Large Language Models Utility for Rapid On-Site Evaluation in Interventional Pulmonology
Diagnostics · 28.05.2026 · 16 (11) · 1658
DOI: 10.3390/diagnostics16111658 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 28.05.2026. Verfasst von Maayan Flaschner und 10 weiteren Autor:innen. Beteiligte Einrichtung: Pulmonary Institute, Rabin Medical Center, Petah Tikva 4941492, Israel. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Rapid on-site evaluation (ROSE) is a valuable technique in interventional procedures to immediately assess the adequacy and quality of biopsy specimens at the time they are obtained. The integration of artificial intelligence (AI) into ROSE workflows has demonstrated diagnostic accuracy comparable to that of experienced cytologists. However, clinical implementation of AI-based ROSE models is limited by complex and expensive development. In contrast, the use of free or near-free global large language models (LLMs) offers a significant advantage, making diagnostic support more accessible. Assess the diagnostic accuracy of the LLMs ChatGPT and Gemini in evaluating cytological smears during interventional pulmonology procedures.
Methods
Retrospective evaluation of the efficacy of LLMs for assessment of cytological smears obtained from adult patients who underwent interventional bronchoscopic and ultrasound-guided biopsies between 2020 and 2025. Images of ROSE-prepared samples were analyzed by ChatGPT-4o, ChatGPT-5, ChatGPT-5 “thinking”, and Gemini 2.5 models.
Results
Forty-eight procedures in 47 patients (mean age 65 years) were analyzed; 79% of biopsies were malignant. Using the final histopathology report as reference, cytologists achieved balanced accuracy of 0.75 (Gwet’s AC1 = 0.53, sensitivity 0.71, specificity 0.78). ChatGPT-5 “thinking” showed high concordance (accuracy 0.65, Gwet’s AC1 = 0.81, sensitivity 1.00, specificity 0.30). Gemini reached an accuracy of 0.59 (Gwet’s AC1 = 0.76, sensitivity 0.97, specificity 0.20).
Conclusions
To our knowledge, this study is the first to evaluate LLM-assisted ROSE in interventional pulmonology. The results suggest the potential feasibility of integrating this AI technology into the workflow within the pulmonary division. Larger prospective studies are needed to confirm effects on diagnostic yield.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Pulmonary Institute, Rabin Medical Center, Petah Tikva 4941492, Israel.
- Gray School of Medicine, Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv 6997801, Israel.
- Department of Pathology, Rabin Medical Center, Petah Tikva 4941492, Israel.
- Institute of Pulmonary Medicine, Tel Aviv Sourasky Medical Center, Tel Aviv 6423906, Israel.
ORCID-Profile: Maayan Flaschner, Mordechai Reuven Kramer, Evgeni Gershman, Shai Moshe Amor, Barak Pertzov, Moshe Heching, Lev Freidkin
Zitieren
APA
Flaschner, M., Kramer, M. R., Krolik, A., Gershman, E., Tovar, A., Rosengarten, D., Amor, S. M., Pertzov, B., Heching, M., Shtraichman, O., & Freidkin, L. (2026). Large Language Models Utility for Rapid On-Site Evaluation in Interventional Pulmonology. Diagnostics, 16(11), 1658. https://doi.org/10.3390/diagnostics16111658
Vancouver
Flaschner M, Kramer MR, Krolik A, Gershman E, Tovar A, Rosengarten D, et al. Large Language Models Utility for Rapid On-Site Evaluation in Interventional Pulmonology. Diagnostics. 2026;16(11):1658. doi:10.3390/diagnostics16111658
BibTeX
@article{Flaschner2026,
author = {Flaschner, Maayan and Kramer, Mordechai Reuven and Krolik, Alex and Gershman, Evgeni and Tovar, Anna and Rosengarten, Dror and Amor, Shai Moshe and Pertzov, Barak and Heching, Moshe and Shtraichman, Osnat and Freidkin, Lev},
title = {Large Language Models Utility for Rapid On-Site Evaluation in Interventional Pulmonology},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {11},
pages = {1658},
doi = {10.3390/diagnostics16111658}
}
EUVIMED