Investigator
Technical University Of Munich
Exploring the potential of AI ‐powered applications for clinical decision‐making in gynecologic oncology
Abstract Objective The rise of artificial intelligence (AI) and large language models like Llama, Gemini, or Generative Pretraining Transformer (GPT) signals a promising new era in natural language processing and has significant potential for application in medical care. This study seeks to investigate the potential of GPT‐4 for automated therapy recommendations by examining individual patient health record data with a focus on gynecologic malignancies and breast cancer. Methods We tasked GPT‐4 with generating independent treatment proposals for 60 randomly selected patient cases presented at gynecologic and senologic multidisciplinary tumor boards (MDTs). The treatment recommendations by GPT‐4 were compared with those of the MDTs using a novel clinical concordance score and were reviewed both qualitatively and quantitatively by experienced gynecologic oncologists. Results GPT‐4 generated coherent therapeutic recommendations for all clinical cases. Overall, these recommendations were assessed by clinical experts as moderately sufficient for real‐word clinical application. Deficiencies in both accuracy and completeness were especially noted. Using a quantitative clinical concordance score, GPT‐4 consistently demonstrated superior performance in managing the senologic cases compared with the gynecologic cases. Iterative prompting substantially enhanced treatment recommendations in both categories, increasing concordance with MDT decisions to up to 84% in senologic cases. Conclusion GPT‐4 is capable of processing complex patient cases and generates detailed treatment recommendations; however, differences persist in surgical approaches and the use of systemic therapies, and there is a tendency toward recommending excessive genetic testing. As AI‐powered solutions continue to be integrated into medicine, we envision the potential for automated therapy recommendations to play a supportive role in human clinical decision‐making in the future.
AI‐driven simplification of surgical reports in gynecologic oncology: A potential tool for patient education
AbstractIntroductionThe emergence of large language models heralds a new chapter in natural language processing, with immense potential for improving medical care and especially medical oncology. One recent and publicly available example is Generative Pretraining Transformer 4 (GPT‐4). Our objective was to evaluate its ability to rephrase original surgical reports into simplified versions that are more comprehensible to patients. Specifically, we aimed to investigate and discuss the potential, limitations, and associated risks of using these simplified reports for patient education and information in gynecologic oncology.Material and MethodsWe tasked GPT‐4 with generating simplified versions from n = 20 original gynecologic surgical reports. Patients were provided with both their original report and the corresponding simplified version generated by GPT‐4. Alongside these reports, patients received questionnaires designed to facilitate a comparative assessment between the original and simplified surgical reports. Furthermore, clinical experts evaluated the artificial intelligence (AI)‐generated reports with regard to their accuracy and clinical quality.ResultsThe simplified surgical reports generated by GPT‐4 significantly improved our patients' understanding, particularly with regard to the surgical procedure, its outcome, and potential risks. However, despite the reports being more accessible and relevant, clinical experts highlighted concerns about their lack of medical precision.ConclusionsAdvanced language models like GPT‐4 can transform unedited surgical reports to improve clarity about the procedure and its outcomes. It offers considerable promise for enhancing patient education. However, concerns about medical precision underscore the need for rigorous oversight to safely integrate AI into patient education. Over the medium term, AI‐generated, simplified versions of these reports—and other medical records—could be effortlessly integrated into standard automated postoperative care and digital discharge systems.
