Automated thematic analysis of health information technology (HIT) related incident reports
In this paper, the authors describe a method for exploring the feasibility of using Natural Language Processing (NLP) and Machine Learning (ML) techniques to analyze patient safety incident database reports for themes. We developed a novel thematic analysis strategy to automatically detect keywords...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hong Kong Bao Long Accounting & Secretarial Limited
2021-12-01
|
| Series: | Knowledge Management & E-Learning: An International Journal |
| Subjects: | |
| Online Access: | http://www.kmel-journal.org/ojs/index.php/online-publication/article/view/488 |
| _version_ | 1818138561303543808 |
|---|---|
| author | Yanyan Li Casper Shyr Elizabeth M. Borycki Andre W. Kushniruk |
| author_facet | Yanyan Li Casper Shyr Elizabeth M. Borycki Andre W. Kushniruk |
| author_sort | Yanyan Li |
| collection | DOAJ |
| description | In this paper, the authors describe a method for exploring the feasibility of using Natural Language Processing (NLP) and Machine Learning (ML) techniques to analyze patient safety incident database reports for themes. We developed a novel thematic analysis strategy to automatically detect keywords and latent themes that describe HIT-related patient safety incidents. The strategy was applied to patient safety reports to test the approach. The efforts by the automated strategy were compared to the efforts by analysts who manually reviewed and identified key words, topics, and themes for the same reports. The computer-based error themes were also compared to the human-determined themes for crosschecking. The manual thematic analysis took about 150 hours to complete on the patient safety reports. The semi-automated approach took only 10% of that time. 95% of the themes extracted from the automated method were aligned with the themes from the manual process. The findings underscore the utility of NLP and ML in identifying thematic patterns embedded in large numbers of unstructured data. The NLP-ML method therefore represents a valuable addition to the tools of detecting and understanding HIT-related errors.
|
| first_indexed | 2024-12-11T10:14:09Z |
| format | Article |
| id | doaj.art-277626f6aafa4a4fa5963c86ef47a054 |
| institution | Directory Open Access Journal |
| issn | 2073-7904 |
| language | English |
| last_indexed | 2024-12-11T10:14:09Z |
| publishDate | 2021-12-01 |
| publisher | Hong Kong Bao Long Accounting & Secretarial Limited |
| record_format | Article |
| series | Knowledge Management & E-Learning: An International Journal |
| spelling | doaj.art-277626f6aafa4a4fa5963c86ef47a0542022-12-22T01:11:39ZengHong Kong Bao Long Accounting & Secretarial LimitedKnowledge Management & E-Learning: An International Journal2073-79042021-12-0113440842010.34105/j.kmel.2021.13.022Automated thematic analysis of health information technology (HIT) related incident reportsYanyan Li0Casper Shyr1Elizabeth M. Borycki2https://orcid.org/0000-0003-0928-8867Andre W. Kushniruk3https://orcid.org/0000-0002-2557-9288University of Victoria, BC, CanadaUniversity of Victoria, BC, CanadaUniversity of Victoria, BC, CanadaUniversity of Victoria, BC, CanadaIn this paper, the authors describe a method for exploring the feasibility of using Natural Language Processing (NLP) and Machine Learning (ML) techniques to analyze patient safety incident database reports for themes. We developed a novel thematic analysis strategy to automatically detect keywords and latent themes that describe HIT-related patient safety incidents. The strategy was applied to patient safety reports to test the approach. The efforts by the automated strategy were compared to the efforts by analysts who manually reviewed and identified key words, topics, and themes for the same reports. The computer-based error themes were also compared to the human-determined themes for crosschecking. The manual thematic analysis took about 150 hours to complete on the patient safety reports. The semi-automated approach took only 10% of that time. 95% of the themes extracted from the automated method were aligned with the themes from the manual process. The findings underscore the utility of NLP and ML in identifying thematic patterns embedded in large numbers of unstructured data. The NLP-ML method therefore represents a valuable addition to the tools of detecting and understanding HIT-related errors. http://www.kmel-journal.org/ojs/index.php/online-publication/article/view/488patient safety incidents reportingnatural language processingmachine learningtext mining |
| spellingShingle | Yanyan Li Casper Shyr Elizabeth M. Borycki Andre W. Kushniruk Automated thematic analysis of health information technology (HIT) related incident reports Knowledge Management & E-Learning: An International Journal patient safety incidents reporting natural language processing machine learning text mining |
| title | Automated thematic analysis of health information technology (HIT) related incident reports |
| title_full | Automated thematic analysis of health information technology (HIT) related incident reports |
| title_fullStr | Automated thematic analysis of health information technology (HIT) related incident reports |
| title_full_unstemmed | Automated thematic analysis of health information technology (HIT) related incident reports |
| title_short | Automated thematic analysis of health information technology (HIT) related incident reports |
| title_sort | automated thematic analysis of health information technology hit related incident reports |
| topic | patient safety incidents reporting natural language processing machine learning text mining |
| url | http://www.kmel-journal.org/ojs/index.php/online-publication/article/view/488 |
| work_keys_str_mv | AT yanyanli automatedthematicanalysisofhealthinformationtechnologyhitrelatedincidentreports AT caspershyr automatedthematicanalysisofhealthinformationtechnologyhitrelatedincidentreports AT elizabethmborycki automatedthematicanalysisofhealthinformationtechnologyhitrelatedincidentreports AT andrewkushniruk automatedthematicanalysisofhealthinformationtechnologyhitrelatedincidentreports |