Development and testing of a text-mining approach to analyse patients’ comments on their experiences of colorectal cancer care
Background: Quality of cancer care may greatly impact upon patients’ health-related quality of life (HRQoL). Free-text responses to patient-reported outcome measures (PROMs) provide rich data but analysis is time and resource-intensive. This study developed and tested a learning-based text-mining ap...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Published: |
BMJ Publishing Group
2015
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/32437/ |
| _version_ | 1848794406315884544 |
|---|---|
| author | Wagland, Richard Recio Saucedo, Alejandra Simon, Michael Bracher, Michael Hunt, Katherine Foster, Claire Downing, Amy Glaser, Adam W. Corner, Jessica |
| author_facet | Wagland, Richard Recio Saucedo, Alejandra Simon, Michael Bracher, Michael Hunt, Katherine Foster, Claire Downing, Amy Glaser, Adam W. Corner, Jessica |
| author_sort | Wagland, Richard |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Background: Quality of cancer care may greatly impact upon patients’ health-related quality of life (HRQoL). Free-text responses to patient-reported outcome measures (PROMs) provide rich data but analysis is time and resource-intensive. This study developed and tested a learning-based text-mining approach to facilitate analysis of patients’ experiences of care and develop an explanatory model illustrating impact upon HRQoL.
Methods: Respondents to a population-based survey of colorectal cancer survivors provided free-text comments regarding their experience of living with and beyond cancer. An existing coding framework was tested and adapted, which informed learning-based text mining of the data. Machine-learning algorithms were trained to identify comments relating to patients’ specific experiences of service quality, which were verified by manual qualitative analysis. Comparisons between coded retrieved comments and a HRQoL measure (EQ5D) were explored.
Results: The survey response rate was 63.3% (21,802/34,467), of which 25.8% (n=5634) participants provided free-text comments. Of retrieved comments on experiences of care (n=1688), over half (n=1045, 62%) described positive care experiences. Most negative experiences concerned a lack of post-treatment care (n=191, 11% of retrieved comments), and insufficient information concerning self-management strategies (n=135, 8%) or treatment side effects (n=160, 9%). Associations existed between HRQoL scores and coded algorithm-retrieved comments. Analysis indicated that the mechanism by which service quality impacted upon HRQoL was the extent to which services prevented or alleviated challenges associated with disease and treatment burdens.
Conclusions: Learning-based text mining techniques were found useful and practical tools to identify specific free-text comments within a large dataset, facilitating resource-efficient qualitative analysis. This method should be considered for future PROM analysis to inform policy and practice. Study findings indicated that perceived care quality directly impacts upon HRQoL. |
| first_indexed | 2025-11-14T19:15:41Z |
| format | Article |
| id | nottingham-32437 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:15:41Z |
| publishDate | 2015 |
| publisher | BMJ Publishing Group |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-324372020-05-04T17:18:38Z https://eprints.nottingham.ac.uk/32437/ Development and testing of a text-mining approach to analyse patients’ comments on their experiences of colorectal cancer care Wagland, Richard Recio Saucedo, Alejandra Simon, Michael Bracher, Michael Hunt, Katherine Foster, Claire Downing, Amy Glaser, Adam W. Corner, Jessica RC 254 Neoplasms. Tumors. Oncology (including Cancer) RT Nursing Background: Quality of cancer care may greatly impact upon patients’ health-related quality of life (HRQoL). Free-text responses to patient-reported outcome measures (PROMs) provide rich data but analysis is time and resource-intensive. This study developed and tested a learning-based text-mining approach to facilitate analysis of patients’ experiences of care and develop an explanatory model illustrating impact upon HRQoL. Methods: Respondents to a population-based survey of colorectal cancer survivors provided free-text comments regarding their experience of living with and beyond cancer. An existing coding framework was tested and adapted, which informed learning-based text mining of the data. Machine-learning algorithms were trained to identify comments relating to patients’ specific experiences of service quality, which were verified by manual qualitative analysis. Comparisons between coded retrieved comments and a HRQoL measure (EQ5D) were explored. Results: The survey response rate was 63.3% (21,802/34,467), of which 25.8% (n=5634) participants provided free-text comments. Of retrieved comments on experiences of care (n=1688), over half (n=1045, 62%) described positive care experiences. Most negative experiences concerned a lack of post-treatment care (n=191, 11% of retrieved comments), and insufficient information concerning self-management strategies (n=135, 8%) or treatment side effects (n=160, 9%). Associations existed between HRQoL scores and coded algorithm-retrieved comments. Analysis indicated that the mechanism by which service quality impacted upon HRQoL was the extent to which services prevented or alleviated challenges associated with disease and treatment burdens. Conclusions: Learning-based text mining techniques were found useful and practical tools to identify specific free-text comments within a large dataset, facilitating resource-efficient qualitative analysis. This method should be considered for future PROM analysis to inform policy and practice. Study findings indicated that perceived care quality directly impacts upon HRQoL. BMJ Publishing Group 2015-10-28 Article PeerReviewed Wagland, Richard, Recio Saucedo, Alejandra, Simon, Michael, Bracher, Michael, Hunt, Katherine, Foster, Claire, Downing, Amy, Glaser, Adam W. and Corner, Jessica (2015) Development and testing of a text-mining approach to analyse patients’ comments on their experiences of colorectal cancer care. BMJ Quality & Safety . pp. 1-26. ISSN 2044-5423 text-mining PROMs quality of life colorectal cancer machine learning machine learning algorithms thematic analysis thematic content analysis qualitative methods http://qualitysafety.bmj.com/content/early/2015/10/28/bmjqs-2015-004063 doi:10.1136/bmjqs-2015-004063 doi:10.1136/bmjqs-2015-004063 |
| spellingShingle | RC 254 Neoplasms. Tumors. Oncology (including Cancer) RT Nursing text-mining PROMs quality of life colorectal cancer machine learning machine learning algorithms thematic analysis thematic content analysis qualitative methods Wagland, Richard Recio Saucedo, Alejandra Simon, Michael Bracher, Michael Hunt, Katherine Foster, Claire Downing, Amy Glaser, Adam W. Corner, Jessica Development and testing of a text-mining approach to analyse patients’ comments on their experiences of colorectal cancer care |
| title | Development and testing of a text-mining approach to analyse patients’ comments on their experiences of colorectal cancer care |
| title_full | Development and testing of a text-mining approach to analyse patients’ comments on their experiences of colorectal cancer care |
| title_fullStr | Development and testing of a text-mining approach to analyse patients’ comments on their experiences of colorectal cancer care |
| title_full_unstemmed | Development and testing of a text-mining approach to analyse patients’ comments on their experiences of colorectal cancer care |
| title_short | Development and testing of a text-mining approach to analyse patients’ comments on their experiences of colorectal cancer care |
| title_sort | development and testing of a text-mining approach to analyse patients’ comments on their experiences of colorectal cancer care |
| topic | RC 254 Neoplasms. Tumors. Oncology (including Cancer) RT Nursing text-mining PROMs quality of life colorectal cancer machine learning machine learning algorithms thematic analysis thematic content analysis qualitative methods |
| url | https://eprints.nottingham.ac.uk/32437/ https://eprints.nottingham.ac.uk/32437/ https://eprints.nottingham.ac.uk/32437/ |