Dr. Lev Freidkin is a pulmonologist and clinical researcher specializing in interventional pulmonology. He currently serves as a Clinical Fellow in Interventional Pulmonology at McMaster University and holds a Clinical Lecturer appointment at Tel Aviv University. His expertise includes diagnostic and therapeutic bronchoscopy, critical care medicine, thoracic ultrasound, and pulmonary research. Dr. Freidkin has authored numerous peer-reviewed publications in respiratory medicine and has presented his work at national and international conferences. He is fluent in English, Hebrew, and Russian and actively integrates AI tools into medical education, research, and clinical practice.

Large Language Models Utility for Rapid On-Site Evaluation in Interventional Pulmonology Abstract Background: 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 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 (LLM) offers a significant advantage making diagnostic support more accessible. Objectives: Assess the diagnostic accuracy of the LLMs ChatGPT and Gemini in evaluating cytological smears during interventional pulmonology procedures. Methods: Retrospective evaluation of efficacy of LLMs for assessment of cytological smears obtained from adult patients that 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 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 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 feasibility of integrating this AI technology into workflow within pulmonary division. Larger prospective studies are needed to confirm effects on diagnostic yield. Keywords: Rapid on-site evaluation; cytology; Artificial Intelligence; ChatGPT; Gemini; interventional pulmonology; large language model