by A groundbreaking study conducted by researchers at the University of California, San Francisco (UCSF) indicates that Artificial Intelligence (AI) could potentially match the accuracy of human physicians in prioritizing patients based on their need for immediate medical attention in emergency departments.
The researchers analyzed anonymized records of 251,000 adult emergency department (ED) visits to assess the AI model’s ability to extract symptoms from patients’ clinical notes. They compared the AI analysis with the Emergency Severity Index (ESI), a widely used 1–5 scale that ED nurses employ during patient triage to allocate resources based on the severity of their condition.
The study, published on May 7 in JAMA Network Open, ensured the patients’ data remained de-identified throughout the research process. The researchers utilized UCSF’s secure generative AI platform, which boasts robust privacy protections, to access the data and evaluate it using the ChatGPT-4 large language model (LLM).
*Note:
1.Source: Coherent Market Insights, Public sources, Desk research
2.We have leveraged AI tools to mine information and compile it
