Leveraging AI to Drive Timely Improvements in Patient Experience Feedback: Algorithm Validation
Abstract BackgroundUnderstanding and improving patient care is pivotal for health care providers. With increasing volumes of the Friends and Family Test (FFT) data in England, manual analysis of this patient feedback poses challenges for many health care organizations. This un...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2025-07-01
|
| Series: | JMIR Medical Informatics |
| Online Access: | https://medinform.jmir.org/2025/1/e60900 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850101402161905664 |
|---|---|
| author | Mustafa Khanbhai Catalina Carenzo Sarindi Aryasinghe David Manton Erik Mayer |
| author_facet | Mustafa Khanbhai Catalina Carenzo Sarindi Aryasinghe David Manton Erik Mayer |
| author_sort | Mustafa Khanbhai |
| collection | DOAJ |
| description |
Abstract
BackgroundUnderstanding and improving patient care is pivotal for health care providers. With increasing volumes of the Friends and Family Test (FFT) data in England, manual analysis of this patient feedback poses challenges for many health care organizations. This underscores the importance of automated text analysis, particularly in predicting sentiments and themes in real time.
ObjectiveLeveraging machine learning and natural language processing, this study explores the utility of a supervised algorithm to systematically test and refine the algorithm’s cross-contextual performance in diverse health care settings, addressing variations in population characteristics, geographical locations, and care settings, ultimately driving improvements based on patient feedback.
MethodsThe text analytics algorithm initially developed in a large acute trust in London was further tested in 9 health care organizations with diverse care settings across England. These trusts varied in technical capacity and resource, population demographics, and FFT free text datasets. Testing and validation of the algorithm were performed, including manual coding of a subset of retrospective comments. Technical infrastructure, including coding environments and packages for algorithm testing and deployment, was optimized. The algorithm was iteratively trained using bag of words from anonymized data, tailored to accommodate contextual variations, and tested for change in algorithm performance while simultaneously rectifying issues identified.
ResultsThe algorithm demonstrated satisfactory overall accuracy (>75%) in predicting themes and sentiments embedded within free-text responses across a variety of care settings and population demographics. While the algorithm yielded strong and reusable models in relatively stable environments, such as adult inpatient care settings, the initial accuracy was notably lower in organizations providing services such as pediatrics and mental health. However, the accuracy of our algorithm significantly improved when individual trust coding templates were applied. Thematic saturation was reached after the fifth organization was recruited, and no further coding was required for the last 4 organizations. Subsequently, a framework and pipeline for deployment of the algorithm were developed to provide a standardized approach for implementation and analysis of FFT free text, ensuring ease of use.
ConclusionsThis study represents a significant step forward in leveraging free-text FFT data for valuable insights in diverse health care settings through the testing and development of a robust supervised learning text analytics algorithm. The disparity in some care settings was anticipated, given that the lexicon and phraseology used was inherently different from those prevalent in adult inpatient care (where the algorithm was developed). However, these challenges were addressed with further coding and testing. This approach enhanced the accuracy and reliability of the algorithm, encouraged inter- and intraorganizational collaboration, and shared learning. |
| format | Article |
| id | doaj-art-154c4cd93a2a4e9d96bed1769a25f41f |
| institution | DOAJ |
| issn | 2291-9694 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Medical Informatics |
| spelling | doaj-art-154c4cd93a2a4e9d96bed1769a25f41f2025-08-20T02:40:02ZengJMIR PublicationsJMIR Medical Informatics2291-96942025-07-0113e60900e6090010.2196/60900Leveraging AI to Drive Timely Improvements in Patient Experience Feedback: Algorithm ValidationMustafa Khanbhaihttp://orcid.org/0000-0002-4434-1785Catalina Carenzohttp://orcid.org/0009-0006-5772-8029Sarindi Aryasinghehttp://orcid.org/0009-0000-2435-8638David Mantonhttp://orcid.org/0000-0002-6490-7272Erik Mayerhttp://orcid.org/0000-0002-5509-4580 Abstract BackgroundUnderstanding and improving patient care is pivotal for health care providers. With increasing volumes of the Friends and Family Test (FFT) data in England, manual analysis of this patient feedback poses challenges for many health care organizations. This underscores the importance of automated text analysis, particularly in predicting sentiments and themes in real time. ObjectiveLeveraging machine learning and natural language processing, this study explores the utility of a supervised algorithm to systematically test and refine the algorithm’s cross-contextual performance in diverse health care settings, addressing variations in population characteristics, geographical locations, and care settings, ultimately driving improvements based on patient feedback. MethodsThe text analytics algorithm initially developed in a large acute trust in London was further tested in 9 health care organizations with diverse care settings across England. These trusts varied in technical capacity and resource, population demographics, and FFT free text datasets. Testing and validation of the algorithm were performed, including manual coding of a subset of retrospective comments. Technical infrastructure, including coding environments and packages for algorithm testing and deployment, was optimized. The algorithm was iteratively trained using bag of words from anonymized data, tailored to accommodate contextual variations, and tested for change in algorithm performance while simultaneously rectifying issues identified. ResultsThe algorithm demonstrated satisfactory overall accuracy (>75%) in predicting themes and sentiments embedded within free-text responses across a variety of care settings and population demographics. While the algorithm yielded strong and reusable models in relatively stable environments, such as adult inpatient care settings, the initial accuracy was notably lower in organizations providing services such as pediatrics and mental health. However, the accuracy of our algorithm significantly improved when individual trust coding templates were applied. Thematic saturation was reached after the fifth organization was recruited, and no further coding was required for the last 4 organizations. Subsequently, a framework and pipeline for deployment of the algorithm were developed to provide a standardized approach for implementation and analysis of FFT free text, ensuring ease of use. ConclusionsThis study represents a significant step forward in leveraging free-text FFT data for valuable insights in diverse health care settings through the testing and development of a robust supervised learning text analytics algorithm. The disparity in some care settings was anticipated, given that the lexicon and phraseology used was inherently different from those prevalent in adult inpatient care (where the algorithm was developed). However, these challenges were addressed with further coding and testing. This approach enhanced the accuracy and reliability of the algorithm, encouraged inter- and intraorganizational collaboration, and shared learning.https://medinform.jmir.org/2025/1/e60900 |
| spellingShingle | Mustafa Khanbhai Catalina Carenzo Sarindi Aryasinghe David Manton Erik Mayer Leveraging AI to Drive Timely Improvements in Patient Experience Feedback: Algorithm Validation JMIR Medical Informatics |
| title | Leveraging AI to Drive Timely Improvements in Patient Experience Feedback: Algorithm Validation |
| title_full | Leveraging AI to Drive Timely Improvements in Patient Experience Feedback: Algorithm Validation |
| title_fullStr | Leveraging AI to Drive Timely Improvements in Patient Experience Feedback: Algorithm Validation |
| title_full_unstemmed | Leveraging AI to Drive Timely Improvements in Patient Experience Feedback: Algorithm Validation |
| title_short | Leveraging AI to Drive Timely Improvements in Patient Experience Feedback: Algorithm Validation |
| title_sort | leveraging ai to drive timely improvements in patient experience feedback algorithm validation |
| url | https://medinform.jmir.org/2025/1/e60900 |
| work_keys_str_mv | AT mustafakhanbhai leveragingaitodrivetimelyimprovementsinpatientexperiencefeedbackalgorithmvalidation AT catalinacarenzo leveragingaitodrivetimelyimprovementsinpatientexperiencefeedbackalgorithmvalidation AT sarindiaryasinghe leveragingaitodrivetimelyimprovementsinpatientexperiencefeedbackalgorithmvalidation AT davidmanton leveragingaitodrivetimelyimprovementsinpatientexperiencefeedbackalgorithmvalidation AT erikmayer leveragingaitodrivetimelyimprovementsinpatientexperiencefeedbackalgorithmvalidation |