Cargando…
Learning Outcomes and Their Relatedness Under Curriculum Drift
A typical medical curriculum is organized as a hierarchy of learning outcomes (LOs), each LO is a short text that describes a medical concept. Machine learning models have been applied to predict relatedness between LOs. These models are trained on examples of LO-relationships annotated by experts....
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7334708/ http://dx.doi.org/10.1007/978-3-030-52240-7_39 |
_version_ | 1783553985687322624 |
---|---|
author | Mondal, Sneha Dhamecha, Tejas I. Pathak, Smriti Mendoza, Red Wijayarathna, Gayathri K. Gagnon, Paul Carlstedt-Duke, Jan |
author_facet | Mondal, Sneha Dhamecha, Tejas I. Pathak, Smriti Mendoza, Red Wijayarathna, Gayathri K. Gagnon, Paul Carlstedt-Duke, Jan |
author_sort | Mondal, Sneha |
collection | PubMed |
description | A typical medical curriculum is organized as a hierarchy of learning outcomes (LOs), each LO is a short text that describes a medical concept. Machine learning models have been applied to predict relatedness between LOs. These models are trained on examples of LO-relationships annotated by experts. However, medical curricula are periodically reviewed and revised, resulting in changes to the structure and content of LOs. This work addresses the problem of model adaptation under curriculum drift. First, we propose heuristics to generate reliable annotations for the revised curriculum, thus eliminating dependence on expert annotations. Second, starting with a model pre-trained on the old curriculum, we inject a task-specific transformation layer to capture nuances of the revised curriculum. Our approach makes significant progress towards reaching human-level performance. |
format | Online Article Text |
id | pubmed-7334708 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
record_format | MEDLINE/PubMed |
spelling | pubmed-73347082020-07-06 Learning Outcomes and Their Relatedness Under Curriculum Drift Mondal, Sneha Dhamecha, Tejas I. Pathak, Smriti Mendoza, Red Wijayarathna, Gayathri K. Gagnon, Paul Carlstedt-Duke, Jan Artificial Intelligence in Education Article A typical medical curriculum is organized as a hierarchy of learning outcomes (LOs), each LO is a short text that describes a medical concept. Machine learning models have been applied to predict relatedness between LOs. These models are trained on examples of LO-relationships annotated by experts. However, medical curricula are periodically reviewed and revised, resulting in changes to the structure and content of LOs. This work addresses the problem of model adaptation under curriculum drift. First, we propose heuristics to generate reliable annotations for the revised curriculum, thus eliminating dependence on expert annotations. Second, starting with a model pre-trained on the old curriculum, we inject a task-specific transformation layer to capture nuances of the revised curriculum. Our approach makes significant progress towards reaching human-level performance. 2020-06-10 /pmc/articles/PMC7334708/ http://dx.doi.org/10.1007/978-3-030-52240-7_39 Text en © Springer Nature Switzerland AG 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic. |
spellingShingle | Article Mondal, Sneha Dhamecha, Tejas I. Pathak, Smriti Mendoza, Red Wijayarathna, Gayathri K. Gagnon, Paul Carlstedt-Duke, Jan Learning Outcomes and Their Relatedness Under Curriculum Drift |
title | Learning Outcomes and Their Relatedness Under Curriculum Drift |
title_full | Learning Outcomes and Their Relatedness Under Curriculum Drift |
title_fullStr | Learning Outcomes and Their Relatedness Under Curriculum Drift |
title_full_unstemmed | Learning Outcomes and Their Relatedness Under Curriculum Drift |
title_short | Learning Outcomes and Their Relatedness Under Curriculum Drift |
title_sort | learning outcomes and their relatedness under curriculum drift |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7334708/ http://dx.doi.org/10.1007/978-3-030-52240-7_39 |
work_keys_str_mv | AT mondalsneha learningoutcomesandtheirrelatednessundercurriculumdrift AT dhamechatejasi learningoutcomesandtheirrelatednessundercurriculumdrift AT pathaksmriti learningoutcomesandtheirrelatednessundercurriculumdrift AT mendozared learningoutcomesandtheirrelatednessundercurriculumdrift AT wijayarathnagayathrik learningoutcomesandtheirrelatednessundercurriculumdrift AT gagnonpaul learningoutcomesandtheirrelatednessundercurriculumdrift AT carlstedtdukejan learningoutcomesandtheirrelatednessundercurriculumdrift |