RESUMO
INTRODUCTION AND OBJECTIVE: Generative artificial intelligence makes it possible to ask about medical pathologies in dialog boxes. Our objective was to analyze the quality of information about the most common urological pathologies provided by ChatGPT (OpenIA), BARD (Google), and Copilot (Microsoft). METHODS: We analyzed information on the following pathologies and their treatments as provided by AI: prostate cancer, kidney cancer, bladder cancer, urinary lithiasis, and benign prostatic hypertrophy (BPH). Questions in English and Spanish were posed in dialog boxes; the answers were collected and analyzed with DISCERN questionnaires and the overall appropriateness of the response. Surgical procedures were performed with an informed consent questionnaire. RESULTS: The responses from the three chatbots explained the pathology, detailed risk factors, and described treatments. The difference is that BARD and Copilot provide external information citations, which ChatGPT does not. The highest DISCERN scores, in absolute numbers, were obtained in Copilot; however, on the appropriacy scale it was noted that their responses were not the most appropriate. The best surgical treatment scores were obtained by BARD, followed by ChatGPT, and finally Copilot. CONCLUSIONS: The answers obtained from generative AI on urological diseases depended on the formulation of the question. The information provided had significant biases, depending on pathology, language, and above all, the dialog box consulted.
Assuntos
Idioma , Doenças Urológicas , Humanos , Inteligência Artificial , Inquéritos e Questionários , InternetRESUMO
INTRODUCTION AND OBJECTIVE: Next-generation imaging (NGI) tests, such as choline PET/CT and PSMA PET, have shown to increase sensitivity in the detection of nodal and metastatic disease in prostate cancer. However, their use implies an increase in diagnostic costs compared to conventional imaging (CI) tests such as CT and bone scan. The aim of our study was to determine which diagnostic pathway is more cost-effective in high-risk prostate cancer. MATERIAL AND METHOD: Cost-effectiveness analysis of the available imaging tests (CI, Choline/PSMA PET) for the staging of high-risk prostate cancer. Sensitivity and specificity were estimated based on published evidence, and costs were collected from the Management Department. In order to carry out a cost-effectiveness analysis, five diagnostic pathways were proposed estimating the accurate diagnoses. RESULTS: PSMA PET was the most accurate diagnostic option. The CI diagnostic workup was the most economical and CI+PSMA the most expensive. Analyzing the diagnostic cost-effectiveness ratio, CI+PSMA proved to be the most expensive (5627.30 per correct diagnosis) followed by PET PSMA (4987.11), choline (4599.84) and CI (4444.22). CONCLUSIONS: PSMA PET is the most accurate strategy in staging distant disease in patients with high-risk prostate cancer. Radiotracer uptake tests such as CI have been shown to be the most cost-effective option, followed by choline and PSMA.