Increasing Realism and Variety of Virtual Patient Dialogues for Prenatal Counseling Education Through a Novel Application of ChatGPT: Exploratory Observational Study
Open accessPublished version of a preprint
The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Background: Using virtual patients, facilitated by natural language processing, provides a valuable educational experience for learners. Generating a large, varied sample of realistic and appropriate responses for virtual patients is challenging. Artificial intelligence (AI) programs can be a viable source for these responses, but their utility for this purpose has not been explored. Objective: In this study, we explored the effectiveness of generative AI (ChatGPT) in developing realistic virtual standardized patient dialogues to teach prenatal counseling skills. Methods: ChatGPT was prompted to generate a list of common areas of concern and questions that families expecting preterm delivery at 24 weeks gestation might ask during prenatal counseling. ChatGPT was then prompted to generate 2 role-plays with dialogues between a parent expecting a potential preterm delivery at 24 weeks and their counseling physician using each of the example questions. The prompt was repeated for 2 unique role-plays: one parent was characterized as anxious and the other as having low trust in the medical system. Role-play scripts were exported verbatim and independently reviewed by 2 neonatologists with experience in prenatal counseling, using a scale of 1-5 on realism, appropriateness, and utility for virtual standardized patient responses. Results: ChatGPT generated 7 areas of concern, with 35 example questions used to generate role-plays. The 35 role-play transcripts generated 176 unique parent responses (median 5, IQR 4-6, per role-play) with 268 unique sentences. Expert review identified 117 (65%) of the 176 responses as indicating an emotion, either directly or indirectly. Approximately half (98/176, 56%) of the responses had 2 or more sentences, and half (88/176, 50%) included at least 1 question. More than half (104/176, 58%) of the responses from role-played parent characters described a feeling, such as being scared, worried, or concerned. The role-plays of parents with low trust in the medical system generated many unique sentences (n=50). Most of the sentences in the responses were found to be reasonably realistic (214/268, 80%), appropriate for variable prenatal counseling conversation paths (233/268, 87%), and usable without more than a minimal modification in a virtual patient program (169/268, 63%). Conclusions: Generative AI programs, such as ChatGPT, may provide a viable source of training materials to expand virtual patient programs, with careful attention to the concerns and questions of patients and families. Given the potential for unrealistic or inappropriate statements and questions, an expert should review AI chat outputs before deploying them in an educational program.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115
Kung, T. H., Cheatham, M., ChatGPT, Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., et al. (2022) · doi:10.1101/2022.12.19.22283643 · Cited by 4,115
A large annotated corpus for learning natural language inference
Bowman, S. R., Angeli, G., Potts, C., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1075 · Cited by 3,377
Generalizing from a Few Examples: A Survey on Few-shot Learning
Wang, Y., Yao, Q., Kwok, J. T., & Ni, L. M. (2021) · ACM Computing Surveys · doi:10.1145/3386252 · Cited by 3,165 · cited 1×
“Following this pretraining is “one-shot” learning, a rapid task-specific learning [11].”
BackgroundCook, D. A., Hatala, R., Brydges, R., Zendejas, B., Szostek, J. H., Wang, A. T., Erwin, P. J., & Hamstra, S. J. (2011) · JAMA · doi:10.1001/jama.2011.1234 · Cited by 2,170
A critical review of simulation‐based medical education research: 2003–2009
McGaghie, W. C., Issenberg, S. B., Petrusa, E. R., & Scalese, R. J. (2010) · Medical Education · doi:10.1111/j.1365-2923.2009.03547.x · Cited by 1,733
SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation
Cer, D., Diab, M., Agirre, E., Lopez-Gazpio, I., & Specia, L. (2017) · Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017) · doi:10.18653/v1/s17-2001 · Cited by 1,562
Efficient Learning of Sparse Representations with an Energy-Based Model
Ranzato, M., Poultney, C., Chopra, S., & LeCun, Y. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0147 · Cited by 1,106
Semi-supervised Sequence Learning
Dai, A. M., & Le, Q. V. (2015) · arXiv · doi:10.48550/arxiv.1511.01432 · Cited by 994 · cited 1×
“ChatGPT decodes user prompts to create relevant responses using autoregressive language modeling [13].”
MethodNeural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2015) · arXiv · doi:10.48550/arxiv.1508.07909 · Cited by 950
Research works printed but not linked: 26
- 10.1080/0142159x.2023.2259069 · DOI
- 10.1097/sih.0000000000000730 · DOI
- 10.1097/sih.0000000000000742 · DOI
- 10.1186/s12912-021-00740-x · DOI
- 10.2196/games.9611 · DOI
- 10.3115/v1/w14-4012 · DOI · Paper page
- Dai, A, ArXiv. Preprint posted online on Nov 4, 2015
- Dockrell, J, 2002, Bishop, Dorothy V. M. & Leonard, Laurence B. (eds), Speech and language impairments in children: causes, characteristics, intervention and outcome. Hove, UK. Psychology Press, 2000. Pp. xiii+305, 701
- 10.11613/bm.2012.031 · DOI · Paper page
- 10.1007/s10916-023-01925-4 · DOI · Paper page
- 10.4300/jgme-d-22-00088.1 · DOI
- 10.1080/10872981.2021.1946896 · DOI
- 10.1016/j.profnurs.2023.05.007 · DOI
- 10.1016/j.socscimed.2018.02.013 · DOI · Paper page
- 10.1080/10810730.2019.1669742 · DOI
- 10.1108/09526860410515918 · DOI
- 10.4236/ojog.2014.411094 · DOI
- 10.1055/s-0035-1551672 · doi:10.1055/s-0035-1551672
- 10.1016/j.pec.2019.03.016 · DOI
- 10.1111/apa.16690 · DOI
- 10.1016/j.pec.2021.10.033 · DOI
- 10.1055/s-0041-1730430 · doi:10.1055/s-0041-1730430
- 10.1055/s-0041-1742186 · doi:10.1055/s-0041-1742186
- 10.1093/pch/pxy158 · DOI
- 10.1016/j.jpeds.2017.10.067 · DOI
- 10.1111/apa.12716 · doi:10.1111/apa.12716
Cited by
Large language models in patient education: a scoping review of applications in medicine
Aydin, S., Karabacak, M., Vlachos, V., & Margetis, K. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1477898 · Cited by 288
A large language model digital patient system enhances ophthalmology history taking skills
Luo, M.-J., Bi, S., Pang, J., Liu, L., Tsui, C.-K., Lai, Y., Chen, W., Yang, Y., Xu, K., Zhao, L., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01841-6 · Cited by 39
“31 demonstratetheuseofLLMsto generate authentic patient-clinician dialogs, while Cook et al. 32,33 and McKell et al. 34 further supported their potential for enhancing medical education.”
Thomae, A. V., Witt, C. M., & Barth, J. (2024) · JMIR Medical Education · doi:10.2196/50545 · Cited by 36
Assessing ChatGPT’s capability as a new age standardized patient: qualitative study
Cross, J., Kayalackakom, T., Robinson, R. E., Vaughans, A., Sebastian, R., Hood, R., Lewis, C., Devaraju, S., Honnavar, P., Naik, S., et al. (2025) · JMIR Medical Education · doi:10.2196/63353 · Cited by 33
“The significance of prompt engineering when using LLMs as virtual SPs, or in developing related materials, is also supported by other studies [28,30-33].”
Factors influencing patients’ engagement with ChatGPT for accessing health-related information
Alanezi, F. (2024) · Critical Public Health · doi:10.1080/09581596.2024.2348164 · Cited by 26
“Recent studies (Gray et al., 2024; Kumar, 2023) found that patients are more engaged when they perceive AI applications like ChatGPT as reliable sources of medical information and vice versa.”
Jacobs, C., Johnson, H., Tan, N., Brownlie, K., Joiner, R., & Thompson, T. (2025) · JMIR Medical Education · doi:10.2196/70766 · Cited by 20
“Simulated virtual patients (VPs) have shown promise in prenatal counseling education, where ChatGPT-gener-ated dialogues increased the realism and variety of patient interactions while maintaining clinical accuracy [10].”
Quantum leap in medical mentorship: exploring ChatGPT’s transition from textbooks to terabytes
Chokkakula, S., Chong, S., Yang, B., Jiang, H., Yu, J., Han, R., Attitalla, I. H., Yin, C., & Zhang, S. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1517981 · Cited by 12
Synthetic Participants Generated by Large Language Models: A Systematic Literature Review
Kuric, E., Demcak, P., & Krajcovic, M. (2026) · doi:10.21203/rs.3.rs-9057643/v1 · Cited by 2
Metadata
- Authors
- Gray, M., Baird, A., Sawyer, T., James, J., DeBroux, T., Bartlett, M., Krick, J., & Umoren, R.
- Venue
- JMIR Medical Education
- Publisher
- JMIR Publications Inc.
- Published
- 2024-02-01
- Volume
- 10
- Pages
- e50705
- ISSN
- 2369-3762 (ISSN-L)
- OpenAlex
- W4389577325
- Cited by
- 36
- References
- 21
- FWCI
- 1.25
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.