and interpret. Decision trees use different object attributes to classify different subsets of objects. (Their great advantage is that they don't use a fixed number of predetermined attributes.) In the decision tree approach, the members of a set of objects are classified as either positive or negative instances (in our case patients with PMV Syndrome or without it). Candidate attributes that may possibly describe the concept are then outlined. A decision tree construction tool uses outlined attributes to formulate the appropriate decision tree that identifies all positive instances of the underlying concept according to objects with known classification. (In our case the classification is done with the echo examination). The first set of objects used for the tree generation is usually called the training set. This decision tree characterization next becomes a basis: 1) forecasting whether an object previously unseen is a positive or negative instance of the concept being modeled, and 2) the hierarchical representation of the most important attributes of the concept being investigated. Our main interest and idea is to discover symptoms, syndromes, and illnesses related to PMV that can be distinguished by general practitioners in their everyday job and which should help them to identify possible PMV candidate patients. To this end, we constructed a computerized tool called ROSE. According to the principles presented above, we first taught ROSE using the sample of 400 examined volunteers. ROSE, considering that the clinical PMV diagnosis is practically not researched, is relatively successful. (abstract truncated)

Algorithms↗

PubMed1994

Decision trees based on automatic learning and their use in cardiology.

Computerized information systems, especially decision support systems, have become an increasingly important role in medical applications, particularly in those where important decision must be made effectively and reliably. But the possibility of using computers in medical decision making is limited by many difficulties, including the complexity of conventional computer languages, methodologies and tools. Thus a conceptual simple decision making model with the possibility of automating learning should be used. In this paper we introduce a cardiological knowledge-based system based on the decision tree approach supporting the mitral valve prolapse determination. Prolapse is defined as the displacement of a bodily part from its normal position. The term mitral valve prolaps (PMV), therefore, implies that the mitral leaflets are displaced relative to some structure, generally taken to the mitral annulus. The implications of the PMV are the following: disturbed normal laminar blood flow, turbulence of the blood flow, injury of the chordae tendinae, the possibility of thrombus's composition, bacterial endocarditis, and finally hemodynamic changes defined as mitral insufficiency and mitral regurgitation. Uncertainty persists about how it should be diagnosed and about its clinical importance. It is our deep belief that the echocardiography enables properly trained experts armed with proper criteria to evaluate PMV almost 100%. But unfortunately, there are some problems concerned with the use of echocardiography. In that manner we have decided to start a research project aimed at finding new criteria and enabling the general practitioner to evaluate PMV using conventional methods and to select potential patients from the general population.(ABSTRACT TRUNCATED AT 250 WORDS)

Adolescent↗

PubMed1993

Metaparadigm: a soft systemic MIS design approach.

The aim of this paper is to introduce the soft systemic approach to medical information system design, called metaparadigm. The metaparadigm is a metadesign paradigm. Using it we first design an IS design paradigm and it is our deep belief that metaparadigms employment can enhance many conventional IS design weaknesses and result in successful information system design and use. In the paper we show the applicability of the metaparadigm in MIS design and introduce a new personal MIS design paradigm.

Information Systems↗

PubMed1991

A new microcomputer software system evaluation paradigm: the medical perspective.

The new fourth-generation software has enormously eased the burden of computing for users, but they have also created a confusing, difficult problem in software evaluation and selection. Therefore it is argued that a sound and complete evaluation paradigm is a key element in an efficient and effective software system design and use process. While much has been written about software evaluation in general, in the medical field, the guidances and recommendations previously provided are too general to be of practical use. Considering also the other weaknesses of conventional evaluation paradigms we have decided to develop a more adequate one which will have a solid theoretical framework, specific guidances, strict and well-defined taxonomic space, and a fair ranking approach. In the present paper we will therefore introduce our new evaluation paradigm and show its applicability in evaluation and selection of medical software systems according to their usability.

Classification↗

PubMed1990

Structured spreadsheet modeling in medical decision making and research.

The construction, evaluation, implementation, and use of models representing various algorithms, strategies, methods, theories etc. based on the analysis of great amounts of data are necessary in both Medical Research and Decision Making (MR/DM). Performing such tasks manually is not only time consuming and tedious, but also very error-prone. The appearance of a computer with its ability to store and process information has opened an opportunity to facilitate enormously and improve activities. However, the effective use of computers is limited by difficulties accompanying noncomputer specialists like doctors, nurses, and other medical staff in learning and using conventional programming languages, tools, and techniques. In this paper we present Structured Spreadsheet Modeling as a possible solution, and show that it is applicable in the MR/DM field on a concrete basis.

Adolescent↗

PubMedDate not supplied

Using intelligent search for finding medical sites.

In this paper we present an intelligent search tool, which we developed in order to automate search and evaluation of websites. We used TFIDF heuristics to determine term frequency and decision trees to evaluate the quality of sites. Training set for the decision tree contained manually evaluated websites. Each website was described by the combination of various attributes, complexity metrics and the evaluation. The intelligent search tool is equipped with a user-friendly interface, which enables people to exploit the tool to its limits with minimum effort, in their quest for information. For testing purposes, we looked for sites with telemedical content. The set of sites, which was the result of using the intelligent search tool, has been evaluated by a group of students.

Decision Trees↗

PubMedDate not supplied

Two levelled design of an unified paediatric health care encounter.

The appearance of the new computer-based information technology has initiated the possibility of medical staff performing their everyday routine activities more effectively and efficiently. But to be able to use information technology as successfully as possible, unified and integrated medical encounters are urgently needed especially in the paediatrics field. The tendency to unify the medical encounter is relatively old and had already begun in the 'pre-computer era'. There were some, unpublished, attempts to unify the child's medical encounter during the last years in our country. Unfortunately they were all unsuccessful for various reasons, but it is our deep belief that the common factor for their lack of success was the inappropriateness of the methodology being used and the neglect of many system theory principles especially soft-system ones. It is the objective of this paper to briefly introduce MetaMet and its application in the design of the UNCLE (UNified Child's heaLth carE Encounter). MetaMet is an information system design approach, based on two-levelled design and its aim is to overcome at least some problems concerned with software crisis and to enable more successful design of (medical) information systems.

Adolescent↗

PubMedDate not supplied

[The mitral valve prolapse syndrome in children and adolescents].

The authors studied the prevalence of mitral valve prolapse (MVP) in the group of 656 children and adolescents (329 males and 327 females), who were a representative sample (obtained with the Monte Carlo method of statistical trials) of all newborns in the city of Maribor, Republic of Slovenia, in the period of 18 years (1976-1992). The results were considered positive in children and adolescents who in addition to possible history (chest pain, palpitations, dizziness, loss of consciousness, headaches, perspiration), probable auscultatory finding (mezzosystolic click and late systolic murmur), and suspected phonocardiographic and ECG findings, also had a positive M-mode echocardiographic finding. The criteria for MVP on M-mode echocardiography were taken from the literature: descending of mitral cusp, either anterior or posterior, of at least 3 mm below the line connecting points C and D. Children and adolescents were divided into six age groups (infants, toddlers, preschool children, early school age, children in puberty, adolescents). Assuming MVP as a cause of cardiac arrhythmias, beside standard ECG we also performed holter ECG monitoring in 61 children and adolescents (29 with MVP, 32 without MVP). The results were tested with standard statistical tools (chi 2-test, Student t-test, 2 x 2 Fisher chi 2-test). MVP was found in 71 patients (10.8%, 32 males and 39 females). As regards age and sex we found lower prevalence of MVP in male children (9.7%) compared to female children (11.9%). The highest prevalence was found in early school age, more so in females (14.2 vs 13.7). The differences were not statistically significant (p > 0.05). In both sexes most frequent was endosystolic prolapse (males 59.3%, females 51.3%). Most commonly both cusps are involved in the prolapse (males 78.1%, females 66.7%). Most frequently measured descending of the cusps was 3-4.5 mm (males 56.2%, females 48.7%). Negative auscultatory finding (silent MVP) was detected in 47.8% of the patients with MVP. Most patients with diagnosed MVP had no symptoms (71.8%). The prevalence of asymptomatic MVP declines with age in both sexes. The prevalence of arrhythmias, both in standard ECG and holter ECG, is higher in patients with MVP (6.8:0%--NS and 44.6%:9.3%--p < 0.05). The influence of constitutional changes (dolichostenomelia, asthenic constitution, genua valga) on the appearance of MVP is reflected in statistically significant difference in the Rohr' index in the group of patients with MVP in relation to the healthy group (p < 0.05). The higher prevalence of headache and dizziness in the group with MVP is statistically significant (p < 0.05).

Adolescent↗