Milica Radovic

Dr. Milica Radovic

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
1 January 2024 in Scandinavian Journal of Pain
Verified
Journal Article
Open access
PDF file
SBSuzana Bojic
Suzana Bojic
NRNemanja Radovanovic
Nemanja Radovanovic
MRMilica Radovic
Milica Radovic
DSDusica Stamenkovic
Dusica Stamenkovic
Background: Generative artificial intelligence (AI) models offer potential assistance in pain research data acquisition, yet concerns persist regarding data accuracy and reliability. In a comparative study, we evaluated open generative AI models’ capacity to acquire data on acute pain in rock climbers comparable to field research. Methods: Fifty-two rock climbers (33 m/19 f; age 29.0 [24.0–35.75] years) were asked to report pain location and intensity during a single climbing session. Five generative pretrained transformer models were tasked with responses to the same questions. Results: Climbers identified the back of the forearm (19.2%) and toes (17.3%) as primary pain sites, with reported median pain intensity at 4 [3–5] and median maximum pain intensity at 7 [5–8]. Conversely, AI models yielded divergent findings, indicating fingers, hands, shoulders, legs, and feet as primary pain localizations with average and maximum pain intensity ranging from 3 to 4.4 and 5 to 10, respectively. Only two AI models provided references that were untraceable in PubMed and Google searches. Conclusion: Our findings reveal that, currently, open generative AI models cannot match the quality of field-collected data on acute pain in rock climbers. Moreover, the models generated nonexistent references, raising concerns about their reliability.

7 July 2026 in Life
Verified
Journal Article
Open access
PDF file
BMBojan Mitrovic
Bojan Mitrovic
MRMilica Radovic
Milica Radovic
Ljiljana KosLjiljana Kos
Ljiljana Kos
TKTamara Kovacevic-Preradovic
Tamara Kovacevic-Preradovic
BDBoris Dzudovic
Boris Dzudovic
SOSlobodan Obradovic
Slobodan Obradovic
Background: The significance of imaging right-heart thrombus via echocardiography in acute pulmonary embolism (PE) patients, as well as its management, remains uncertain. Methods: In this retrospective, observational, multicenter, and multinational registry of consecutive acute PE patients, we compared 100 patients in whom thrombus was visualized in the right heart during echocardiographic evaluation with 2635 patients without visualization of thrombus. The co-primary endpoints were all-cause in-hospital mortality and PE-related mortality. Secondary endpoints included the prevalence of severe PE at admission (intermediate–high and high-risk PE), the frequency of thrombolytic therapy administration, and mortality among patients who received thrombolysis. Results: All-cause and PE-related mortality were higher in patients with thrombus in the right heart (31.0% vs. 9.6%, and 25.8% vs. 5.6%, p < 0.001, respectively). Patients with right-heart thrombi had a more severe PE presentation than those without (74.0% vs. 45.3%, p < 0.001). In patients treated with thrombolysis, all-cause mortality was higher in patients with right-heart thrombi (35.5% vs. 12.7%, p < 0.001). In the multivariable Cox regression analysis adjusted for ESC mortality risk, age, presence of syncope, atrial fibrillation, and hypoxemia, patients with thrombus in the right heart had a significantly higher risk of all-cause and PE-related death compared to patients without thrombus (HR 2.60, 95% CI 1.753–3.859, p < 0.001, and HR 3.287, 95% CI 2.056–5.253, p < 0.001, respectively). Conclusions: Visualization of thrombus in transit through the right heart is associated with higher all-cause and PE-related mortality, independent of PE severity and the use of thrombolytic therapy.