2021
DOI: 10.1136/bmjhci-2020-100274
|View full text |Cite
|
Sign up to set email alerts
|

Categorising patient concerns using natural language processing techniques

Abstract: ObjectivesPatient feedback is critical to identify and resolve patient safety and experience issues in healthcare systems. However, large volumes of unstructured text data can pose problems for manual (human) analysis. This study reports the results of using a semiautomated, computational topic-modelling approach to analyse a corpus of patient feedback.MethodsPatient concerns were received by Alberta Health Services between 2011 and 2018 (n=76 163), regarding 806 care facilities in 163 municipalities, includin… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1
1

Relationship

1
6

Authors

Journals

citations
Cited by 11 publications
(6 citation statements)
references
References 43 publications
0
6
0
Order By: Relevance
“…35 That said, the generalization of digital health records at the hospital level and the development of artificial intelligence algorithms applied to electronic medical records could create a pathway to automated clinical prediction models in the near future. 36,37…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…35 That said, the generalization of digital health records at the hospital level and the development of artificial intelligence algorithms applied to electronic medical records could create a pathway to automated clinical prediction models in the near future. 36,37…”
Section: Discussionmentioning
confidence: 99%
“…While this option remains possible, it would also require more detailed clinical information than is available in administrative claims-based data . That said, the generalization of digital health records at the hospital level and the development of artificial intelligence algorithms applied to electronic medical records could create a pathway to automated clinical prediction models in the near future …”
Section: Discussionmentioning
confidence: 99%
“…Many patient concerns were categorized into multiple topics. Some were more specific versions of categories from the existing framework (e.g., communication issues causing delays), while others were novel (e.g., smoking in inappropriate settings) [ 27 ].…”
Section: Resultsmentioning
confidence: 99%
“…Percent agreement between the reviewers was measured, and disagreements were resolved during a consensus meeting. Recognizing that this is a very labour-intensive process, our team has explored the use of natural language processing to analyze patient concerns data [ 27 ]. This second method is quite advantageous as it can be done in real-time.…”
Section: Methodsmentioning
confidence: 99%
“…Studies cite a range of critical themes in negative online reviews: discordant expectations (education, support, and promises) and sub-optimal communication and quality of care (management, organization, staff, and equipment) [ 12 , 60 , 61 ]. These were only partly reflected in our findings.…”
Section: Discussionmentioning
confidence: 99%