Jan Paralic

• full professor
• Deputy Head of Department at Technical University of Košice

The focus of this study, and the subject of this article, resides in the conceptually funded usability evaluation of an application of descriptive models to a specific dataset obtained from the East Slovak Institute of Heart and Vascular Diseases targeting cardiovascular patients. Delving into the current state-of-the-art practices, we examine the...

This article deals with the issue of usability of an exploratory data analysis tool in the field of medicine. The text portion contains a description of the methods and the visualization procedure. It analyses the current state on usability, medical data visualization and presents the benefits of visualization tools. The goal of this research was t...

Machine learning (ML) has been used in different ways in the fight against COVID-19 disease. ML models have been developed, e.g., for diagnostic or prognostic purposes and using various modalities of data (e.g., textual, visual, or structured). Due to the many specific aspects of this disease and its evolution over time, there is still not enough u...

Emotions are an integral part of human life. We know many different definitions of emotions. They are most often defined as a complex pattern of reactions, and they could be confused with feelings or moods. They are the way in which individuals cope with matters or situations that they find personally significant. Emotion can also be characterized...

Deep learning methods have proven to be effective for multiple diagnostic tasks in medicine and have been performing significantly better in comparison to other traditional machine learning methods. However, the black-box nature of deep neural networks has restricted their use in real-world applications, especially in healthcare. Therefore, explain...

Deep neural network models have produced significant results in solving various challenging tasks, including medical diagnostics. To increase the credibility of these black-box models in the eyes of doctors, it is necessary to focus on their explainability. Several papers have been published combining deep learning methods with selected types of ex...

Data in many application domains provide a valuable source for analysis and data-driven decision support. On the other hand, legislative restrictions are provided, especially on personal data and patients’ data in the medical domain. In order to maximize the use of data for decision purposes and comply with legislation, sensitive data needs to be p...

Background: High prevalence and mortality of cardiovascular diseases (CVD) are global problems. Many countries focus their healthcare on secondary treatment, and primary prevention is in the background. Focusing on risk factors (RF) screening of CVD in personalized medicine has great potential for the future. We present a methodology for identifica...

This research paper deals with usability aspects that can be examined in clinical decision support systems based on data analytic models. In the analytical part, we first describe the evolution of usability, then we define it according to dominant perspective and according to international standards (ISO 9241- 11). We analyze current state of the a...

This paper discusses the necessity of fake news detection and how selected features can show differences between trustworthy and fake news. To demonstrate this concept, we first identified a set of features, that we believe can distinguish between fake and trustworthy news. We used these features to analyse two real datasets and evaluated our resul...

Today, there are many parameters used for cardiovascular risk quantification and to identify many of the high-risk subjects; however, many of them do not reflect reality. Modern personalized medicine is the key to fast and effective diagnostics and treatment of cardiovascular diseases. One step towards this goal is a better understanding of connect...

(1) Objectives: We aimed to identify clusters of physical frailty and cognitive impairment in a population of older primary care patients and correlate these clusters with their associated comorbidities. (2) Methods: We used a latent class analysis (LCA) as the clustering technique to separate different stages of mild cognitive impairment (MCI) and...

Data streams can be defined as the continuous stream of data in many forms coming from different sources. Data streams are usually non-stationary with continually changing their underlying structure. Solving of predictive or classification tasks on such data must consider this aspect. Traditional machine learning models applied on the drifting data...

While digital space is a place where users communicate increasingly, the recent threat of COVID-19 infection even more emphasised the necessity of effective and well-organised online environment. Therefore, it is nowadays, more whenever in the past, important to deal with various unhealthy phenomena, that prohibit effective communication and knowle...

One of the most fundamental phenomena heavily influencing the digital society is Big Data. It is crucial not only to collect and analyze vast amounts of data but do it in an intelligent way. We believe that in order to do so, there needs to be a suitable interplay between the knowledge already known in the given application domain (background knowl...

The paper presents a new approach to effectively support the adaptation phases in the case-based reasoning (CBR) process. The use of the CBR approach in DSS (Decision Support Systems) can help the doctors better understand existing knowledge and make personalized decisions. CBR simulates human thinking by reusing previous solutions applied to past...

This book aims to provide readers with up-to-date knowledge on how to make these technologies smarter. Humanity is now going through difficult times to fight the Covid-19 pandemic. Simultaneously, in these difficult times of physical separation, we can also realize how much digital society technology helps us cope with many difficulties that bring...

Introduction Currently, just a few major parameters are used for cardiovascular (CV) risk quantification to identify many of the high-risk subjects; however, they leave a lot of them with an underestimated level of CV risk which does not reflect the reality. Material and methods The submitted study design of the Kosice Selective Coronarography Mul...

Background Physical frailty, cognitive impairment, and symptoms of anxiety and depression frequently co-occur in later life, but, to date, each has been assessed separately. The present study assessed their patterns in primary care patients aged ≥60 years. Material/Methods This cross-sectional study evaluated 263 primary care patients aged ≥60 yea...

In this paper we present a decision support system, which has been designed and implemented on the case-based reasoning principles. Our decision support system is being implemented in tight cooperation with the cardiologist, who represents the main future users of the system. Our system enables its user to find the most similar historical cases to...

Objective: Hepatitis E infection is one of the most frequent acute hepatitis in the world. Currently five human genotypes with different geographical distributions and distinct epidemiologic patterns are identified. In Slovakia, only rare cases of hepatitis E have been reported in recent years. Therefore, the aim of the study was to evaluate the p...

Human urine is one of most accessible body fluids and its collection does not burden patients. Wide spectrum of compounds present in urine with a close relation to metabolism determines a large diagnostic potential. Presented work is focused on information extraction from autofluorescent data analysis of urine. Simple modified synchronous autofluor...

Intrusion detection systems (IDS) present a critical component of network infrastructures. Machine learning models are widely used in the IDS to learn the patterns in the network data and to detect the possible attacks in the network traffic. Ensemble models combining a variety of different machine learning models proved to be efficient in this dom...

E-mail marketing is one of the main channels of communication with existing and potential customers. The Open Rate metric is as one of the primary indicators of email campaign success. There are many features of e-mail communication affecting the behavior of individual recipients. Understanding and properly setting these features imply the success...

Príspevok sa zaoberá predikciou nákupného správania zá-kazníkov z pohľadu uplatnenia troch možných kupónov pri budúcich objednávkach prostredníctvom vhodných metód dolovania v dátach. Marketing založený na poskytovaní zľavových kupónov sa využíva hlavne na zvýšenie počtu zákazníkov, zvýšenie zisku, ako aj odmeňo-vanie súčasných zákazníkov. Na rieše...

So stúpajúcou prevalenciou kardiovaskulárnych ochorení je potrebné detailnejšie skúmať vplyv rôznych faktorov, ktoré ich ovplyvňujú. Interdisciplinárnym spojením medicíny a dátovej analýzy sa pokúsime preukázať rôznu silu vplyvu jednotlivých faktorov na stupeň závažnosti kardiovaskulárnych ochorení. Údaje o pacientoch sme získali zo špecializovanéh...

Vďaka svojej závažnosti a stúpajúcej miere úmrtí následkom kardiovaskulárnych ochorení sú tieto stále vo väčšej miere objektom záujmu mnohých výskumníkov. Opakovane sa vykonávajú analýzy na voľne dostupných dátových súboroch, pričom autori týchto výskumov sa snažia o nový príspevok z hľadiska preukázania kauzality vzťahov medzi rôznymi atribútmi ve...

This paper reviews the Case-based reasoning (CBR) approach and its usability in the medicine and presents a new concept on how to improve its adaptation phase. We use the CBR as a supporting method for decision support like diseases diagnostics or therapy identification. We investigated existing approaches, studies, and research works to solve one...

Metabolic syndrome (MS) represents an important risk factor for the development of cardiovascular diseases, as well as type 2 diabetes mellitus, which as one of a few clinical syndromes affects more than 25% of the world population. The diagnosis is often associated with various negative activities like little physical exercise, poor diet, stress,...

The aim of this article is to present how we processed and analysed data from a logistics company using various Business Intelligence tools. The theoretical part of the article is therefore focused on defining Business Intelligence concepts and data warehouses that are relevant to the issue. The practical part of the article focuses on editing data...

Predovšetkým v medicíne je výber správnych atribútov pre klasifikačnú úlohu často veľmi komplikovaný. Význam niektorých atribútov je často ťažko pochopiteľný pre bežných analytikov, ktorí môžu mať problémy určiť ich relevantnosť pre ďalšie analýzy. V tomto článku sme sa zamerali na popis rôznych spôsobov výberu atribútov, napríklad pomocou experta,...

The medical procedures for disease diagnostics are significantly demanding and time-consuming. Data mining methods can accelerate this process and assist doctors in making decisions in complex situations. In case of Parkinson´s disease (PD), the diagnostics of the initial disease stage is the primary issue since the symptoms are not so unambiguous...

Cieľom tohto článku je uľahčiť diagnostiku Parkinsonovej choroby pomocou navrhnutých klasifikačných modelov zahrnutých vo webovej aplikácii. Zamerali sme sa na kognitívne príznaky Parkinsonovej choroby získané z mPower mobilnej aplikácie, ktoré sú prístupné na webovom portáli organizácie Sage Bionetworks. V úvode popisujeme súčasný stav a prehľad o...

Tento článok pojednáva o práci, ktorá sa zaoberá analýzou vybranej dátovej vzorky o Parkinsonovej chorobe. Hlavným cieľom bolo zistiť s akou najvyššou presnosťou je možné určiť z dostupných dát o chôdzi človeka a zo základných demografických údajov, či človek, od ktorého pochádza dátová vzorka, má alebo nemá diagnostikovanú Parkinsonovu chorobu. Pr...

Data analytics represents a new chance for medical diagnosis and treatment to make it more effective and successful. This expectation is not so easy to achieve as it may look like at a first glance. The medical experts, doctors or general practitioners have their own vocabulary, they use specific terms and type of speaking. On the other side, data...

Background: There is potential for medical research on the basis of routine data used from general practice electronic health records (GP eHRs), even in areas where there is no common GP research platform. We present a case study on menopausal women with hypertension and metabolic syndrome (MS). The aims were to explore the appropriateness of the...

Metabolic syndrome represents an important risk factor for the development of cardiovascular diseases, as well as type 2 diabetes mellitus. It affects more than 25% of the world population. This fact motivated many researchers to support effective diagnostics with different analytical methods. They used various data samples, pre-processing approach...

The aim of this paper is to apply predictive data mining (DM) techniques in order to predict the average fuel consumption for trucks and drivers resp., to identify the key factors that affect fuel consumption of vehicles and also to identify best practices and driving styles of drivers. For this purpose different models have been proposed to provid...

Predkladaný článok sa zoberá problematikou spracovania dokumentov špecifického typu, a síce lekárskych správ v slovenskom jazyku a následnou extrakciou hodnôt požadovaných atribútov. Na analýzu súčasného stavu skúmanej problematiky a dostupných možností nadväzuje popis spôsobu tvorby vlastného nástroja. Článok taktiež popisuje experimenty vykonané...

Predkladaný článok sa zameriava na potreby a možnosti štatistického testovania vo fáze pochopenia dát metodológie CRISP-DM. V úvode sa zameriava na možnosti a príležitosť vytvorenia R Shiny aplikácie umožňujúcej základnú štatistickú analýzu. Plynule prechádza na popis vytvorenej aplikácie, pričom čitateľovi približuje v dostatočnej miere jednotlivé...

Predkladaný článok približuje úsilie spojené so spracovaním lekárskych správ a následnú extrakciu údajov do štruktúrovanej podoby, pričom novozískané štruktúrované údaje je neskôr možné použiť na strojové spracovanie. V našom článku sa zameriavame hlavne na prvotnú fázu celého procesu, teda na spracovanie lekárskych záznamov, pričom tieto súvisia s...

Proces diagnózy Parkinsonovej choroby je často veľmi zložitý a musí byť založený na dôkladnom klinickom vyšetrení, ktoré prihliada aj na podrobné údaje o priebehu a charaktere pacientových ťažkostí. Žiadny samostatný symptóm nie je taký jasný, aby lekári mohli vylúčiť iné ochorenie a stanoviť diagnózu Parkinsonovej choroby. Preto sme sa v tomto člá...

Lekársky postup diagnostikovania určitej choroby u pacientov je časovo zdĺhavý a veľmi náročný. Metódy dolovania v dátach môžu tento proces urýchliť a pomôcť tak lekárom pri rozhodovaní v zložitých situáciách. V prípade Parkinsonovej choroby (PCH) je najväčším problémom diagnostika prvotného štádia, pretože symptómy nie sú tak jednoznačné a ľahko p...

Medicínska diagnostika predstavuje komplexný proces pozostávajúci z množstva vstupov a potenciálnych závislostí, ktoré môžu v konečnom dôsledku ovplyvniť správnosť výsledku a následnú liečbu. Dátová analytika a príbuzné domény ako štatistika alebo umelá inteligencia môžu byť v tomto smere nápomocné, ak sú k dispozícii medicínske záznamy v elektroni...

Tento článok sa zaoberá problematikou objavovania znalostí z dát. Popisuje rôzne techniky a metódy, ktoré sa v súčasnosti využívajú v procese dolovania v dátach a problémy, s ktorými sa v tomto procese najčastejšie stretávame. Cieľom našej práce bolo upraviť a následne analyzovať dáta, ktoré pochádzali z výskumu zameraného na diagnostikovanie Parki...

Tento článok popisuje prácu, ktorej cieľom bolo pomocou dolovania v dátach objaviť poznatky o Parkinsonovej chorobe. Pritom sme použili metodiku CRISP-DM. V článku najprv uvedieme základné informácie o Parkinsonovej chorobe ako sú hlavné príznaky, jednotlivé štádia, liečba a pod.. Následne popíšeme princíp objavovania znalostí v databázach, jeho zá...

Ako uvádza World Health Organization (WHO, Svetová zdravotnícka organizácia), počas niekoľkých posledných dekád sú najčastejšou príčinou úmrtí ľudí kardiovaskulárne ochorenia (KVO). Mnoho vedcov sa pokúša analyzovať rôzne medicínske údaje z rôznych lekárskych oblastí, často z kardiológie, s cieľom klasifikovať pacientov (ne)trpiacich KVO alebo pred...

This article in the introduction explains the area of medical data analysis for the purpose of early diagnosis as well as the basic characteristics of Parkinson´s disease. Then it describes the current state and method of collecting the data from people suffering from this disease in order to create classification models. The mPower mobile applicat...

According to World Health Organization, Cardiovascular Diseases (CVD) are the biggest killer of people in a few last decades. Many researchers attempt to analyze data from various medical domains, often from cardiology, to classify patients (not) suffering from CVD or to predict increased risk of formation of acute coronary syndrome. These research...

In determining the symptoms and predicting disease in medicine, health outcomes of patients are used, which are obtained from different clinical tests. Among the initial symptoms of people suffering from Parkinson's disease we can include muscle rigidity, problems with speech (dyspho-nia), movement or writing (dysgraphia). In this article, we focus...

Data Analytics provides various methods and approaches to extract hidden and potentially useful knowledge for different purposes. It means that we can use this knowledge for decision support, e.g. to identify crucial inputs and relations , to predict some future state, to confirm or reject our hypothesis. The medical diagnostics deals with all the...

Parkinson’s disease is the second most frequent neurodegenerative disorder after Alzheimer’s disease. There are numerous symptoms among the population suffering from the disease including tremor, slowed movement, impaired posture and balance, and rigid muscles, however dysphonia – changes in speech and articulation – is the most significant precurs...

This paper presents an application for managing education by creating presence lists. An administration application has also been created in order to allow manipulating with the content of the enumerables in the presence lists. Overviews of possible solutions are presented. Our main motivation was to provide secure and reliable way of evaluating st...

Selection of the right decision strategy is a crucial factor to success in the foreign exchange market. This article presents an innovative approach how to support related decision steps by means of suitable data mining methods applied on collected data from the market. The motivation is a trading under the best conditions, i.e. with the highest ch...

The aim of this article is to describe the design, implementation and evaluation of the educational application to support learning of data mining algorithms. The role of the application is to help students to better understand the algorithms such as Naive Bayes classifier, decision trees and association rules. The application also includes a test...

Pri určovaní symptómov a predikovaní vybraných chorôb v medicíne sa často používajú zdravotné výsledky pacientov, ktoré sú získané z rôznych testov. Pri ľuďoch trpiacich Parkinsonovou chorobou existuje viacero príznakov, avšak typickým symptómom je problém s artikuláciou a rečou (dysfónia). Práve preto sme sa v tomto článku zamerali na klasifikáciu...

Topic modeling becomes a popular research area which shows us new way to search, browse and summarize large amount of texts. Methods of topic modeling try to uncover the hidden thematic structure in document collections. Topic modeling in connection with social networks, which are one of the strongest communication tool and produces large amount of...

In this paper we report on a study of 1541 articles from three different journals (Journal of Informetrics, Information Processing and Management, and Computers and Electrical Engineering) from the period 2007–2014. We analyzed their dates of submission and of final decision to accept and investigated whether the difference between these two dates...

Hidden information and knowledge which are not obvious at the first glance might be discovered from the data saved in the databases using the data mining methods. This knowledge is highly significant and important in the medical field, as it may assist in doctors ‘decision making during the critical situations. This article provides state of the ar...

This article contains description how to create prediction models for more efficient utilization of running IT resources. Prediction model creation is presented as one of the most important steps within the process of the knowledge discovery. Presented models were created based on real data from a local IT company by means of the programming langua...

in this paper we describe the actual state of the big data analysis and related technologies teaching in Business information systems study program at the Technical University Kosice, Slovakia. We have been teaching at the Department of cybernetics and artificial intelligence, various courses specialized on data analysis, machine learning as well a...

In this paper we show that assigning weights to the edges in a collaboration network of authors, according to a decreasing exponential function depending on the time elapsed since the publication of a common paper, may add valuable information to the process of ranking authors based on importance. The main idea is that a recent collaboration repres...

The paper presents the Jbowl, Java software library for data and text analysis, and various research activities performed and implemented on top of the library. The paper describes the various analytical services for text and data mining implemented in Jbowl as well as numerous extensions aimed to address the evolving trends in data and text analys...

This paper presents how to improve the diagnostic process of hepatitis B and C based on collected questionnaires from patients hospitalized in all regional departments of infectology in Slovakia. Performed experiments were oriented in two directions: economic demands of the recommended treatment based on realized diagnostics and possible improvemen...

This paper analyses how information from user profile influences quality of recommendations. We first start with an overview of recommendation systems, their functions methods used. The empirical part focuses on collaborative filtering method with the aim to find improvement of recommendations based on the user profile. The main objective for reali...

Hlavným cieľom tohto príspevku je informovať o bilaterálnom Česko-Slovenskom výskumnom projekte zameranom na analýzu súčasných, ako aj návrh a overenie nových scientometrických ukazovateľov, vychádzajúcich z metód analýzy citačných sietí a metód dolovania znalostí z textov. V rámci metód založených na analýze sietí je pritom hlavná pozornosť venova...

The aim of this chapter is to evaluate a potential of suitable data mining methods for analyses of aviation historical data. In our case, we used public aviation dataset from Federal Aviation Administration (FAA) Accident/Incident Data System containing information about civil aviation accidents or incidents within United States of America. This da...

The work presented in this paper demonstrates how different data mining approaches can be applied to extend conventional combinations of variables determining the Metabolic Syndrome with new influential variables, which are easily available in the everyday physician‘s practice. The results have important consequences: patients with the Metabolic Sy...

The paper deals with the decision of small and medium-sized software companies in transition to SaaS model. The goal of the research is to design a comprehensive methodic to support decision making based on actual data of the company itself. Based on a careful analysis, taxonomy of costs, revenue streams and decision-making criteria are proposed in...

This paper presents an application of data mining on aviation incident data in order to predict the level of incidents' seriousness. Every incident can be seen as a problem that must be avoided or at least minimized its consequences. In aviation industry we can identify several interesting tasks that can be solved by means of data mining methods, e...

This paper firstly describes TCO (Total Cost of Ownership) and ROI (Return On Investments) metrics and proposes their adjustments for measuring envisaged SaaS (Software As A Service) investments of companies. Moreover, we designed and implemented a learning application which helps SMEs to understand measure and compare financial flows and calculati...

Aspect-based sentiment analysis has become popular research field which allows the quantification of textual evaluations of different aspects of products and services. Methods of aspect-based sentiment analysis built on machine learning usually depend on manually annotated training corpora. In order to facilitate the processes of their creation, an...

This paper deals with social network analysis targeted to local structure analysis of company network in order to get view of local structure characteristics and paterns in such kind of network. This paper describes an original aproach, which has ben experimentaly verifed on Slovak company network. We first aimed to prove presence of signifcant loc...

Business bankruptcy is a negative phenomenon, whose symptoms can be identified in advance by means of financial data analyses. The aim of this paper is to present two experimental studies using two different approaches to analyze company’s financial situation based on selected financial indicators. The first approach used data from financial databa...

The paper addresses the concept of Technology Enhanced Learning, which is in focus of the IT4KT project of the Technical University of Kosice. Namely, we present an approach towards the collaborative design and implementation of semantic structures that are capable to support an automation in selected educational processes, especially in mathematic...

Sentiment analysis is currently a popular research area which methods are usually divided into two main types. Both of them, methods based on machine learning as well as dictionary based methods, are dependent on manually annotated corpora. These corpora contain manually annotated documents which are necessary for the training and evaluation of mac...

Sentiment analysis is currently a popular research area which methods are usually divided into two main types. Both of them, methods based on machine learning as well as dictionary based methods, are dependent on manually annotated corpora. These corpora contain manually annotated documents which are necessary for the training and evaluation of mac...

In this paper we present and compare experiences with two different approaches to the utilization of semantic technologies for the adaptive and personalized access to the services. By services we mean generally both web services accessible online and “traditional” services provided by the business or government organizations. We illustrate presente...

This paper describes basic approaches for modeling collaboration social networks. Some of the new extensions are described – new approach for weighting of the ties among event participants; and temporal based method for modeling of network evolution – aging of the ties among actors in passing time. We evaluate proposed methods by two experiments wi...

In this paper we focus on specific approaches to knowledge transformation within the educational domain. Our approaches can be briefly characterized as process-driven, because the core concepts are educational processes and semantic representations of them. In this paper we present two alternative ways of using process models for knowledge transfer...

E-learning represents still dynamically evolving area of research. For one of the sources of its persistent topicality can be considered its close relationship to the development in the fields of web services, semantic web, online collaboration, and many others, that is constantly reflected by e-learning solutions. The view of e-learning solutions,...

This paper deals with social network analysis of specific type of social networks - company networks. Main part is targeted to a new method for projection of company network onto organization to organization network in order to transform direct and indirect connections into one type of connections in the final network. Proposed type of projections...