A Novel Approach for Mixed-Methods Research Using Large Language Models : A Report Using Patients' Perspectives on Barriers to Arthroplasty
© 2024 The Authors. ACR Open Rheumatology published by Wiley Periodicals LLC on behalf of American College of Rheumatology..
OBJECTIVE: Mixed-methods research is valuable in health care to gain insights into patient perceptions. However, analyzing textual data from interviews can be time-consuming and require multiple analysts for investigator triangulation. This study aims to explore a novel approach to investigator triangulation in mixed-methods research by employing a large language model (LLM) for analyzing data from patient interviews.
METHODS: This study compared the thematic analysis and survey generation performed by human investigators and ChatGPT-4, which uses GPT-4 as its backbone model, using data from an existing study that explored patient perceptions of barriers to arthroplasty. The human- and ChatGPT-4-generated themes and surveys were compared and evaluated based on their representation of salient themes from a predetermined topic guide.
RESULTS: ChatGPT-4 generated analogous dominant themes and a comprehensive corresponding survey as the human investigators but in significantly less time. The survey questions generated by ChatGPT-4 were less precise than those developed by human investigators. The mixed-methods flowchart proposes integrating LLMs and human investigators as a supplementary tool for the preliminary thematic analysis of qualitative data and survey generation.
CONCLUSION: By utilizing a combination of LLMs and human investigators through investigator triangulation, researchers may be able to conduct more efficient mixed-methods research to better understand patient perspectives. Ethical and qualitative implications of using LLMs should be considered.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - year:2024 |
---|---|
Enthalten in: |
ACR open rheumatology - (2024) vom: 07. März |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Mannstadt, Insa [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Revised 07.03.2024 published: Print-Electronic Citation Status Publisher |
---|
doi: |
10.1002/acr2.11662 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM369439163 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM369439163 | ||
003 | DE-627 | ||
005 | 20240308233243.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240308s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1002/acr2.11662 |2 doi | |
028 | 5 | 2 | |a pubmed24n1320.xml |
035 | |a (DE-627)NLM369439163 | ||
035 | |a (NLM)38454175 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Mannstadt, Insa |e verfasserin |4 aut | |
245 | 1 | 2 | |a A Novel Approach for Mixed-Methods Research Using Large Language Models |b A Report Using Patients' Perspectives on Barriers to Arthroplasty |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 07.03.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status Publisher | ||
520 | |a © 2024 The Authors. ACR Open Rheumatology published by Wiley Periodicals LLC on behalf of American College of Rheumatology. | ||
520 | |a OBJECTIVE: Mixed-methods research is valuable in health care to gain insights into patient perceptions. However, analyzing textual data from interviews can be time-consuming and require multiple analysts for investigator triangulation. This study aims to explore a novel approach to investigator triangulation in mixed-methods research by employing a large language model (LLM) for analyzing data from patient interviews | ||
520 | |a METHODS: This study compared the thematic analysis and survey generation performed by human investigators and ChatGPT-4, which uses GPT-4 as its backbone model, using data from an existing study that explored patient perceptions of barriers to arthroplasty. The human- and ChatGPT-4-generated themes and surveys were compared and evaluated based on their representation of salient themes from a predetermined topic guide | ||
520 | |a RESULTS: ChatGPT-4 generated analogous dominant themes and a comprehensive corresponding survey as the human investigators but in significantly less time. The survey questions generated by ChatGPT-4 were less precise than those developed by human investigators. The mixed-methods flowchart proposes integrating LLMs and human investigators as a supplementary tool for the preliminary thematic analysis of qualitative data and survey generation | ||
520 | |a CONCLUSION: By utilizing a combination of LLMs and human investigators through investigator triangulation, researchers may be able to conduct more efficient mixed-methods research to better understand patient perspectives. Ethical and qualitative implications of using LLMs should be considered | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Goodman, Susan M |e verfasserin |4 aut | |
700 | 1 | |a Rajan, Mangala |e verfasserin |4 aut | |
700 | 1 | |a Young, Sarah R |e verfasserin |4 aut | |
700 | 1 | |a Wang, Fei |e verfasserin |4 aut | |
700 | 1 | |a Navarro-Millán, Iris |e verfasserin |4 aut | |
700 | 1 | |a Mehta, Bella |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t ACR open rheumatology |d 2019 |g (2024) vom: 07. März |w (DE-627)NLM295459263 |x 2578-5745 |7 nnns |
773 | 1 | 8 | |g year:2024 |g day:07 |g month:03 |
856 | 4 | 0 | |u http://dx.doi.org/10.1002/acr2.11662 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |j 2024 |b 07 |c 03 |