Literature DB >> 35751571

Classifying unstructured electronic consult messages to understand primary care physician specialty information needs.

Xiyu Ding1, Michael Barnett2,3, Ateev Mehrotra4,5, Delphine S Tuot6,7, Danielle S Bitterman8,9, Timothy A Miller10,11.   

Abstract

OBJECTIVE: Electronic consultation (eConsult) content reflects important information about referring clinician needs across an organization, but is challenging to extract. The objective of this work was to develop machine learning models for classifying eConsult questions for question type and question content. Another objective of this work was to investigate the ability to solve this task with constrained expert time resources.
MATERIALS AND METHODS: Our data source is the San Francisco Health Network eConsult system, with over 700 000 deidentified questions from the years 2008-2017, from gastroenterology, urology, and neurology specialties. We develop classifiers based on Bidirectional Encoder Representations from Transformers, experimenting with multitask learning to learn when information can be shared across classifiers. We produce learning curves to understand when we may be able to reduce the amount of human labeling required.
RESULTS: Multitask learning shows benefits only in the neurology-urology pair where they shared substantial similarities in the distribution of question types. Continued pretraining of models in new domains is highly effective. In the neurology-urology pair, near-peak performance is achieved with only 10% of the urology training data given all of the neurology data. DISCUSSION: Sharing information across classifier types shows little benefit, whereas sharing classifier components across specialties can help if they are similar in the balance of procedural versus cognitive patient care.
CONCLUSION: We can accurately classify eConsult content with enough labeled data, but only in special cases do methods for reducing labeling effort apply. Future work should explore new learning paradigms to further reduce labeling effort.
© The Author(s) 2022. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  electronic consultations; machine learning; natural language processing; specialty care

Mesh:

Year:  2022        PMID: 35751571      PMCID: PMC9382391          DOI: 10.1093/jamia/ocac092

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   7.942


  7 in total

1.  Practice profile. A safety-net system gains efficiencies through 'eReferrals' to specialists.

Authors:  Alice Hm Chen; Margot B Kushel; Kevin Grumbach; Hal F Yee
Journal:  Health Aff (Millwood)       Date:  2010-05       Impact factor: 6.301

2.  Los Angeles Safety-Net Program eConsult System Was Rapidly Adopted And Decreased Wait Times To See Specialists.

Authors:  Michael L Barnett; Hal F Yee; Ateev Mehrotra; Paul Giboney
Journal:  Health Aff (Millwood)       Date:  2017-03-01       Impact factor: 6.301

3.  eReferral--a new model for integrated care.

Authors:  Alice Hm Chen; Elizabeth J Murphy; Hal F Yee
Journal:  N Engl J Med       Date:  2013-06-27       Impact factor: 91.245

4.  Automatically classifying question types for consumer health questions.

Authors:  Kirk Roberts; Halil Kilicoglu; Marcelo Fiszman; Dina Demner-Fushman
Journal:  AMIA Annu Symp Proc       Date:  2014-11-14

5.  Combining Open-domain and Biomedical Knowledge for Topic Recognition in Consumer Health Questions.

Authors:  Yassine Mrabet; Halil Kilicoglu; Kirk Roberts; Dina Demner-Fushman
Journal:  AMIA Annu Symp Proc       Date:  2017-02-10

6.  MT-clinical BERT: scaling clinical information extraction with multitask learning.

Authors:  Andriy Mulyar; Ozlem Uzuner; Bridget McInnes
Journal:  J Am Med Inform Assoc       Date:  2021-09-18       Impact factor: 7.942

7.  Semantic annotation of consumer health questions.

Authors:  Halil Kilicoglu; Asma Ben Abacha; Yassine Mrabet; Sonya E Shooshan; Laritza Rodriguez; Kate Masterton; Dina Demner-Fushman
Journal:  BMC Bioinformatics       Date:  2018-02-06       Impact factor: 3.169

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.