Heart-to-heart with ChatGPT: the impact of patients consulting AI for cardiovascular health advice
Objectives The advent of conversational artificial intelligence (AI) systems employing large language models such as ChatGPT has sparked public, professional and academic debates on the capabilities of such technologies. This mixed-methods study sets out to review and systematically explore the capa...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2023-11-01
|
| Series: | Open Heart |
| Online Access: | https://openheart.bmj.com/content/10/2/e002455.full |
| _version_ | 1797366894209007616 |
|---|---|
| author | Jes Sanddal Lindholt Marie Dahl Anton Danholt Lautrup Tobias Hyrup Anna Schneider-Kamp Peter Schneider-Kamp |
| author_facet | Jes Sanddal Lindholt Marie Dahl Anton Danholt Lautrup Tobias Hyrup Anna Schneider-Kamp Peter Schneider-Kamp |
| author_sort | Jes Sanddal Lindholt |
| collection | DOAJ |
| description | Objectives The advent of conversational artificial intelligence (AI) systems employing large language models such as ChatGPT has sparked public, professional and academic debates on the capabilities of such technologies. This mixed-methods study sets out to review and systematically explore the capabilities of ChatGPT to adequately provide health advice to patients when prompted regarding four topics from the field of cardiovascular diseases.Methods As of 30 May 2023, 528 items on PubMed contained the term ChatGPT in their title and/or abstract, with 258 being classified as journal articles and included in our thematic state-of-the-art review. For the experimental part, we systematically developed and assessed 123 prompts across the four topics based on three classes of users and two languages. Medical and communications experts scored ChatGPT’s responses according to the 4Cs of language model evaluation proposed in this article: correct, concise, comprehensive and comprehensible.Results The articles reviewed were fairly evenly distributed across discussing how ChatGPT could be used for medical publishing, in clinical practice and for education of medical personnel and/or patients. Quantitatively and qualitatively assessing the capability of ChatGPT on the 123 prompts demonstrated that, while the responses generally received above-average scores, they occupy a spectrum from the concise and correct via the absurd to what only can be described as hazardously incorrect and incomplete. Prompts formulated at higher levels of health literacy generally yielded higher-quality answers. Counterintuitively, responses in a lower-resource language were often of higher quality.Conclusions The results emphasise the relationship between prompt and response quality and hint at potentially concerning futures in personalised medicine. The widespread use of large language models for health advice might amplify existing health inequalities and will increase the pressure on healthcare systems by providing easy access to many seemingly likely differential diagnoses and recommendations for seeing a doctor for even harmless ailments. |
| first_indexed | 2024-03-08T17:10:00Z |
| format | Article |
| id | doaj.art-a7053d24a7a647b9adf93404fb009665 |
| institution | Directory Open Access Journal |
| issn | 2053-3624 |
| language | English |
| last_indexed | 2024-03-08T17:10:00Z |
| publishDate | 2023-11-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | Open Heart |
| spelling | doaj.art-a7053d24a7a647b9adf93404fb0096652024-01-03T22:25:07ZengBMJ Publishing GroupOpen Heart2053-36242023-11-0110210.1136/openhrt-2023-002455Heart-to-heart with ChatGPT: the impact of patients consulting AI for cardiovascular health adviceJes Sanddal Lindholt0Marie Dahl1Anton Danholt Lautrup2Tobias Hyrup3Anna Schneider-Kamp4Peter Schneider-Kamp5Department of Clinical Research, University of Southern Denmark, Odense, DenmarkDepartment of Clinical Medicine, Aarhus University, Aarhus, DenmarkDepartment of Mathematics and Computer Science, University of Southern Denmark, Odense, DenmarkDepartment of Mathematics and Computer Science, University of Southern Denmark, Odense, DenmarkDepartment of Business and Management, University of Southern Denmark Faculty of Business and Social Sciences, Odense, DenmarkDepartment of Mathematics and Computer Science, University of Southern Denmark, Odense, DenmarkObjectives The advent of conversational artificial intelligence (AI) systems employing large language models such as ChatGPT has sparked public, professional and academic debates on the capabilities of such technologies. This mixed-methods study sets out to review and systematically explore the capabilities of ChatGPT to adequately provide health advice to patients when prompted regarding four topics from the field of cardiovascular diseases.Methods As of 30 May 2023, 528 items on PubMed contained the term ChatGPT in their title and/or abstract, with 258 being classified as journal articles and included in our thematic state-of-the-art review. For the experimental part, we systematically developed and assessed 123 prompts across the four topics based on three classes of users and two languages. Medical and communications experts scored ChatGPT’s responses according to the 4Cs of language model evaluation proposed in this article: correct, concise, comprehensive and comprehensible.Results The articles reviewed were fairly evenly distributed across discussing how ChatGPT could be used for medical publishing, in clinical practice and for education of medical personnel and/or patients. Quantitatively and qualitatively assessing the capability of ChatGPT on the 123 prompts demonstrated that, while the responses generally received above-average scores, they occupy a spectrum from the concise and correct via the absurd to what only can be described as hazardously incorrect and incomplete. Prompts formulated at higher levels of health literacy generally yielded higher-quality answers. Counterintuitively, responses in a lower-resource language were often of higher quality.Conclusions The results emphasise the relationship between prompt and response quality and hint at potentially concerning futures in personalised medicine. The widespread use of large language models for health advice might amplify existing health inequalities and will increase the pressure on healthcare systems by providing easy access to many seemingly likely differential diagnoses and recommendations for seeing a doctor for even harmless ailments.https://openheart.bmj.com/content/10/2/e002455.full |
| spellingShingle | Jes Sanddal Lindholt Marie Dahl Anton Danholt Lautrup Tobias Hyrup Anna Schneider-Kamp Peter Schneider-Kamp Heart-to-heart with ChatGPT: the impact of patients consulting AI for cardiovascular health advice Open Heart |
| title | Heart-to-heart with ChatGPT: the impact of patients consulting AI for cardiovascular health advice |
| title_full | Heart-to-heart with ChatGPT: the impact of patients consulting AI for cardiovascular health advice |
| title_fullStr | Heart-to-heart with ChatGPT: the impact of patients consulting AI for cardiovascular health advice |
| title_full_unstemmed | Heart-to-heart with ChatGPT: the impact of patients consulting AI for cardiovascular health advice |
| title_short | Heart-to-heart with ChatGPT: the impact of patients consulting AI for cardiovascular health advice |
| title_sort | heart to heart with chatgpt the impact of patients consulting ai for cardiovascular health advice |
| url | https://openheart.bmj.com/content/10/2/e002455.full |
| work_keys_str_mv | AT jessanddallindholt hearttoheartwithchatgpttheimpactofpatientsconsultingaiforcardiovascularhealthadvice AT mariedahl hearttoheartwithchatgpttheimpactofpatientsconsultingaiforcardiovascularhealthadvice AT antondanholtlautrup hearttoheartwithchatgpttheimpactofpatientsconsultingaiforcardiovascularhealthadvice AT tobiashyrup hearttoheartwithchatgpttheimpactofpatientsconsultingaiforcardiovascularhealthadvice AT annaschneiderkamp hearttoheartwithchatgpttheimpactofpatientsconsultingaiforcardiovascularhealthadvice AT peterschneiderkamp hearttoheartwithchatgpttheimpactofpatientsconsultingaiforcardiovascularhealthadvice |