Jelena  Djekić Malbaša Djekić Malbaša

Prof. Dr. Jelena Djekić Malbaša Djekić Malbaša

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 June 2022 in JMIR Medical Informatics
Verified
Journal Article
Open access
CACelia Alvarez-Romero
Celia Alvarez-Romero
Alicia Martínez-GarcíaAlicia Martínez-García
Alicia Martínez-García
JVJara Ternero Vega
Jara Ternero Vega
PDPablo Díaz-Jimènez
Pablo Díaz-Jimènez
CJCarlos Jiménez-de Juan
Carlos Jiménez-de Juan
CCCarlos Luis Parra Calderón
Carlos Luis Parra Calderón
Background: Owing to the nature of health data, their sharing and reuse for research are limited by legal, technical, and ethical implications. In this sense, to address that challenge and facilitate and promote the discovery of scientific knowledge, the Findable, Accessible, Interoperable, and Reusable (FAIR) principles help organizations to share research data in a secure, appropriate, and useful way for other researchers. Objective: The objective of this study was the FAIRification of existing health research data sets and applying a federated machine learning architecture on top of the FAIRified data sets of different health research performing organizations. The entire FAIR4Health solution was validated through the assessment of a federated model for real-time prediction of 30-day readmission risk in patients with chronic obstructive pulmonary disease (COPD). Methods: The application of the FAIR principles on health research data sets in 3 different health care settings enabled a retrospective multicenter study for the development of specific federated machine learning models for the early prediction of 30-day readmission risk in patients with COPD. This predictive model was generated upon the FAIR4Health platform. Finally, an observational prospective study with 30 days follow-up was conducted in 2 health care centers from different countries. The same inclusion and exclusion criteria were used in both retrospective and prospective studies. Results: Clinical validation was demonstrated through the implementation of federated machine learning models on top of the FAIRified data sets from different health research performing organizations. The federated model for predicting the 30-day hospital readmission risk was trained using retrospective data from 4.944 patients with COPD. The assessment of the predictive model was performed using the data of 100 recruited (22 from Spain and 78 from Serbia) out of 2070 observed (records viewed) patients during the observational prospective study, which was executed from April 2021 to September 2021. Significant accuracy (0.98) and precision (0.25) of the predictive model generated upon the FAIR4Health platform were observed. Therefore, the generated prediction of 30-day readmission risk was confirmed in 87% (87/100) of cases. Conclusions: Implementing a FAIR data policy in health research performing organizations to facilitate data sharing and reuse is relevant and needed, following the discovery, access, integration, and analysis of health research data. The FAIR4Health project proposes a technological solution in the health domain to facilitate alignment with the FAIR principles.

16 June 2024 in Current Oncology
Verified
Journal Article
Open access
PDF file
Tomi KovacevicTomi Kovacevic
Tomi Kovacevic
BZBojan Zaric
Bojan Zaric
JMJelena Djekić Malbaša Djekić Malbaša
Jelena Djekić Malbaša Djekić Malbaša
DBDarijo Bokan
Darijo Bokan
BNBorislava Lazar Nikolin
Borislava Lazar Nikolin
DMDragana Maric
Dragana Maric
Background and Objectives: Death is an unavoidable experience in any person’s life and affects not only the dying person but also their caregivers. The dying process has been displaced from homes to health care facilities in the majority of cases. Facing death and dying has become an everyday life of health care professionals (HCP), especially in palliative care (PC) settings. This study aimed to investigate the death attitudes among HCPs in Serbia. Materials and Methods: The Serbian version of the Death Attitude Profile-Revised (DAP-RSp) was used as a measurement instrument. Results: The average age of the 180 included participants was 42.2 ± 9.9 years; the majority were females (70.0%), with more than 10 years of working experience (73.0%), physicians (70.0%) and those working in a non-oncological (non-ONC) field (57.78%). The mean total score of DAP-RSp was 124.80 ± 22.44. The highest mean score was observed in the neutral acceptance dimension (NA) (5.82 ± 0.90) and lowest in the Escape acceptance (EA) (2.57 ± 1.21). Higher negative death attitudes were reported among nurses compared to physicians (p = 0.002). Statistically significant differences were observed in the fear of death (FD) and death avoidance (DA) domains, favoring PC specialists and oncologists (p = 0.004; p = 0.015). Physicians working in Oncology (ONC) showed lower FD values (p = 0.001) compared to non-ONC departments. Conclusions: Attitudes toward death among HCPs are of great importance for the well-being of both HCPs and patients. Negative attitudes can lead to deficient care. The fear of death is highly represented among Serbian HCPs working in non-ONC fields, including both nurses and physicians. This study emphasizes the need for further research to comprehensively explore and understand HCPs’ attitudes toward death. This research highlights the need for the development of an educational curriculum across all levels of medical education, aimed at overcoming the fear of death and enhancing coping strategies, which will improve the care for patients diagnosed with terminal illnesses.

17 October 2022 in Microorganisms
Verified
Journal Article
Open access
PDF file
APAleksandra Patić
Aleksandra Patić
Vladimir VukovićVladimir Vuković
Vladimir Vuković
Gordana KovacevicGordana Kovacevic
Gordana Kovacevic
VPVladimir J Petrovic
Vladimir J Petrovic
MRMioljub Ristić
Mioljub Ristić
ICIvana Hrnjaković Cvjetković
Ivana Hrnjaković Cvjetković
Rotaviruses (RV) are the leading cause of gastroenteritis in infants, young children, and adults, responsible for serious disease burden. In the period 2012–2018, a cross-sectional study was conducted using stool samples collected from patients with acute gastroenteritis from Vojvodina, Serbia. We described age and gender distribution, as well as seasonal patterns of RV prevalence. Out of 1853 included stool samples, RV was detected in 29%. Hospitalized children between 1–2 years old were especially affected by RV infection (45%). The highest prevalence of infection was observed during the colder, winter/spring months. We compared sequenced representative G and P genotypes circulating in Serbia with vaccine strains and determined their genetic similarity. Genotype combination G2P[4] was the most prevalent (34.6%), followed by G2P[8] (24.1%) and G1P[8] (21.1%). Given that several epitopes were conserved, neutralization motifs among circulating strains can be characterized as sufficiently matching vaccine strains Rotarix™ and RotaTeq™, but existing antigenic disparities should not be overlooked. The present results contribute to a better insight into the prevalence of rotavirus infection in our region and point out the need for epidemiological surveillance of rotaviruses before the introduction of vaccines. These data can help formulate future vaccine strategies in Serbia.

31 August 2023 in Respiratio
Verified
Journal Article
Closed access
SVSremska Kamenica Institut Za Plućne Bolesti Vojvodine
Sremska Kamenica Institut Za Plućne Bolesti Vojvodine
JMJelena Djekić Malbaša Djekić Malbaša
Jelena Djekić Malbaša Djekić Malbaša
DBDarijo Bokan
Darijo Bokan
BZBojan Zaric
Bojan Zaric
Tomi KovacevicTomi Kovacevic
Tomi Kovacevic
IKIvan Kuhajda
Ivan Kuhajda
Introduction Better survival of lung cancer (LC) patients is possible if the diagnosis is made early in the disease course. Low-dose CT in a high-risk population for developing LC enables cancer detection in the earlier stages of the disease and improves survival. Method LC screening with low-dose CT was performed at the Institute for Pulmonary Diseases of Vojvodina (IPBV) from September 2020 to December 2022. People aged 50-74 years, ex-smokers (started smoking 10 years ago) and active smokers with •30 pack-years, or •20 pack-years with additional risk factors, were included. We retrospectively analyzed screen population characteristics, screening results (according to Lung-RADS score) and definite findings of suspicious nodules by histological type and LC stage by gender. Results During the observed period, a total of 3432 LDCT scans were performed, of which 62.3% (2138) were baseline LDCT. Suspicious and highly suspicious nodule findings (Lung-RADS 4) were observed in 196 (9.2%) subjects. The emphysema was registered in 709 (33.2%) subjects. The LC detection rate was 1.8% (40/2138). 88.5% (23/26) of confirmed LC were detected after the initial LDCT, while the remaining 11.5% (3/26) were established after the follow-up period. 75% (30/40) of LC were in stages I to IIIA. Non-small cell lung cancer (adenocarcinoma 60.0% (24/40), squamous cancers 22.5% (9/40) and other non-small cell cancers (NOS) 5.0% (2/40)) accounted for 85.7% (35/40), while small cells lung cancer was present in 12.5% (5/40). Conclusion Most LC cases were detected in the early stage of the disease. Therefore, screening for LC should cover the high-risk population in the territory of the entire Republic.

1 January 2024 in Srpski arhiv za celokupno lekarstvo
Verified
Journal Article
Open access
PDF file
MKMarko Koprivica
Marko Koprivica
JMJelena Djekić Malbaša Djekić Malbaša
Jelena Djekić Malbaša Djekić Malbaša
Introduction/Objective. Clostridioides difficile is one of the most common infectious agents and an important cause of infections among hospitalized patients, often resulting in severe and potentially fatal outcomes. The objective of this study was to determine demographical characteristics (age and sex distribution) and outcomes among hospitalized patients with Clostridioides difficile infection, and to analyze differences in toxin A, toxin B or toxin A/B prevalence among hospitalized patients with Clostridioides difficile infection. Methods. Retrospective descriptive analysis of 200 patients hospitalized at the Institute for Pulmonary Diseases of Vojvodina, Serbia, from 2015 to 2018 was performed. The data were obtained using a standardized ?Active surveillance of Clostridioides difficile? questionnaire. A non-parametric ?2 test and binominal logistic regression was used to validate all hypotheses: focusing on higher infection rates and mortality in the elderly compared to younger populations, and the predominance of diagnostic methods isolating both toxins A and B. Results. There are statistically significant differences in the distribution of infection cases among age groups, particularly with a higher prevalence in individuals aged 66 and older, (p < 0.001). There is a statistically significant difference in the frequency of respondents in relation to the detection of toxins. Percentage of representation of toxins is 61.5%. Conclusion. The results show that the most common diagnostic method is the detection of toxins A and B, rather than isolating either toxin independently. However, the study suggests that certain diagnostic methods should be supplemented by other newer diagnostic methods.

16 July 2026 in Healthcare
Verified
Journal Article
Open access
PDF file
BMBiljana Mijović
Biljana Mijović
Bojan JoksimovićBojan Joksimović
Bojan Joksimović
MDMilena Dubravac
Milena Dubravac
JKJovan Kulić
Jovan Kulić
ZSZorica Stojanović
Zorica Stojanović
PDPredrag Duric
Predrag Duric
Background: The Health in All Policies (HiAP) approach promotes the systematic integration of health considerations into policymaking across non-health sectors to address social determinants of health and improve population health outcomes. Although increasingly recognized internationally, the extent of its legislative implementation in the Republic of Srpska remains unclear. Objective: To assess the extent to which HiAP principles are embedded in sectoral legislation in the Republic of Srpska and to identify strengths and gaps in current legal frameworks. Methods: A structured content analysis of the text of laws was conducted across ten priority sectors. Twenty-two laws were reviewed using an analytical framework based on five core HiAP components: health outcomes, intersectoral governance, health equity, evidence-informed policymaking, and monitoring and accountability. The presence and distribution of these components were systematically examined across sectors. Results: Health considerations were frequently reflected in the text of the analysed legislation. Explicit references to health outcomes and intersectoral governance were identified in more than 60% of laws. However, integration was uneven across sectors. Health equity principles were inconsistently incorporated, while monitoring, evaluation, and accountability mechanisms were insufficiently developed, with explicit provisions found in fewer than half of the laws. No analysed law formally mandated Health Impact Assessment as a policy instrument. Conclusions: The Republic of Srpska has an existing legislative basis for advancing HiAP, but implementation remains fragmented rather than systematic. Addressing identified gaps—particularly in health equity, Health Impact Assessment, and health-oriented monitoring mechanisms—through targeted legislative reforms could improve policy coherence, accountability, and long-term sustainability. To our knowledge, this is the first systematic content analysis of HiAP integration in the sectoral legislation of the Republic of Srpska; it applies a replicable analytical framework derived from the WHO HiAP Framework for Country Action that is transferable to other decentralised and transitional governance settings.