Table 1.
Degree | Position | Years in position | Role | NLP experience? | SUS score | |
---|---|---|---|---|---|---|
Group 1: Initial model trained with 10 documents | ||||||
p1 | MD PhD | Assistant Professor | <5 | Clinician, Researcher | Yes; current and past projects | 75 |
p2 | MD | Faculty Researcher | 5–10 | Clinician, Researcher | No; using in future project | 55 |
p3 | MD | Faculty Researcher | <5 | Clinician | No | 90 |
p4 | MD | Fellow | <5 | Clinician | No | 77.5 |
Group 2: Initial model trained with 30 documents | ||||||
p5 | MD | Resident Physician | <5 | Clinician | No | 67.5 |
p6 | MD | Fellow | <5 | Clinician, Researcher | No | 77.5 |
p7 | MD | Resident Physician | <5 | Clinician | No | 85 |
p8 | MD | Resident Physician | <5 | Clinician | No | 52.5 |
p9a | MD MAS | Physician | 5–10 | Clinician, Researcher | Currently involved in a project | 55 |
We obtained the System Usability Scale scores24 using a post-study questionnaire.
ap9 faced technical difficulties during the study, which may have influenced perceived usability.