S755
Clinical - Lung
ESTRO 2026
treatment recommendations from large language models (LLMs) with expert decisions based on NCCN guidelines. Material/Methods: A retrospective analysis was conducted on 12 MPM cases treated between 2021 and 2023 at a tertiary university hospital. AI-generated recommendations from ChatGPT, Gemini, and Copilot were compared with multidisciplinary tumor board decisions regarding initial treatment strategy, radiotherapy (RT) timing, target volume delineation, dosimetric assessment, and RT plan approval. AI responses were scored using a 5- point Likert scale by three radiation oncologists. Readability and quality assessments were performed using the DISCERN scale and established readability metrics. Statistical analyses included intraclass correlation coefficients, Friedman tests, and Wilcoxon signed-rank tests with Bonferroni correction. Results: The study analyzed 12 cases with 60 questions comparing three large language models (LLMs) in mesothelioma treatment decision-making. ChatGPT demonstrated superior performance with the highest mean score (4.50 ± 0.57) and a median score of 5, significantly outperforming both Gemini (mean 3.77 ± 0.43, median 4) and Copilot (mean 3.85 ± 0.52, median 4). These differences were statistically significant (p < 0.001).The category-specific analysis showed that ChatGPT consistently excelled across all decision- making domains, with particularly strong performance in radiotherapy timing and dosimetric data evaluation (median scores of 5). ChatGPT significantly outperformed the other models in four of five categories: Initial Treatment Recommendation, Radiotherapy Timing, Radiotherapy Planning, and Dosimetric Data Evaluation (all p < 0.05).Gemini maintained consistent but moderate performance with median scores of 4 across all categories. Copilot showed more variable performance with median scores ranging from 3-4 depending on the category. In the Radiotherapy Plan Approval category, ChatGPT and Gemini performed similarly (p = 1.000), while Copilot scored significantly lower (p = 0.025). ChatGPT achieved the highest DISCERN score (70/75, excellent quality), while Copilot (62/75) and Gemini (61/75) were rated as good. Readability analyses classified all AI outputs as "difficult to read," with Copilot being the most readable (Flesch Reading Ease Score = 35.52). Conclusion: Among the evaluated AI models, ChatGPT provided the most accurate and clinically relevant recommendations for MPM management. While AI tools show promise in decision support, their integration into clinical workflows requires further validation. Future research should focus on refining AI algorithms to enhance readability and reliability for clinical applications.
30.9 months (95% CI:14.3-NR), and the median PFS was 9.1 months (95% CI: 6.1-NR). Best response rates were: complete response (CR) 46.2%, partial response (PR) 15.3%, progressive disease (PD) 23.1%, and non- evaluable 15.4%. Among patients with progression, only 1 (7.7%) had local failure, while the rest experienced distant metastases. Common adverse events included esophagitis (69.2%; Grade 1-2: 61.5%, Grade 3: 7.6%), neutropenia (61.5%; Grade 1-2: 23%, Grade 3-4: 38.4%), and pneumonitis (38.4%, all Grade 1). No Grade 5 events occurred. The median GTV was 156 cc (range: 36-444), and the mean lung dose was 15.03 Gy (range: 7.9-24). Conclusion: Conclusions: In this real-world experience, high-dose RT (60 Gy in 40 fractions over 4 weeks given twice daily), for LS-SCLC resulted in promising response rates, excellent local control, and favorable early survival outcomes. These findings, consistent with the previous phase 2 trial, support the broader implementation of this intensive regimen in clinical practice. Turrisi AT, Kim K, Blum R, et al. Twice-Daily Compared with Once-Daily Thoracic Radiotherapy in Limited Small-Cell Lung Cancer Treated Concurrently with Cisplatin and Etoposide. New England Journal of Medicine. 1999;340(4):265- 271. doi:10.1056/NEJM199901283400403/ASSET/6B099F54- A4BD-43002. Li C, Lei S, Ding L, et al. Global burden and trends of lung cancer incidence and mortality. Chin Med J (Engl). 2023;136(13):1583. doi:10.1097/CM9.000000000000253. Grønberg BH, Killingberg KT, Fløtten Ø, et al. High-dose versus standard-dose twice-daily thoracic radiotherapy for patients with limited stage small-cell lung cancer: an open-label, randomised, phase 2 trial. Lancet Oncol. 2021;22(3):321-331. doi:10.1016/S1470- 2045(20)30742-7 Keywords: high radiation dose , limited sclc, lung cancer References: References:1. Artificial Intelligence-Assisted Decision Making in Malignant Pleural Mesothelioma: A Comparative Analysis of AI Responses Mert Delikaya, Fatma Sert Radiation Oncology, Ege University School of Medicine, Izmir, Turkey Purpose/Objective: This study evaluates the applicability of artificial intelligence (AI) in clinical decision-making for malignant pleural mesothelioma (MPM) by comparing Digital Poster 224
Made with FlippingBook - Share PDF online