Assessing Unmet Information Needs of Breast Cancer Survivors: Exploratory Study of Online Health Forums Using Text Classification and Retrieval

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Background

Patient education materials given to breast cancer survivors may not be a good fit for their information needs. Needs may change over time, be forgotten, or be misreported, for a variety of reasons. An automated content analysis of survivors' postings to online health forums can identify expressed information needs over a span of time and be repeated regularly at low cost. Identifying these unmet needs can guide improvements to existing education materials and the creation of new resources.

Objective

The primary goals of this project are to assess the unmet information needs of breast cancer survivors from their own perspectives and to identify gaps between information needs and current education materials.

Methods

This approach employs computational methods for content modeling and supervised text classification to data from online health forums to identify explicit and implicit requests for health-related information. Potential gaps between needs and education materials are identified using techniques from information retrieval.

Results

We provide a new taxonomy for the classification of sentences in online health forum data. 260 postings from two online health forums were selected, yielding 4179 sentences for coding. After annotation of data and training alternative one-versus-others classifiers, a random forest-based approach achieved F1 scores from 66% (Other, dataset2) to 90% (Medical, dataset1) on the primary information types. 136 expressions of need were used to generate queries to indexed education materials. Upon examination of the best two pages retrieved for each query, 12% (17/136) of queries were found to have relevant content by all coders, and 33% (45/136) were judged to have relevant content by at least one.

Conclusions

Text from online health forums can be analyzed effectively using automated methods. Our analysis confirms that breast cancer survivors have many information needs that are not covered by the written documents they typically receive, as our results suggest that at most a third of breast cancer survivors’ questions would be addressed by the materials currently provided to them.

Related collections

Most cited references 22

Record: found
Abstract: found
Article: not found

Brief assessment of adult cancer patients' perceived needs: development and validation of the 34-item Supportive Care Needs Survey (SCNS-SF34).

Christophe Lecathelinais, Afaf Girgis, Allison Boyes (2009)

This study aimed to develop and validate a short version of the Supportive Care Needs Survey (SCNS) that would reduce respondent burden and could be used in routine cancer care, without compromising the psychometric properties of the original instrument. Secondary analyses of the data from two studies (n = 888 and 250) were undertaken. All 59 items of the original SCNS were assessed using psychometric analyses and evaluated for clinical utility. The 34 items retained were examined for internal consistency, ceiling and floor effects, known groups validity, convergent validity, sensitivity and readability. The 34-item instrument has five factors (psychological, health system and information, physical and daily living, patient care and support, and sexuality needs) identical to the original instrument, explaining 73% of the variance. Internal consistency was high with Cronbach's alpha coefficients for the five factors ranging from 0.86 to 0.96. Correlations of the 34-item short-form SCNS (SCNS-SF34) with three other measures of psychosocial well-being demonstrated convergent validity (r = 0.48-0.56). Kappa coefficients of at least 0.83 for each domain indicated almost perfect agreement between the 34-item and 59-item surveys to identify patients needing help. The 34-item SCNS maintained the psychometric properties of the original instrument and could be readily comprehended by people with seventh to eighth grade education. The SCNS-SF34 is a valid instrument for measuring cancer patients' perceived needs across a range of domains, and could be utilized as part of routine cancer care.

0 comments Cited 169 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Self-Reported Differences in Empowerment Between Lurkers and Posters in Online Patient Support Groups

Cornelia F. van Uden-Kraan, Constance Drossaert, Erik Taal … (2008)

Background Patients who visit online support groups benefit in various ways. Results of our earlier study indicated that participation in online support groups had a profound effect on the participants’ feelings of “being empowered.” However, most studies of online patient support groups have focused on the members of these groups who actively contribute by sending postings (posters). Thus far, little is known about the impact for “lurkers” (ie, those who do not actively participate by sending postings). Objective In the present study, we explored if lurkers in online patient support groups profit to the same extent as posters do. Methods We searched the Internet with the search engine Google to identify all Dutch online support groups for patients with breast cancer, fibromyalgia, and arthritis. Invitations to complete an online survey were sent out by the owners of 19 groups. In the online questionnaire, we asked questions about demographic and health characteristics, use of and satisfaction with the online support group, empowering processes, and empowering outcomes. The online questionnaire was completed by 528 individuals, of which 109 (21%) identified themselves as lurkers. Results Lurkers (mean age 47 years) were slightly older than active participants (mean age 43 years, P = .002), had a shorter disease history (time since diagnosis 3.7 years vs 5.4 years, P = .001), and reported lower mental well-being (SF 12 subscore 37.7 vs 40.5, P = .004). No significant differences were found in other demographic variables. Posters indicated visiting the online support groups significantly more often for social reasons, such as curiosity about how other members were doing, to enjoy themselves, as a part of their daily routine (all P < .001), and because other members expected them to be there (P = .003). Lurkers and posters did not differ in their information-related reasons for visiting the online support group. Lurkers were significantly less satisfied with the online support group compared to posters (P < .001). With regard to empowering processes such as “exchanging information” and “finding recognition,” lurkers scored significantly lower than posters. However, lurkers did not differ significantly from posters with regard to most empowering outcomes, such as “being better informed,” “feeling more confident in the relationship with their physician,” “improved acceptance of the disease,” “feeling more confident about the treatment,” “enhanced self-esteem,” and “increased optimism and control.” The exception was “enhanced social well-being,” which scored significantly lower for lurkers compared to posters (P < .001). Conclusion Our study revealed that participation in an online support group had the same profound effect on lurkers’ self-reported feelings of being empowered in several areas as it had on posters. Apparently, reading in itself is sufficient to profit from participation in an online patient support group.

0 comments Cited 82 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: not found
Article: not found

Latent dirichlet allocation

DM Blei, AY Ng, MI Jordan … (2003)

0 comments Cited 77 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Contributors

Susan McRoy:

Department of Electrical Engineering and Computer ScienceUniversity of Wisconsin-MilwaukeeCollege of Engineering & Applied SciencePO Box 784Milwaukee, WI, 53201United States1 414 229 66951 414 229 6958mcroy@uwm.edu

ORCID: http://orcid.org/0000-0003-4826-0947

Journal

Journal ID (nlm-ta): JMIR Cancer

Journal ID (iso-abbrev): JMIR Cancer

Journal ID (publisher-id): JC

Title: JMIR Cancer

Publisher: JMIR Publications (Toronto, Canada )

ISSN (Electronic): 2369-1999

Publication date Collection: Jan-Jun 2018

Publication date (Electronic): 15 May 2018

Volume: 4

Issue: 1

Electronic Location Identifier: e10

Affiliations

[1] ¹ Department of Electrical Engineering and Computer Science University of Wisconsin-Milwaukee Milwaukee, WI United States

[2] ² Mayo Clinic Rochester, MN United States

Author notes

Corresponding Author: Susan McRoy mcroy@ 123456uwm.edu

Author information

Susan McRoy http://orcid.org/0000-0003-4826-0947

Majid Rastegar-Mojarad http://orcid.org/0000-0001-6962-3554

Yanshan Wang http://orcid.org/0000-0003-4433-7839

Kathryn J Ruddy http://orcid.org/0000-0001-6298-332X

Tufia C Haddad http://orcid.org/0000-0001-8226-3581

Hongfang Liu http://orcid.org/0000-0003-2570-3741

Article

Publisher ID: v4i1e10

DOI: 10.2196/cancer.9050

PMC ID: 5974460

PubMed ID: 29764801

SO-VID: 66d9247a-61d8-4a6a-bba8-9c89b2f00f52

License:

This is an open-access article distributed under the terms of the Creative Commons Attribution License ( https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Cancer, is properly cited. The complete bibliographic information, a link to the original publication on http://cancer.jmir.org/, as well as this copyright and license information must be included.

History

Date received : 27 September 2017

Date revision requested : 29 November 2017

Date revision received : 23 January 2018

Date accepted : 22 April 2018

Comments

Comment on this article

scite_

Smart Citations

Citing PublicationsSupportingMentioningContrasting

View Citations

See how this article has been cited at scite.ai

scite shows how a scientific paper has been cited by providing the context of the citation, a classification describing whether it supports, mentions, or contrasts the cited claim, and a label indicating in which section the citation was made.

Cited by 11

See all cited by

Most referenced authors 319

See all reference authors

Submit your digital health research with an established publisher
- celebrating 25 years of open access