Justin F. Rousseau

Jul 23, 2024 | nature.com | Qiao Jin |Fangyuan Chen |Yiliang Zhou |Justin F. Rousseau |Marc Landsman |Sally Baxter | +5 more

AbstractRecent studies indicate that Generative Pre-trained Transformer 4 with Vision (GPT-4V) outperforms human physicians in medical challenge tasks. However, these evaluations primarily focused on the accuracy of multi-choice questions alone.

Aug 24, 2023 | nature.com | Zhaoyi Sun |Jordan G. Nestor |Ali Soroush |Pierre Elias |Justin F. Rousseau |Chunhua Weng | +1 more

AbstractRecent advances in large language models (LLMs) have demonstrated remarkable successes in zero- and few-shot performance on various downstream tasks, paving the way for applications in high-stakes domains. In this study, we systematically examine the capabilities and limitations of LLMs, specifically GPT-3.5 and ChatGPT, in performing zero-shot medical evidence summarization across six clinical domains.

May 23, 2023 | nature.com | Yifan Peng |Justin F. Rousseau

Evidence-based medicine (EBM) requires the retrieval and ranking of relevant evidence by epistemological strength, to identify the most appropriate evidence to inform guidelines and policies, with a preference for robust evidence from randomized clinical trials (RCTs), systematic reviews, and meta-analyses.