Publications by authors named "A Cagnina"
Article Synopsis
- The study assessed how well ChatGPT can help decide if high-risk non-ST-elevation acute coronary syndrome (NSTE-ACS) patients need invasive coronary angiography (ICA) based on clinical data and imaging findings.
- In a trial involving 86 patients, ChatGPT showed high accuracy at 86%, correctly advising against ICA for 19 patients and recommending it for 67, leading to significant findings in most cases.
- The results indicate ChatGPT could aid in decision-making to avoid unnecessary procedures, but more extensive studies are needed to truly evaluate AI's effectiveness in clinical settings.
Background: FFRangio and QFR are angiography-based technologies that have been validated in patients with stable coronary artery disease. No head-to-head comparison to invasive fractional flow reserve (FFR) has been reported to date in patients with acute coronary syndromes (ACS).
Methods: This study is a subset of a larger prospective multicenter, single-arm study that involved patients diagnosed with high-risk ACS in whom 30-70% stenosis was evaluated by FFR.
Use of large language models for evidence-based cardiovascular medicine.
Eur Heart J Digit Health
October 2023
Chat Generative Pre-trained Transformer (ChatGPT) is currently a trending topic worldwide triggering extensive debate about its predictive power, its potential uses, and its wider implications. Recent publications have demonstrated that ChatGPT can correctly answer questions from undergraduate exams such as the United States Medical Licensing Examination. We challenged it to answer questions from a more demanding, post-graduate exam-the European Exam in Core Cardiology (EECC), the final exam for the completion of specialty training in Cardiology in many countries.
View Article and Find Full Text PDF