Bogdan Levita

Dr. Bogdan Levita

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
SESemil Eminovic
Semil Eminovic
BLBogdan Levita
Bogdan Levita
ADAndrea Dell'Orco
Andrea Dell'Orco
JLJonas Alexander Leppig
Jonas Alexander Leppig
JNJawed Nawabi
Jawed Nawabi
TPTobias Penzkofer
Tobias Penzkofer
Background/Objectives: This study compares the accuracy of responses from state-of-the-art large language models (LLMs) to patient questions before CT and MRI imaging. We aim to demonstrate the potential of LLMs in improving workflow efficiency, while also highlighting risks such as misinformation. Methods: There were 57 CT-related and 64 MRI-related patient questions displayed to ChatGPT-4o, Claude 3.5 Sonnet, Google Gemini, and Mistral Large 2. Each answer was evaluated by two board-certified radiologists and scored for accuracy/correctness/likelihood to mislead using a 5-point Likert scale. Statistics compared LLM performance across question categories. Results: ChatGPT-4o achieved the highest average scores for CT-related questions and tied with Claude 3.5 Sonnet for MRI-related questions, with higher scores across all models for MRI (ChatGPT-4o: CT [4.52 (± 0.46)], MRI: [4.79 (± 0.37)]; Google Gemini: CT [4.44 (± 0.58)]; MRI [4.68 (± 0.58)]; Claude 3.5 Sonnet: CT [4.40 (± 0.59)]; MRI [4.79 (± 0.37)]; Mistral Large 2: CT [4.25 (± 0.54)]; MRI [4.74 (± 0.47)]). At least one response per LLM was rated as inaccurate, with Google Gemini answering most often potentially misleading (in 5.26% for CT and 2.34% for MRI). Mistral Large 2 was outperformed by ChatGPT-4o for all CT-related questions (p < 0.001) and by ChatGPT-4o (p = 0.003), Google Gemini (p = 0.022), and Claude 3.5 Sonnet (p = 0.004) for all CT Contrast media information questions. Conclusions: Even though all LLMs performed well overall and showed great potential for patient education, each model occasionally displayed potentially misleading information, highlighting the clinical application risk.

26 June 2026 in JMIR AI
Verified
Journal Article
Open access
SESemil Eminovic
Semil Eminovic
RSRobin Schmidt
Robin Schmidt
BLBogdan Levita
Bogdan Levita
MLMaximilian Lindholz
Maximilian Lindholz
AHAnna-Maria Haack
Anna-Maria Haack
TPTobias Penzkofer
Tobias Penzkofer
Background: Radiology trainees require efficient, accurate, and accessible resources to master complex imaging techniques and identify findings that guide clinical decision-making. Large language models (LLMs) are emerging as promising tools for medical education and clinical workflows, offering the potential to enhance learning by providing instant feedback, aiding in diagnostic accuracy, and offering personalized learning experiences. However, systematic comparisons of LLMs for radiology education and clinical support remain limited, particularly regarding differences across subspecialties and resident experience levels. Objective: This study aimed to evaluate and compare the response quality of 2 state-of-the-art reasoning-based LLMs, namely DeepSeek-R1 and ChatGPT-o1, as clinical and radiology residency support tools, comparing performance across clinical and didactic dimensions, including text- and image-based responses. Methods: Overall, 27 radiology questions covering 9 radiological subspecialties were answered by both LLMs. Additionally, 6 image-based questions were presented only to ChatGPT-o1 due to its image processing capabilities. Responses were independently rated by 7 radiology residents (postgraduate years 2‐5) across 9 rating criteria grouped into 3 dimensions (factual accuracy, clinical practicality, and didactic value), using a 5-point Likert scale. Statistics compared LLMs, reader experience, and response types for text- as well as image-based for ChatGPT-o1 queries. Results: DeepSeek-R1 consistently outperformed ChatGPT-o1 across all rating dimensions, with highly significant differences across all criteria (mean ratings: DeepSeek-R1 4.51, SD 0.73 vs ChatGPT-o1 3.73, SD 0.98; P <.001). In an exploratory subspecialty-level analysis, DeepSeek-R1 descriptively outperformed ChatGPT-o1 across all subspecialties. For both LLMs accumulated, junior residents tended to rate slightly higher than seniors in 7 of 9 criteria, although differences were not statistically significant. However, for ChatGPT-o1, junior residents rated significantly higher in overall score across all criteria (juniors 3.81, SD 0.64 vs seniors 3.63, SD 0.65; P =.02). Image-based responses by ChatGPT-o1 scored significantly lower than text-based (mean 3.19, SD 1.42; P =.007), particularly in factual accuracy (mean 2.75, SD 1.45; P <.001) and clinical practicality (mean 3.11, SD 1.47; P =.03). Conclusions: Both DeepSeek-R1 and ChatGPT-o1 demonstrate promising potential on simulated radiology question sets designed for educational and clinical contexts, with DeepSeek-R1 outperforming ChatGPT-o1 across all evaluated criteria. These results emphasize the value of open-source models for educational use and provide early evidence that LLMs may support radiology resident training under controlled conditions; however, their real-world educational and clinical effects require further investigation. Future research should prospectively evaluate how LLMs can be integrated into radiology training, assess their impact alongside conventional teaching methods, and investigate multimodal capabilities to better reflect realistic clinical scenarios.

13 October 2025 in CVIR Endovascular
Verified
Journal Article
Open access
PDF file
BLBogdan Levita
Bogdan Levita
SESemil Eminovic
Semil Eminovic
WLWillie Magnus Lüdemann
Willie Magnus Lüdemann
DSDirk Schnapauff
Dirk Schnapauff
RSRobin Schmidt
Robin Schmidt
TPTobias Penzkofer
Tobias Penzkofer
Purpose: This study evaluates four large language models’ (LLMs) ability to answer common patient questions preceding transarterial periarticular embolization (TAPE), computed tomography (CT)-guided high-dose-rate (HDR) brachytherapy, and bleomycin electrosclerotherapy (BEST). The goal is to evaluate their potential to enhance clinical workflows and patient comprehension, while also assessing associated risks. Materials and methods: Thirty-five TAPE, 34 CT-HDR brachytherapy, and 36 BEST related questions were presented to ChatGPT-4o, DeepSeek-V3, OpenBioLLM-8b, and BioMistral-7b. The LLM-generated responses were independently assessed by two board-certified radiologists. Accuracy was rated on a 5-point Likert scale. Statistics compared LLM performance across question categories for patient-education suitability. Results: DeepSeek-V3 attained the highest mean scores for BEST [4.49 (± 0.77)] and CT-HDR [4.24 (± 0.81)] and demonstrated comparable performance to ChatGPT-4o for TAPE-related questions (DeepSeek-V3 [4.20 (± 0.77)] vs. ChatGPT-4o [4.17 (± 0.64)]; p = 1.000). In contrast, OpenBioLLM-8b (BEST 3.51 (± 1.15), CT-HDR 3.32 (± 1.13), TAPE 3.34 (± 1.16)) and BioMistral-7b (BEST 2.92 (± 1.35), CT-HDR 3.03 (± 1.06), TAPE 3.33 (± 1.28)) performed significantly worse than DeepSeek-V3 and ChatGPT-4o across all procedures. Preparation/Planning was the only category without statistically significant differences across all three procedures. Conclusion: DeepSeek-V3 and ChatGPT-4o excelled on TAPE, BEST, and CT-HDR brachytherapy questions, indicating potential to enhance patient education in interventional radiology, where complex but minimally invasive procedures often are explained in brief consultations. However, OpenBioLLM-8b and BioMistral-7b exhibited more frequent inaccuracies, suggesting that LLMs cannot replace comprehensive clinical consultations yet. Patient feedback and clinical workflow implementation should validate these findings.

22 August 2025 in Research Square
Verified
Preprint
Open access
PDF file
BLBogdan Levita
Bogdan Levita
SESemil Eminovic
Semil Eminovic
WLWillie Magnus Lüdemann
Willie Magnus Lüdemann
DSDirk Schnapauff
Dirk Schnapauff
RSRobin Schmidt
Robin Schmidt
TPTobias Penzkofer
Tobias Penzkofer
Purpose : This study evaluates four large language models’ (LLMs) ability to answer common patient questions preceding transarterial periarticular embolization (TAPE), computed tomography (CT)-guided high-dose-rate (HDR) brachytherapy, and bleomycin electrosclerotherapy (BEST). The goal is to evaluate their potential to enhance clinical workflows and patient comprehension, while also assessing associated risks. Materials and Methods: 35 TAPE, 34 CT‑HDR brachytherapy, and 36 BEST related questions were presented to ChatGPT-4o, DeepSeek-V3, OpenBioLLM-8b, and BioMistral-7b. The LLM-generated responses were independently assessed by two board-certified radiologists. Accuracy was rated on a 5-point Likert scale. Statistics compared LLM performance across question categories for patient-education suitability. Results: DeepSeek-V3 attained the highest mean scores for BEST [4.49 (± 0.77)] and CT-HDR [4.24 (± 0.81)] and demonstrated comparable performance to ChatGPT-4o for TAPE-related questions (DeepSeek-V3 [4.20 (± 0.77)] vs. ChatGPT-4o [4.17 (± 0.64)]; p = 1.000). In contrast, OpenBioLLM-8b (BEST 3.51 (± 1.15), CT-HDR 3.32 (± 1.13), TAPE 3.34 (± 1.16)) and BioMistral-7b (BEST 2.92 (± 1.35), CT-HDR 3.03 (± 1.06), TAPE 3.33 (± 1.28)) performed significantly worse than DeepSeek-V3 and ChatGPT-4o across all procedures. Preparation/Planning was the only category without statistically significant differences across all three procedures. Conclusion: DeepSeek‑V3 and ChatGPT‑4o excelled on TAPE, BEST and CT‑HDR brachytherapy questions, indicating potential to enhance patient education in interventional radiology, where complex but minimally invasive procedures often are explained in brief consultations. However, OpenBioLLM‑8b and BioMistral‑7b exhibited more frequent inaccuracies, suggesting that LLMs cannot replace comprehensive clinical consultations yet. Patient feedback and clinical workflow implementation should validate these findings.

1 February 2026 in Digital Health
Verified
Journal Article
Open access
SESemil Eminovic
Semil Eminovic
BLBogdan Levita
Bogdan Levita
RSRobin Schmidt
Robin Schmidt
MLMaximilian Lindholz
Maximilian Lindholz
DDDmitriy Desser
Dmitriy Desser
JNJawed Nawabi
Jawed Nawabi
Objectives: Large language models (LLMs) are being used to facilitate academic writing. We aimed (1) to assess the quality, integrity, and factual reliability of LLM-assisted academic writing in medicine, and (2) to compare the performance of open-source versus proprietary LLMs, reflecting differences in model transparency. Methods: In this prospective, controlled evaluation study, an open-source model (DeepSeek-R1) and proprietary model (ChatGPT-o1) completed ten academic tasks: generating five scientific essays and five evidence-based question-answers covering clinical topics in neuroradiology. Two radiologists rated outputs using 14 Likert and 7 binary criteria across the domains of academic quality, linguistic expression, factual reliability. Paired Wilcoxon/McNemar (Holm) assessed differences; ICC/Cohen’s κ assessed reliability. Results: DeepSeek-R1 achieved higher overall mean Likert scores than ChatGPT-o1 (mean ratings ± standard deviation: 3.23 ± 0.44 vs 3.02 ± 0.30, p = 0.021). It significantly outperformed in reasoning depth (p = 0.015), contextual coherence (p = 0.043), subtlety (p = 0.037), and evidence integration (p = 0.027). Although both models cited sources in every output, citation reliability was poor. DeepSeek-R1 cited more real publications (55.1% vs. 33.3%, p=0.053) but showed a higher confirmed fabrication rate (36.7% vs. 2.6%, p<0.001). DeepSeek-R1 respected word limits in 90%, ChatGPT-o1 only in 50%. Neither reviewer reliably noticed AI‐generated text features. Inter-rater reliability was poor for Likert criteria (ICC = 0.466) and substantial for binary items (κ = 0.746). Conclusion: DeepSeek-R1 outperformed ChatGPT-o1 in generating academic content for neuroradiology, highlighting the potential of transparent, locally deployable models. However, moderate quality, citation errors and hallucinations indicate that LLMs are not yet sufficient for unsupervised academic writing and demand rigorous human review.