ChatGPT4’s diagnostic accuracy in inpatient neurology: A retrospective cohort study
Sebastian Cano-Besquet, Tyler Rice-Canetto, Hadi Abou-El-Hassan, Simon Alarcon, Jason Zimmerman, Leo Issagholian, Nasser Salomon, Ivan Rojas, Joseph Dhahbi, Michael M Neeki · 2024
Read ChatGPT4’s diagnostic accuracy in inpatient neurology: A retrospective cohort study by Sebastian Cano-Besquet, Tyler Rice-Canetto, Hadi Abou-El-Hassan, Simon Alarcon, Jason Zimmerman, Leo Issagholian, Nasser Salomon, Ivan Rojas, Joseph Dhahbi, Michael M Neeki (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11699242.txt.
Description
Sebastian Cano-Besquet and nine colleagues published an AI study in two thousand twenty-four on ChatGPT-4 as a diagnostic helper in hospital neurology. The chatbot had beaten rivals on test questions, but real ward cases are messier. The team fed it records from a neurology consultation service in California.
Fifty-one consecutive patients were included. The model received chart data and produced first guesses, test plans, a final diagnosis, and a treatment plan for each. Raters scored how well its first guesses matched the consultants' final diagnoses on a short scale. Spread estimates came from resampling. The authors frame the work as a proof of concept rather than a verdict on clinical use.
Catalog record
| CREATOR | Sebastian Cano-Besquet, Tyler Rice-Canetto, Hadi Abou-El-Hassan, Simon Alarcon, Jason Zimmerman, Leo Issagholian, Nasser Salomon, Ivan Rojas, Joseph Dhahbi, Michael M Neeki |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |