Your browser doesn't support javascript.
loading
Professionalism and clinical short answer question marking with machine learning.
Lam, Antoinette; Lam, Lydia; Blacketer, Charlotte; Parnis, Roger; Franke, Kyle; Wagner, Morganne; Wang, David; Tan, Yiran; Oakden-Rayner, Lauren; Gallagher, Steve; Perry, Seth W; Licinio, Julio; Symonds, Ian; Thomas, Josephine; Duggan, Paul; Bacchi, Stephen.
Afiliación
  • Lam A; University of Adelaide, Adelaide, South Australia, Australia.
  • Lam L; University of Adelaide, Adelaide, South Australia, Australia.
  • Blacketer C; University of Adelaide, Adelaide, South Australia, Australia.
  • Parnis R; Royal Adelaide Hospital, Adelaide, South Australia, Australia.
  • Franke K; University of Adelaide, Adelaide, South Australia, Australia.
  • Wagner M; Royal Darwin Hospital, Darwin, Northern Territory, Australia.
  • Wang D; University of Adelaide, Adelaide, South Australia, Australia.
  • Tan Y; State University of New York (SUNY) Upstate Medical University, Syracuse, New York, USA.
  • Oakden-Rayner L; University of Otago, Dunedin, New Zealand.
  • Gallagher S; University of Adelaide, Adelaide, South Australia, Australia.
  • Perry SW; Royal Adelaide Hospital, Adelaide, South Australia, Australia.
  • Licinio J; University of Adelaide, Adelaide, South Australia, Australia.
  • Symonds I; Royal Adelaide Hospital, Adelaide, South Australia, Australia.
  • Thomas J; University of Otago, Dunedin, New Zealand.
  • Duggan P; State University of New York (SUNY) Upstate Medical University, Syracuse, New York, USA.
  • Bacchi S; State University of New York (SUNY) Upstate Medical University, Syracuse, New York, USA.
Intern Med J ; 52(7): 1268-1271, 2022 07.
Article en En | MEDLINE | ID: mdl-35879236
Machine learning may assist in medical student evaluation. This study involved scoring short answer questions administered at three centres. Bidirectional encoder representations from transformers were particularly effective for professionalism question scoring (accuracy ranging from 41.6% to 92.5%). In the scoring of 3-mark professionalism questions, as compared with clinical questions, machine learning had a lower classification accuracy (P < 0.05). The role of machine learning in medical professionalism evaluation warrants further investigation.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Estudiantes de Medicina / Profesionalismo Límite: Humans Idioma: En Revista: Intern Med J Asunto de la revista: MEDICINA INTERNA Año: 2022 Tipo del documento: Article País de afiliación: Australia Pais de publicación: Australia
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Estudiantes de Medicina / Profesionalismo Límite: Humans Idioma: En Revista: Intern Med J Asunto de la revista: MEDICINA INTERNA Año: 2022 Tipo del documento: Article País de afiliación: Australia Pais de publicación: Australia