Tag: GPT-4o

In a comparative study of one hundred cardiac surgery records, ChatGPT substantially outperformed the domain-specific OpenBioLLM model in generating personalized ...

A blinded study of 113 urodynamic reports found that artificial intelligence models achieved perfect numerical extraction and substantial agreement with ...

An AI-assisted analysis of 2,025 skin-containing figures from 14 open-access orthopedic journals finds light skin in 65.6% of images and ...

A zero-shot evaluation of GPT-4o found strong performance for chemical incident extraction from news articles, while radiological events were too ...

OntoGPT, an AI tool that grounds a large language model in scientific ontologies, agreed with human reviewers on 65 percent ...

Researchers have developed CAMV, a framework that automatically extracts contextual information from datasets and generates coordinated multi-view visualizations to help ...

A new framework combines large language models, game theory, and Dialectical Behavior Therapy to let a chatbot strategically select the ...

A four-week Ghanaian pilot study found that supervised GPT-4o-supported science learning was associated with large improvements in achievement and conceptual ...

A quasi-experimental study of 383 first-year medical students found that voluntary, single-session practice with a GPT-4o-based virtual patient did not ...

NASA Ames researchers built an LLM-based aviation decision-support system that routes natural language queries through nine validated expert models, achieving ...