Studying gpt analyses of 4CE notes
This international 4CE project aims to assess the capabilities of Large Language Models (LLMs) in analyzing de-identified clinical notes of obese patients with a history of COVID-19, with tasks including generating codes, translations, trial eligibility, guideline evaluation, SOAP notes, referrals, and medication summaries.
A minimum of seven de-identified admission notes from each hospital participating in the study will be collected and submitted here. Clinicians will de-identify these admission notes so no personal identifiable information will be made available to the researchers before submission on this portal. Sites should also ensure that they have their DUA approved by their respective IRBs. The DUA can be found here.
Patients with below inclusion criteria at participating hospitals.
Patients aged 18 to 65, both male and female, with obesity and with active COVID or history of COVID.
Patients outside the age range, without obesity or COVID.