Back

Research Design Protocol: Assessing the Impact of Using ChatGPT in Radiology Reporting in an Emergency Setting in Egypt

Hamouda, N.; Ibrahim, M. K.; Jabal, M. S.

2023-07-03 radiology and imaging
10.1101/2023.06.28.23291928 medRxiv
Show abstract

This research design protocol outlines a study conducted in Egypt as an example of a developing country with limited resources. The objective is to assess the impact of using ChatGPT, a language model, in radiology reporting in the context of an emergency setting where reporting is traditionally done manually. The study aims to evaluate the effectiveness of ChatGPT in helping format structured reports, drawing impressions from the reports, and improving the efficiency of communication between radiologists and treating clinicians. A standardized survey will be utilized to compare the differences between the older subjective reporting format and ChatGPT-assisted reports.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.