Dimitar Hristovski | University of Ljubljana (original) (raw)

Papers by Dimitar Hristovski

The Eighth International Conference on Advances in Databases, Knowledge, and Data Applications (D... more The Eighth International Conference on Advances in Databases, Knowledge, and Data Applications (DBKDA 2016), held between June 26 - 30, 2016 - Lisbon, Portugal, continued a series of international events covering a large spectrum of topics related to advances in fundamentals on databases, evolution of relation between databases and other domains, data base technologies and content processing, as well as specifics in applications domains databases. Advances in different technologies and domains related to databases triggered substantial improvements for content processing, information indexing, and data, process and knowledge mining. The push came from Web services, artificial intelligence, and agent technologies, as well as from the generalization of the XML adoption. High-speed communications and computations, large storage capacities, and load-balancing for distributed databases access allow new approaches for content processing with incomplete patterns, advanced ranking algorithm...

Scientometrics, 2021

Literature-based discovery (LBD) aims to discover valuable latent relationships between disparate... more Literature-based discovery (LBD) aims to discover valuable latent relationships between disparate sets of literatures. LBD research has undergone an evolution from being an emerging area to a mature research field. Hence it is timely and necessary to summarize the LBD literature and scrutinize general bibliographic characteristics, current and future publication trends, and its intellectual structure. This paper presents the first inclusive scientometric overview of LBD research. We utilize a comprehensive scientometric approach incorporating CiteSpace to systematically analyze the literature on LBD from the last four decades (1986-2020). After manual cleaning, we have retrieved a total of 409 documents from six bibliographic databases (Web of Science, Scopus, PubMed, IEEE Xplore, ACM Digital Library, and Springer Link) and two preprint servers (ArXiv and BiorXiv). The results have shown that Thomas C. Rindflesch published the highest number of LBD papers, followed by Don R. Swanson. The United States plays a leading role in LBD research with the University of Chicago as the dominant institution. To go deeper, we also perform science mapping including cascading citation expansion. The knowledge base of LBD research has changed significantly since its inception, with emerging topics including deep learning and explainable artificial intelligence. The results have indicated that LBD is still growing and evolving. Drawing on our insights, we now better understand the historical progress of LBD in the

a series of international events covering a large spectrum of topics related to advances in funda... more a series of international events covering a large spectrum of topics related to advances in fundamentals on databases, evolution of relation between databases and other domains, data base technologies and content processing, as well as specifics in applications domains databases. Advances in different technologies and domains related to databases triggered substantial improvements for content processing, information indexing, and data, process and knowledge mining. The push came from Web services, artificial intelligence, and agent technologies, as well as from the generalization of the XML adoption. High-speed communications and computations, large storage capacities, and load-balancing for distributed databases access allow new approaches for content processing with incomplete patterns, advanced ranking algorithms and advanced indexing methods. Evolution on e-business, ehealth and telemedicine, bioinformatics, finance and marketing, geographical positioning systems put pressure on...

Izvleček. Razdvoumljanje simbolov genov je raziskovalno zelo aktualno področje. Največji problem ... more Izvleček. Razdvoumljanje simbolov genov je raziskovalno zelo aktualno področje. Največji problem predstavlja ločevanje med besednimi simboli, ki označujejo gene oz. njihove produkte ter simboli, ki se nanašajo na ostale biomedicinske koncepte (npr. CT, MR). V članku predstavimo hiter in preprost pristop k razdvoumljanju, ki temelji na razvrščanju MEDLINE® zapisov v genetsko in negenetsko domeno, ob predpostavki, da se simboli v genetski domeni najverjetneje nanašajo na gene. Algoritem sloni na statistični primerjavi domensko reprezentativnih korpusov zgrajenih na osnovi MeSH® deskriptorjev. Metoda je jasno razumljiva, preprosta za implementacijo ter računsko nezahtevna. Točnost razvrstitve, merjena na validacijski množici podatkov, je znašala 0,91. Algoritem je implementiran kot pomožni sistem za razdvoumljanje simbolov genov v sistemu za odkrivanje dejanskih ali potencialnih zakonitosti iz bibliografskih podatkov BITOLA.

Journal of Biomedical Informatics, 2021

Objective. To discover candidate drugs to repurpose for COVID-19 using literature-derived knowled... more Objective. To discover candidate drugs to repurpose for COVID-19 using literature-derived knowledge and knowledge graph completion methods. Methods. We propose a novel, integrative, and neural network-based literaturebased discovery (LBD) approach to identify drug candidates from PubMed and other COVID-19-focused research literature. Our approach relies on semantic triples extracted using SemRep (via SemMedDB). We identified an informative and accurate subset of semantic triples using filtering rules and an accuracy classifier developed on a BERT variant. We used this subset to construct a knowledge graph, and applied five state-of-the-art, neural knowledge graph completion algorithms (TransE, RotatE, DistMult, ComplEx, and STELP) to predict drug repurposing candidates. The models were trained and assessed using a time slicing approach and the predicted drugs were compared with a list of drugs reported in the literature and evaluated in clinical trials. These models were complemented by a discovery pattern-based approach. Results. Accuracy classifier based on PubMedBERT achieved the best performance (F 1 = 0.854) in classifying semantic predications. Among five knowledge graph completion models, TransE outperformed others (MR = 0.923, Hits@1 = 0.417). Some known drugs linked to COVID-19 in the literature were identified, as well as others that have not yet been studied. Discovery patterns enabled identification of additional candidate drugs and generation of plausible hypotheses regarding the links between the candidate drugs and COVID-19. Among them, five highly ranked and novel drugs (paclitaxel, SB 203580, alpha 2-antiplasmin, metoclopramide, and oxymatrine) and the mechanistic explanations for their potential use are further discussed.

Journal of Biomedical Informatics, 2018

Scientific knowledge constitutes a complex system that has recently been the topic of in-depth an... more Scientific knowledge constitutes a complex system that has recently been the topic of in-depth analysis. Empirical evidence reveals that little is known about the dynamic aspects of human knowledge. Precise dissection of the expansion of scientific knowledge could help us to better understand the evolutionary dynamics of science. In this paper, we analyzed the dynamic properties and growth principles of the MEDLINE bibliographic database using network analysis methodology. The basic assumption of this work is that the scientific evolution of the life sciences can be represented as a list of co-occurrences of MeSH descriptors that are linked to MEDLINE citations. The MEDLINE database was summarized as a complex system, consisting of nodes and edges, where the nodes refer to knowledge concepts and the edges symbolize corresponding relations. We performed an extensive statistical evaluation based on more than 25 million citations in the MEDLINE database, from 1966 until 2014. We based our analysis on node and community level in order to track temporal evolution in the network. The degree distribution of the network follows a stretched exponential distribution which prevents the creation of large hubs. Results showed

Journal of medical systems, 2017

Although telegenetics as a telehealth tool for online genetic counseling was primarily initiated ... more Although telegenetics as a telehealth tool for online genetic counseling was primarily initiated to improve access to genetics care in remote areas, the increasing demand for genetic services with personalized genomic medicine, shortage of clinical geneticists, and the expertise of established genetic centers make telegenetics an attractive alternative to traditional in-person genetic counseling. We review the scope of current telegenetics practice, user experience of patients and clinicians, quality of care in comparison to traditional counseling, and the advantages and disadvantages of information and communication technology in telegenetics. We found that live videoconference consultations are generally well accepted by both clients and clinicians, and these have been successfully used in several genetic counseling settings in practice. Future use of telegenetics could increase patients' access to specialized care and help in meeting the increasing demand for genetic services.

This paper describes the telegenetics component of the SIGN project. Telegenetics is a subfield o... more This paper describes the telegenetics component of the SIGN project. Telegenetics is a subfield of telemedicine applied to clinical genetics. In the SIGN project, telegenetics aims to provide remote genetic services in the cross-border region of Italy and Slovenia. More specifically, the goal is to develop remote genetic services in areas without them and to provide best expertise in clinical genetics without the need to travel large distances (patients or professionals). The major telegenetics activities within the SIGN project are the development of remote genetic services: for genetic counseling, for expert to expert communication, and for communication between the partners of the project. To accomplish the activities, these major tasks had to be done: testing and selection of video-conferencing equipment and software for secure data sharing and exchange; development of work protocols; end-user education; installation, configuration and testing of necessary hardware, software and developed protocols; and evaluation of user satisfaction (both patients and genetic service providers). The preliminary evaluation results show promising user-satisfaction. They also highlight areas where further improvement of the remote services is possible.

Libraries without Limits: Changing Needs — Changing Roles, 1999

Advances in information technology offer many opportunities for improving the access to local res... more Advances in information technology offer many opportunities for improving the access to local resources as well as delivery of information from external resources. The common goal of all medical libraries is to provide access as efficiently as possible to the information resources needed in the work of their users. It can be approached by creating library web sites by offering users better access to information and services.1 The Central Medical Library (CMK) of the Faculty of Medicine in Ljubljana, Slovenia challenged by growth of information resources in medicine and increasing users’ computer literacy decided to built its own web site with embedded search engine.

The article describes the state and some trends in the development of medical informatics especia... more The article describes the state and some trends in the development of medical informatics especially regarding the fields of scientific information, knowledge discovery in databases, and the role of standards in data exchange. The ways of publication of scientific documents experienced dramatic changes with the development of the www, hence causing major changes in daily information practice. Contemporary textual databases contain full documents of hypertextual and multimedia nature and links to full documents are increasingly common within the records of bibliographic databases. The last decade brought the advent of the web information tools, from web portals to global search engines, which are powerful aids but demand strong precaution regarding the quality of retrieved documents from the users. On the other hand, we are witnessing the development of digital libraries of scientific documents as a result of the self-organization of academic institutions, research groups and individuals, often in the opposition to the interests of publishing companies. The information support as an important element of medical procedures made possible the exchange of data between all segments of the health-care system and it has become clear that lack of standards governing structure, understanding and safety is among the biggest obstacles to successful data exchange. In addition, the article comprises a report on the methods of knowledge discovery in databases, which help us discover hidden structures and potential knowledge, invisible to the normal data-processing software, in the enormous amount of data.

The article describes the state and some trends in the development of medical informatics especia... more The article describes the state and some trends in the development of medical informatics especially regarding the fields of scientific information, knowledge discovery in databases, and the role of standards in data exchange. The ways of publication of scientific documents experienced dramatic changes with the development of the www, hence causing major changes in daily information practice. Contemporary textual databases contain full documents ofhypertextual and multimedia nature and links to full documents are increasingly common within the records of bibliographic databases. The last decade brought the advent of the web information tools, from web portals to global search engines, which are powerful aids but demand strong precaution regarding the quality of retrieved documents from the users. On the other hand, we are witnessing the development of digital libraries of scientific documents as a result of the self-organization of academic institutions, research groups and individuals, often in the opposition to the interests of publishing companies. The information support as an important element of medical procedures made possible the exchange of data between all segments of the health-care system and it has become clear that lack of standards governing structure, understanding and safety is among the biggest obstacles to successful data exchange. In addition, the article comprises a report on the methods of knowledge discovery in databases, which help us discover hiddenstructures and potential knowledge, invisible to the normal data processing software, in the enormous amount of data.

Literature-based discovery (LBD) combines known facts in the scientific literature to generate di... more Literature-based discovery (LBD) combines known facts in the scientific literature to generate discoveries, or hypotheses. Potential discoveries have the form of relations between concepts; for example, in the biomedical domain (on which we concentrate), a drug may be determined to treat a disease other than the one for which it was intended. We view the domain knowledge underpinning LBD as a network consisting of a set of concepts along with the relations connecting them. In the study presented here, we used SemMedDB, a database of semantic relations between biomedical concepts extracted with SemRep from MEDLINE. SemMedDB is distributed as a MySQL relational database, which is not optimal for dealing with network data. We transformed and uploaded SemMedDB into a Neo4j graph database, and implemented the basic LBD discovery algorithms with the Cypher query language. We conclude that storing the data needed for semantic LBD is facilitated by a graph database. Also, implementing LBD d...

AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, 2011

We present an extension to literature-based discovery that goes beyond making discoveries to a pr... more We present an extension to literature-based discovery that goes beyond making discoveries to a principled way of navigating through selected aspects of some biomedical domain. The method is a type of "discovery browsing" that guides the user through the research literature on a specified phenomenon. Poorly understood relationships may be explored through novel points of view, and potentially interesting relationships need not be known ahead of time. In a process of "cooperative reciprocity" the user iteratively focuses system output, thus controlling the large number of relationships often generated in literature-based discovery systems. The underlying technology exploits SemRep semantic predications represented as a graph of interconnected nodes (predication arguments) and edges (predicates). The system suggests paths in this graph, which represent chains of relationships. The methodology is illustrated with depressive disorder and focuses on the interaction of ...

Amia Annual Symposium Proceedings Amia Symposium Amia Symposium, 2011

Program, Apr 13, 2013

The Central Medical Library (CMK) at the Medical Faculty, University of Ljubljana, Slovenia creat... more The Central Medical Library (CMK) at the Medical Faculty, University of Ljubljana, Slovenia created its website in 1997 and since then has been actively involved in its maintenance and improvement. Its digital library is under rapid development, with permanently growing number of full text journals and databases. The analysis of our website usage revealed an increasing interest among the Slovene biomedical community especially for full text resources. By using data mining methods we discovered user navigation patterns, some of which were quite unexpected. Patrons have often complained to librarians about information overload and difficulty to follow all websites enhancements. Such a situation demanded for a dynamic restructuring of the CMK website. Often such problems are solved with customisable and personalised library portals because they address the modern library role directly by being customer focused, responding to customer needs, and empowering users to create personal information systems that are responsive to their individual needs. That is why we started to develop a personalised medical library portal. As we have limited financial and human resources, we decided to customise and extend an existing library portal software solution. We were especially interested in portal software from the higher education community and libraries as these solutions are usually being distributed under GNU Public Licence as open source code. We selected the MyLibrary library portal software from the North Carolina State University because it is the best documented of such projects, and has a well-developed and fairly intuitive interface for both users and administrators. We not only customised the MyLibrary portal for our library, but we also added some important new functionality, most notably multilingual support. Multilingual-support means that the user can select a language in which the portal interface is presented to her/him. Our extensions to the MyLibrary portal required changes both to the underlying data model and to the corresponding CGI Perl scripts which deal with the user and administrative interfaces. We would like to share our experience with developing a personalised medical library portal because we believe it is applicable to other European libraries, most of which usually offer information in at least two languages.

Scientometrics, 2021

Journal of Biomedical Informatics, 2021

Journal of Biomedical Informatics, 2018

Journal of medical systems, 2017

Libraries without Limits: Changing Needs — Changing Roles, 1999

The article describes the state and some trends in the development of medical informatics especia... more The article describes the state and some trends in the development of medical informatics especially regarding the fields of scientific information, knowledge discovery in databases, and the role of standards in data exchange. The ways of publication of scientific documents experienced dramatic changes with the development of the www, hence causing major changes in daily information practice. Contemporary textual databases contain full documents ofhypertextual and multimedia nature and links to full documents are increasingly common within the records of bibliographic databases. The last decade brought the advent of the web information tools, from web portals to global search engines, which are powerful aids but demand strong precaution regarding the quality of retrieved documents from the users. On the other hand, we are witnessing the development of digital libraries of scientific documents as a result of the self-organization of academic institutions, research groups and individuals, often in the opposition to the interests of publishing companies. The information support as an important element of medical procedures made possible the exchange of data between all segments of the health-care system and it has become clear that lack of standards governing structure, understanding and safety is among the biggest obstacles to successful data exchange. In addition, the article comprises a report on the methods of knowledge discovery in databases, which help us discover hiddenstructures and potential knowledge, invisible to the normal data processing software, in the enormous amount of data.

AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, 2011

Amia Annual Symposium Proceedings Amia Symposium Amia Symposium, 2011

Program, Apr 13, 2013