The Consistency and Quality of ChatGPT Responses Compared to Clinical Guidelines for Ovarian Cancer: A Delphi Approach.

INTRODUCTION: In recent years, generative Artificial Intelligence models, such as ChatGPT, have increasingly been utilized in healthcare. Despite acknowledging the high potential of AI models in terms of quick access to sources and formulating responses to a clinical question, the results obtained using these models still require validation through comparison with established clinical guidelines. This study compares the responses of the AI model to eight clinical questions with the Italian Association of Medical Oncology (AIOM) guidelines for ovarian cancer. MATERIALS AND METHODS: The authors used the Delphi method to evaluate responses from ChatGPT and the AIOM guidelines. An expert panel of healthcare professionals assessed responses based on clarity, consistency, comprehensiveness, usability, and quality using a five-point Likert scale. The GRADE methodology assessed the evidence quality and the recommendations' strength. RESULTS: A survey involving 14 physicians revealed that the AIOM guidelines consistently scored higher averages compared to the AI models, with a statistically significant difference. Post hoc tests showed that AIOM guidelines significantly differed from all AI models, with no significant difference among the AI models. CONCLUSIONS: While AI models can provide rapid responses, they must match established clinical guidelines regarding clarity, consistency, comprehensiveness, usability, and quality. These findings underscore the importance of relying on expert-developed guidelines in clinical decision-making and highlight potential areas for AI model improvement.

Iris metastasis from endometrial carcinoma: A challenging diagnosis and individualized eye-sparing treatment.

A woman in her 70's with a history of recurrent oral aphthosis and two years earlier of resected stage IA low risk endometrial adenocarcinoma, presented with blurred vision and a painful mass of the right eye that had developed in two months. PET/CT imaging detected a nodule in the right lung. Because of diagnostic uncertainties between inflammatory disease (Behçet syndrome) or cancer, a biopsy of iris and pulmonary lesions were performed and lead to histologically documented metastases from endometrial adenocarcinoma in both sites. After a multidisciplinary team discussion excluding disfiguring local therapies (radiation therapy or surgery), systemic chemotherapy with carboplatin and paclitaxel was performed, leading to radiological complete response that is sustained at 12 months after the end of treatment. This case shows that chemotherapy should be considered as a valid organ-sparing treatment in the management of these uncommon metastatic sites.

Prognostic value of pathological tumor regression grade in locally advanced gastric cancer: New perspectives from a single-center experience.

BACKGROUND AND OBJECTIVE: Perioperative chemotherapy (PC) with radical surgery represents the gold standard of treatment for resectable advanced gastric cancer (GC). The prognostic value of pathological tumor regression grade (TRG) induced by neoadjuvant chemotherapy (NACT) is not clearly established. This study aimed to investigate the correlation between TRG and survival in GC. METHODS: Patients affected by advanced GC undergoing PC and radical surgery were considered. TRG was assessed for each patient according to Becker's grading system. The correlation between TRG and survival was investigated. RESULTS: One-hundred patients were selected; 25 showed a good response (GR) (TRG 1a/1b), while 75 had a poor response (PR) (TRG 2/3) to NACT. GR patients showed better disease-free survival (DFS) (52 vs. 19 months, p < .001) and disease-specific survival (DSS) (57 vs. 25 months, p < .0001) when compared to PR patients. On univariate analysis, TRG, lymph node ratio (LNR), tumor size, grading, and post-neoadjuvant therapy TNM stage were significantly correlated with survival. On multivariate analysis, TRG, LNR and tumor size were independent prognostic factors for DFS and DSS. CONCLUSIONS: TRG, LNR, and tumor size are independent prognostic factors for DFS and DSS in patients with advanced GC undergoing NACT.