Assessment of Appearance-related Questions About Breast Reconstruction Generated by Chat Generative Pre-trained Transformer
Background:. Previous studies have explored the ability of artificial intelligence (AI) tools based on large language models, such as Chat Generative Pre-Trained Transformer (ChatGPT), to answer patient questions about breast reconstruction. In this study, we assessed the quality of questions genera...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer
2025-03-01
|
| Series: | Plastic and Reconstructive Surgery, Global Open |
| Online Access: | http://journals.lww.com/prsgo/fulltext/10.1097/GOX.0000000000006625 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849393800123777024 |
|---|---|
| author | Xiomara T. Gonzalez, MSE Margaret S. Roubaud, MD Mark V. Schaverien, MD Rene D. Largo, MD Christopher S. Parham, MD Ashleigh M. Francis, MD Tzuan A. Chen, PhD Aubri S. Hoffman, PhD Ryan M. Dickey, MD Mia K. Markey, PhD Gregory P. Reece, MD |
| author_facet | Xiomara T. Gonzalez, MSE Margaret S. Roubaud, MD Mark V. Schaverien, MD Rene D. Largo, MD Christopher S. Parham, MD Ashleigh M. Francis, MD Tzuan A. Chen, PhD Aubri S. Hoffman, PhD Ryan M. Dickey, MD Mia K. Markey, PhD Gregory P. Reece, MD |
| author_sort | Xiomara T. Gonzalez, MSE |
| collection | DOAJ |
| description | Background:. Previous studies have explored the ability of artificial intelligence (AI) tools based on large language models, such as Chat Generative Pre-Trained Transformer (ChatGPT), to answer patient questions about breast reconstruction. In this study, we assessed the quality of questions generated by ChatGPT for breast reconstruction patients to ask their providers.
Methods:. ChatGPT was prompted to generate appearance-related questions representative of what patients might ask during breast reconstruction consultations. As a benchmark, a comparison group of questions from credible online sources was compiled. Blinded to the source, surgeons assessed the quality of questions in terms of their acceptability, contribution to the informed consent process, and contribution to the shared decision-making process. Surgeons were also asked to report their agreement on whether questions were generated by an AI tool.
Results:. Experienced reconstructive surgeons rated ChatGPT-generated questions about appearance-related outcomes of breast reconstruction as acceptable (15 of 16), likely to positively contribute to the informed consent process (15 of 16), and likely to positively contribute to the shared decision-making process (16 of 16). These ratings were comparable to those for benchmark questions. Surgeons did not readily recognize questions as being AI-generated. Differences in surgeon assessments were most pronounced regarding the perceived potential for the questions to contribute to the informed consent process.
Conclusions:. The quality of ChatGPT-generated questions related to appearance concerns is comparable to that of questions sourced from reputable online websites. Patients may benefit from discussion with their providers about best practices for using AI tools in preparation for consultations. |
| format | Article |
| id | doaj-art-a4ab6fc0e2774ffa9991e1e8d30701b5 |
| institution | Kabale University |
| issn | 2169-7574 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Wolters Kluwer |
| record_format | Article |
| series | Plastic and Reconstructive Surgery, Global Open |
| spelling | doaj-art-a4ab6fc0e2774ffa9991e1e8d30701b52025-08-20T03:40:17ZengWolters KluwerPlastic and Reconstructive Surgery, Global Open2169-75742025-03-01133e662510.1097/GOX.0000000000006625202503000-00074Assessment of Appearance-related Questions About Breast Reconstruction Generated by Chat Generative Pre-trained TransformerXiomara T. Gonzalez, MSE0Margaret S. Roubaud, MD1Mark V. Schaverien, MD2Rene D. Largo, MD3Christopher S. Parham, MD4Ashleigh M. Francis, MD5Tzuan A. Chen, PhD6Aubri S. Hoffman, PhD7Ryan M. Dickey, MD8Mia K. Markey, PhD9Gregory P. Reece, MD10From the * Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX† Department of Plastic Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX† Department of Plastic Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX† Department of Plastic Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX† Department of Plastic Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX† Department of Plastic Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX‡ Department of Psychological, Health, and Learning Sciences, HEALTH Research Institute, University of Houston, Houston, TX§ Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX† Department of Plastic Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX§ Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX† Department of Plastic Surgery, The University of Texas MD Anderson Cancer Center, Houston, TXBackground:. Previous studies have explored the ability of artificial intelligence (AI) tools based on large language models, such as Chat Generative Pre-Trained Transformer (ChatGPT), to answer patient questions about breast reconstruction. In this study, we assessed the quality of questions generated by ChatGPT for breast reconstruction patients to ask their providers. Methods:. ChatGPT was prompted to generate appearance-related questions representative of what patients might ask during breast reconstruction consultations. As a benchmark, a comparison group of questions from credible online sources was compiled. Blinded to the source, surgeons assessed the quality of questions in terms of their acceptability, contribution to the informed consent process, and contribution to the shared decision-making process. Surgeons were also asked to report their agreement on whether questions were generated by an AI tool. Results:. Experienced reconstructive surgeons rated ChatGPT-generated questions about appearance-related outcomes of breast reconstruction as acceptable (15 of 16), likely to positively contribute to the informed consent process (15 of 16), and likely to positively contribute to the shared decision-making process (16 of 16). These ratings were comparable to those for benchmark questions. Surgeons did not readily recognize questions as being AI-generated. Differences in surgeon assessments were most pronounced regarding the perceived potential for the questions to contribute to the informed consent process. Conclusions:. The quality of ChatGPT-generated questions related to appearance concerns is comparable to that of questions sourced from reputable online websites. Patients may benefit from discussion with their providers about best practices for using AI tools in preparation for consultations.http://journals.lww.com/prsgo/fulltext/10.1097/GOX.0000000000006625 |
| spellingShingle | Xiomara T. Gonzalez, MSE Margaret S. Roubaud, MD Mark V. Schaverien, MD Rene D. Largo, MD Christopher S. Parham, MD Ashleigh M. Francis, MD Tzuan A. Chen, PhD Aubri S. Hoffman, PhD Ryan M. Dickey, MD Mia K. Markey, PhD Gregory P. Reece, MD Assessment of Appearance-related Questions About Breast Reconstruction Generated by Chat Generative Pre-trained Transformer Plastic and Reconstructive Surgery, Global Open |
| title | Assessment of Appearance-related Questions About Breast Reconstruction Generated by Chat Generative Pre-trained Transformer |
| title_full | Assessment of Appearance-related Questions About Breast Reconstruction Generated by Chat Generative Pre-trained Transformer |
| title_fullStr | Assessment of Appearance-related Questions About Breast Reconstruction Generated by Chat Generative Pre-trained Transformer |
| title_full_unstemmed | Assessment of Appearance-related Questions About Breast Reconstruction Generated by Chat Generative Pre-trained Transformer |
| title_short | Assessment of Appearance-related Questions About Breast Reconstruction Generated by Chat Generative Pre-trained Transformer |
| title_sort | assessment of appearance related questions about breast reconstruction generated by chat generative pre trained transformer |
| url | http://journals.lww.com/prsgo/fulltext/10.1097/GOX.0000000000006625 |
| work_keys_str_mv | AT xiomaratgonzalezmse assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer AT margaretsroubaudmd assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer AT markvschaverienmd assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer AT renedlargomd assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer AT christophersparhammd assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer AT ashleighmfrancismd assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer AT tzuanachenphd assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer AT aubrishoffmanphd assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer AT ryanmdickeymd assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer AT miakmarkeyphd assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer AT gregorypreecemd assessmentofappearancerelatedquestionsaboutbreastreconstructiongeneratedbychatgenerativepretrainedtransformer |