Home › Research › End-of-life care
Free-Text Responses in a Nationally Representative Experimental Survey about End-of-Life Care Choices: ChatGPT-4o-Assisted Qualitative Analytical Study
Elizabeth M. Goldberg, Mario Macis, Megan Bounds, Jonathan Gomez Picazo, Lauren Hersch Nicholas. JMIR Aging, 2025-09-22
Topic: Risk, prevention and care in population studies
We identified several key themes: surrogates more often chose comfort care for care recipients with dementia, particularly at advanced stages. They also strongly weighed the patients' perceived quality of life and functional status. Many reported making surrogate decisions based on their own lived experiences or values, rather than making decisions aligned with the patients' previously stated wishes. There was no significant difference between the AI and qualitative software's keyword counts. The most frequent keywords included "life" (2051/81,713, 2.51%), "quality" (903/81,713, 1.11%), and dementia (507/81,713, 0.62%). Overall, AI-generated themes closely aligned with aforementioned human-generated themes. Manual coding of the first 200 free-text responses required 4 hours, including codebook development. In contrast, ChatGPT-4o generated themes in <10 seconds using the predefined codebook. However, dataset preparation, output verification, iterative prompting, debugging, and validation required several weeks. Surrogates often base end-of-life decisions on dementia stage, perceived quality of life, and their own lived experiences, rather than patient preferences. Using an AI chatbot to perform qualitative analysis on free-text responses may help extend the work of qualitatively trained investigators, especially for large datasets such as free-text responses to large surveys.
Key findings
- We identified several key themes: surrogates more often chose comfort care for care recipients with dementia, particularly at advanced stages.
- They also strongly weighed the patients' perceived quality of life and functional status.
- Many reported making surrogate decisions based on their own lived experiences or values, rather than making decisions aligned with the patients' previously stated wishes.
- There was no significant difference between the AI and qualitative software's keyword counts.
- The most frequent keywords included "life" (2051/81,713, 2.51%), "quality" (903/81,713, 1.11%), and dementia (507/81,713, 0.62%).
Why it matters
This study of free-text survey responses found that surrogates more often chose comfort care for care recipients with dementia, particularly at advanced stages, and many made decisions based on their own lived experiences or values rather than the patients' previously stated wishes. It also found that an AI chatbot's themes closely aligned with human-generated themes, but this concerns research methods rather than treatment, cure, or prevention.
Study details
- Participants3,931
- Effect size2.51%; 1.11%; 0.62%
- Evidence strengthLow
How this study scored 46/100
Published in a peer-reviewed journal. Scored zero for study design and randomised / blinded because the record does not state it.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (JMIR Aging) |
| Journal's citation record | 0 / 4 | JMIR Aging: journal h-index 49 (OpenAlex, 2026-10-29) |
| Study design | 0 / 12 | No study design recorded — scores zero, not guessed (not stated in the record — scored 0) |
| Strength of evidence | 1 / 5 | Rated “low” in our summary |
| Peer-review validation | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 4 / 5 | 2025 — within 3 year(s) of the newest study here |
| Sample size | 3 / 4 | 3,931 participants |
| Effect reported | 2 / 3 | Effect reported as a number, without an interval or test |
| Studied in people | 3 / 3 | Studied in people (participant count stated) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 2 / 7 | Cited 5 times (OpenAlex, 2026-10-10) |
| Citations per year | 1 / 5 | 1.7 citations a year over 3 year(s) since 2025 |
| Impact for its field and year | 3 / 6 | Cited 4.2× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 0 / 6 | No other study in this library cites it |
| Still being cited | 1 / 4 | Cited 5 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 2 / 4 | Last-listed author Lauren Hersch Nicholas: h-index 26 (OpenAlex, whole career) |
| Institution's track record | 2 / 3 | Johns Hopkins University: institution h-index 2,306 (OpenAlex) |
| Multi-centre collaboration | 1 / 3 | OpenAlex lists 2 institution(s) in 1 country |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 41160733) |
| Free to read | 2 / 2 | Free to read |
| Total | 46 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. Check the citation against the original before you use it.
APA 7th
Goldberg, E. M., Macis, M., Bounds, M., Picazo, J. G., & Nicholas, L. H. (2025). Free-Text Responses in a Nationally Representative Experimental Survey about End-of-Life Care Choices: ChatGPT-4o-Assisted Qualitative Analytical Study. JMIR Aging. https://doi.org/10.2196/76335
Vancouver
Goldberg EM, Macis M, Bounds M, Picazo JG, Nicholas LH. Free-Text Responses in a Nationally Representative Experimental Survey about End-of-Life Care Choices: ChatGPT-4o-Assisted Qualitative Analytical Study. JMIR Aging. 2025. doi:10.2196/76335. PMID: 41160733.
BibTeX
@article{goldberg2025-41160733,
author = {Goldberg, Elizabeth M. and Macis, Mario and Bounds, Megan and Picazo, Jonathan Gomez and Nicholas, Lauren Hersch},
title = {{Free-Text Responses in a Nationally Representative Experimental Survey about End-of-Life Care Choices: ChatGPT-4o-Assisted Qualitative Analytical Study}},
journal = {JMIR Aging},
year = {2025},
doi = {10.2196/76335},
pmid = {41160733},
url = {https://doi.org/10.2196/76335}
}