Evaluating the Pediatric Behavior Guidance of Students Based on Actual Clinical Transcripts Scored by Faculty and Large Language Models: Pilot Comparative Study
Ishreen Kaur Dhillon, Gabriel Keng Yan Lee, Shijia Hu · 2026
Read Evaluating the Pediatric Behavior Guidance of Students Based on Actual Clinical Transcripts Scored by Faculty and Large Language Models: Pilot Comparative Study by Ishreen Kaur Dhillon, Gabriel Keng Yan Lee, Shijia Hu (2026) 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/PMC13263019.txt.
Description
Ishreen Kaur Dhillon and colleagues test faster ways to grade dental students' handling of child patients in a 2026 journal article. Personal feedback helps students guide children's behavior, but watching full videos takes too long. The Singapore team compared scores from written transcripts of 40 recorded sessions with video scores, and also let two versions of ChatGPT score the transcripts.
Scoring a transcript took about 12 minutes on average, versus 73 minutes of video. Transcript scores agreed well with video scores. The language models agreed only moderately with the human scorer and were inconsistent, giving the same score on all repeats in few cases. The authors back transcripts for teaching, but say the models need work first.
Catalog record
| CREATOR | Ishreen Kaur Dhillon, Gabriel Keng Yan Lee, Shijia Hu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 19944 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |