Recommending Education Materials for Diabetic Questions Using Information Retrieval Approaches

Yuqun Zeng, Xusheng Liu, Yanshan Wang, Feichen Shen, Sijia Liu, Majid Rastegar-Mojarad, Liwei Wang, Hongfang D Liu

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

BACKGROUND: Self-management is crucial to diabetes care and providing expert-vetted content for answering patients' questions is crucial in facilitating patient self-management.

OBJECTIVE: The aim is to investigate the use of information retrieval techniques in recommending patient education materials for diabetic questions of patients.

METHODS: We compared two retrieval algorithms, one based on Latent Dirichlet Allocation topic modeling (topic modeling-based model) and one based on semantic group (semantic group-based model), with the baseline retrieval models, vector space model (VSM), in recommending diabetic patient education materials to diabetic questions posted on the TuDiabetes forum. The evaluation was based on a gold standard dataset consisting of 50 randomly selected diabetic questions where the relevancy of diabetic education materials to the questions was manually assigned by two experts. The performance was assessed using precision of top-ranked documents.

RESULTS: We retrieved 7510 diabetic questions on the forum and 144 diabetic patient educational materials from the patient education database at Mayo Clinic. The mapping rate of words in each corpus mapped to the Unified Medical Language System (UMLS) was significantly different (P<.001). The topic modeling-based model outperformed the other retrieval algorithms. For example, for the top-retrieved document, the precision of the topic modeling-based, semantic group-based, and VSM models was 67.0%, 62.8%, and 54.3%, respectively.

CONCLUSIONS: This study demonstrated that topic modeling can mitigate the vocabulary difference and it achieved the best performance in recommending education materials for answering patients' questions. One direction for future work is to assess the generalizability of our findings and to extend our study to other disease areas, other patient education material resources, and online forums.

Original languageEnglish (US)
Pages (from-to)e342
JournalJournal of Medical Internet Research
Volume19
Issue number10
DOIs
StatePublished - Oct 16 2017
Externally publishedYes

Fingerprint

Information Storage and Retrieval
Patient Education
Education
Semantics
Space Simulation
Self Care
Unified Medical Language System
Vocabulary
Databases

Keywords

  • education materials
  • information retrieval
  • patients
  • questions
  • recommendation

ASJC Scopus subject areas

  • Health Informatics

Cite this

Recommending Education Materials for Diabetic Questions Using Information Retrieval Approaches. / Zeng, Yuqun; Liu, Xusheng; Wang, Yanshan; Shen, Feichen; Liu, Sijia; Rastegar-Mojarad, Majid; Wang, Liwei; Liu, Hongfang D.

In: Journal of Medical Internet Research, Vol. 19, No. 10, 16.10.2017, p. e342.

Research output: Contribution to journalArticle

Zeng, Yuqun ; Liu, Xusheng ; Wang, Yanshan ; Shen, Feichen ; Liu, Sijia ; Rastegar-Mojarad, Majid ; Wang, Liwei ; Liu, Hongfang D. / Recommending Education Materials for Diabetic Questions Using Information Retrieval Approaches. In: Journal of Medical Internet Research. 2017 ; Vol. 19, No. 10. pp. e342.
@article{9e6264cd632b435c98cde8e9588b7216,
title = "Recommending Education Materials for Diabetic Questions Using Information Retrieval Approaches",
abstract = "BACKGROUND: Self-management is crucial to diabetes care and providing expert-vetted content for answering patients' questions is crucial in facilitating patient self-management.OBJECTIVE: The aim is to investigate the use of information retrieval techniques in recommending patient education materials for diabetic questions of patients.METHODS: We compared two retrieval algorithms, one based on Latent Dirichlet Allocation topic modeling (topic modeling-based model) and one based on semantic group (semantic group-based model), with the baseline retrieval models, vector space model (VSM), in recommending diabetic patient education materials to diabetic questions posted on the TuDiabetes forum. The evaluation was based on a gold standard dataset consisting of 50 randomly selected diabetic questions where the relevancy of diabetic education materials to the questions was manually assigned by two experts. The performance was assessed using precision of top-ranked documents.RESULTS: We retrieved 7510 diabetic questions on the forum and 144 diabetic patient educational materials from the patient education database at Mayo Clinic. The mapping rate of words in each corpus mapped to the Unified Medical Language System (UMLS) was significantly different (P<.001). The topic modeling-based model outperformed the other retrieval algorithms. For example, for the top-retrieved document, the precision of the topic modeling-based, semantic group-based, and VSM models was 67.0{\%}, 62.8{\%}, and 54.3{\%}, respectively.CONCLUSIONS: This study demonstrated that topic modeling can mitigate the vocabulary difference and it achieved the best performance in recommending education materials for answering patients' questions. One direction for future work is to assess the generalizability of our findings and to extend our study to other disease areas, other patient education material resources, and online forums.",
keywords = "education materials, information retrieval, patients, questions, recommendation",
author = "Yuqun Zeng and Xusheng Liu and Yanshan Wang and Feichen Shen and Sijia Liu and Majid Rastegar-Mojarad and Liwei Wang and Liu, {Hongfang D}",
year = "2017",
month = "10",
day = "16",
doi = "10.2196/jmir.7754",
language = "English (US)",
volume = "19",
pages = "e342",
journal = "Journal of Medical Internet Research",
issn = "1439-4456",
publisher = "Journal of medical Internet Research",
number = "10",

}

TY - JOUR

T1 - Recommending Education Materials for Diabetic Questions Using Information Retrieval Approaches

AU - Zeng, Yuqun

AU - Liu, Xusheng

AU - Wang, Yanshan

AU - Shen, Feichen

AU - Liu, Sijia

AU - Rastegar-Mojarad, Majid

AU - Wang, Liwei

AU - Liu, Hongfang D

PY - 2017/10/16

Y1 - 2017/10/16

N2 - BACKGROUND: Self-management is crucial to diabetes care and providing expert-vetted content for answering patients' questions is crucial in facilitating patient self-management.OBJECTIVE: The aim is to investigate the use of information retrieval techniques in recommending patient education materials for diabetic questions of patients.METHODS: We compared two retrieval algorithms, one based on Latent Dirichlet Allocation topic modeling (topic modeling-based model) and one based on semantic group (semantic group-based model), with the baseline retrieval models, vector space model (VSM), in recommending diabetic patient education materials to diabetic questions posted on the TuDiabetes forum. The evaluation was based on a gold standard dataset consisting of 50 randomly selected diabetic questions where the relevancy of diabetic education materials to the questions was manually assigned by two experts. The performance was assessed using precision of top-ranked documents.RESULTS: We retrieved 7510 diabetic questions on the forum and 144 diabetic patient educational materials from the patient education database at Mayo Clinic. The mapping rate of words in each corpus mapped to the Unified Medical Language System (UMLS) was significantly different (P<.001). The topic modeling-based model outperformed the other retrieval algorithms. For example, for the top-retrieved document, the precision of the topic modeling-based, semantic group-based, and VSM models was 67.0%, 62.8%, and 54.3%, respectively.CONCLUSIONS: This study demonstrated that topic modeling can mitigate the vocabulary difference and it achieved the best performance in recommending education materials for answering patients' questions. One direction for future work is to assess the generalizability of our findings and to extend our study to other disease areas, other patient education material resources, and online forums.

AB - BACKGROUND: Self-management is crucial to diabetes care and providing expert-vetted content for answering patients' questions is crucial in facilitating patient self-management.OBJECTIVE: The aim is to investigate the use of information retrieval techniques in recommending patient education materials for diabetic questions of patients.METHODS: We compared two retrieval algorithms, one based on Latent Dirichlet Allocation topic modeling (topic modeling-based model) and one based on semantic group (semantic group-based model), with the baseline retrieval models, vector space model (VSM), in recommending diabetic patient education materials to diabetic questions posted on the TuDiabetes forum. The evaluation was based on a gold standard dataset consisting of 50 randomly selected diabetic questions where the relevancy of diabetic education materials to the questions was manually assigned by two experts. The performance was assessed using precision of top-ranked documents.RESULTS: We retrieved 7510 diabetic questions on the forum and 144 diabetic patient educational materials from the patient education database at Mayo Clinic. The mapping rate of words in each corpus mapped to the Unified Medical Language System (UMLS) was significantly different (P<.001). The topic modeling-based model outperformed the other retrieval algorithms. For example, for the top-retrieved document, the precision of the topic modeling-based, semantic group-based, and VSM models was 67.0%, 62.8%, and 54.3%, respectively.CONCLUSIONS: This study demonstrated that topic modeling can mitigate the vocabulary difference and it achieved the best performance in recommending education materials for answering patients' questions. One direction for future work is to assess the generalizability of our findings and to extend our study to other disease areas, other patient education material resources, and online forums.

KW - education materials

KW - information retrieval

KW - patients

KW - questions

KW - recommendation

UR - http://www.scopus.com/inward/record.url?scp=85042753919&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042753919&partnerID=8YFLogxK

U2 - 10.2196/jmir.7754

DO - 10.2196/jmir.7754

M3 - Article

C2 - 29038097

AN - SCOPUS:85042753919

VL - 19

SP - e342

JO - Journal of Medical Internet Research

JF - Journal of Medical Internet Research

SN - 1439-4456

IS - 10

ER -