Literature DB >> 28864104

Classifying patient portal messages using Convolutional Neural Networks.

Lina Sulieman1, David Gilmore2, Christi French2, Robert M Cronin3, Gretchen Purcell Jackson4, Matthew Russell2, Daniel Fabbri5.   

Abstract

OBJECTIVE: Patients communicate with healthcare providers via secure messaging in patient portals. As patient portal adoption increases, growing messaging volumes may overwhelm providers. Prior research has demonstrated promise in automating classification of patient portal messages into communication types to support message triage or answering. This paper examines if using semantic features and word context improves portal message classification.
MATERIALS AND METHODS: Portal messages were classified into the following categories: informational, medical, social, and logistical. We constructed features from portal messages including bag of words, bag of phrases, graph representations, and word embeddings. We trained one-versus-all random forest and logistic regression classifiers, and convolutional neural network (CNN) with a softmax output. We evaluated each classifier's performance using Area Under the Curve (AUC).
RESULTS: Representing the messages using bag of words, the random forest detected informational, medical, social, and logistical communications in patient portal messages with AUCs: 0.803, 0.884, 0.828, and 0.928, respectively. Graph representations of messages outperformed simpler features with AUCs: 0.837, 0.914, 0.846, 0.884 for informational, medical, social, and logistical communication, respectively. Representing words with Word2Vec embeddings, and mapping features using a CNN had the best performance with AUCs: 0.908 for informational, 0.917 for medical, 0.935 for social, and 0.943 for logistical categories. DISCUSSION AND
CONCLUSION: Word2Vec and graph representations improved the accuracy of classifying portal messages compared to features that lacked semantic information such as bag of words, and bag of phrases. Furthermore, using Word2Vec along with a CNN model, which provide a higher order representation, improved the classification of portal messages.
Copyright © 2017 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Convolutional Neural Network; Patient portals; Text mining; Word embedding; Word2Vec

Mesh:

Year:  2017        PMID: 28864104     DOI: 10.1016/j.jbi.2017.08.014

Source DB:  PubMed          Journal:  J Biomed Inform        ISSN: 1532-0464            Impact factor:   6.317


  15 in total

1.  A systematic literature review of machine learning in online personal health data.

Authors:  Zhijun Yin; Lina M Sulieman; Bradley A Malin
Journal:  J Am Med Inform Assoc       Date:  2019-06-01       Impact factor: 4.497

2.  Why Patient Portal Messages Indicate Risk of Readmission for Patients with Ischemic Heart Disease.

Authors:  Lina Sulieman; Zhijun Yin; Bradley A Malin
Journal:  AMIA Annu Symp Proc       Date:  2020-03-04

3.  Applying Natural Language Processing Neural Network Architectures to Augment Appointment Request Review of Self-Referred Patients to an Academic Medical Center.

Authors:  Christopher A Aakre
Journal:  AMIA Annu Symp Proc       Date:  2022-05-23

4.  An Analysis of Electronic Health Record Work to Manage Asynchronous Clinical Messages among Breast Cancer Care Teams.

Authors:  Bryan D Steitz; Kim M Unertl; Mia A Levy
Journal:  Appl Clin Inform       Date:  2021-09-15       Impact factor: 2.762

5.  Extracting Multiple Worries From Breast Cancer Patient Blogs Using Multilabel Classification With the Natural Language Processing Model Bidirectional Encoder Representations From Transformers: Infodemiology Study of Blogs.

Authors:  Tomomi Watanabe; Shuntaro Yada; Eiji Aramaki; Hiroshi Yajima; Hayato Kizaki; Satoko Hori
Journal:  JMIR Cancer       Date:  2022-06-03

6.  Automating the Classification of Complexity of Medical Decision-Making in Patient-Provider Messaging in a Patient Portal.

Authors:  Lina Sulieman; Jamie R Robinson; Gretchen P Jackson
Journal:  J Surg Res       Date:  2020-06-19       Impact factor: 2.192

7.  Detecting Hypoglycemia Incidents Reported in Patients' Secure Messages: Using Cost-Sensitive Learning and Oversampling to Reduce Data Imbalance.

Authors:  Jinying Chen; John Lalor; Weisong Liu; Emily Druhl; Edgard Granillo; Varsha G Vimalananda; Hong Yu
Journal:  J Med Internet Res       Date:  2019-03-11       Impact factor: 5.428

8.  Evaluation of clustering and topic modeling methods over health-related tweets and emails.

Authors:  Juan Antonio Lossio-Ventura; Sergio Gonzales; Juandiego Morzan; Hugo Alatrista-Salas; Tina Hernandez-Boussard; Jiang Bian
Journal:  Artif Intell Med       Date:  2021-05-07       Impact factor: 7.011

9.  Generating contextual embeddings for emergency department chief complaints.

Authors:  David Chang; Woo Suk Hong; Richard Andrew Taylor
Journal:  JAMIA Open       Date:  2020-07-15

10.  Using word embeddings to expand terminology of dietary supplements on clinical notes.

Authors:  Yadan Fan; Serguei Pakhomov; Reed McEwan; Wendi Zhao; Elizabeth Lindemann; Rui Zhang
Journal:  JAMIA Open       Date:  2019-03-28
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.