Prospects for the application of Chat-GPT in organizing medical care for patients with diabetes (brief review of international literature)
https://doi.org/10.25881/18110193_2024_2_6
Abstract
One of the new developments in the field of artificial intelligence (AI) is the Chat-GPT (Generative Pre-trained Transformer) technology, a capacious linguistic model based on the analysis of big data using powerful computing systems through the aggregation of certain algorithms. Such technologies are capable of “understanding” and composing texts close to those created by humans. Their improvement and implementation can lead to better quality and accessibility of medical care for patients, including patients with diabetes mellitus (DM).
The aim of this work was to summarize all available and relevant information about the applicability of Chat-GPT technology in patients with DM.
Materials and methods. The search for relevant information sources was carried out through Pubmed / Medline database. “ChatGPT diabetes” was used as search combination.
Results. Chat-GPT is a fairly new AI technology (start of use - November 2022), and there is a limited amount of published data available regarding its implementation in treatment of patients with DM. This review systematizes and generalizes approaches to assessing the prospects for Chat-GPT application as well as summarizes some its characteristics. Rare research results show that Chat-GPT has the ability to provide valuable information about diabetes in many cases. However, it is necessary to approach the use of this technology with great caution since the system does not always generate completely correct, accurate and detailed answers. A mechanism for assessing the quality of responses from such systems should be developed.
Conclusion. This study is limited to information available in open sources. It is rational to continue studies of Chat-GPT accuracy and precision. It is obvious that improving the system by training on large amounts of medical data updated in real time might open up new prospects for its application.
About the Authors
D. A. Andreev
State Budgetary Institution «Research Institute for Healthcare Organization and Medical Management
of Moscow Health Department»
Russian Federation
Russian Federation
PhD
N. N. Kamynina
State Budgetary Institution «Research Institute for Healthcare Organization and Medical Management
of Moscow Health Department»
Russian Federation
Russian Federation
DSc
References
1. Cheng K, He Y, Li C, Xie R, Lu Y, Gu S, et al. Talk with ChatGPT About the Outbreak of Mpox in 2022: Reflections and Suggestions from AI Dimensions. Ann Biomed Eng. 2023; 51: 870-4. doi: 10.1007/s10439-023-03196-z.
2. Johnson D, Goodman R, Patrinely J, Stone C, Zimmerman E, Donald R, et al. Assessing the Accuracy and Reliability of AI-Generated Medical Responses: An Evaluation of the Chat-GPT Model. Res Sq. 2023. doi: 10.21203/rs.3.rs-2566942/v1.
3. Kung TH, Cheatham M, Medenilla A, Sillos C, De Leon L, Elepaño C, et al. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS Digit Heal. 2023; 2: e0000198. doi: 10.1371/journal.pdig.0000198.
4. Gilson A, Safranek CW, Huang T, Socrates V, Chi L, Taylor RA, et al. How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Models for Medical Education and Knowledge Assessment. JMIR Med Educ. 2023; 9: e45312. doi: 10.2196/45312.
5. Shen Y, Heacock L, Elias J, Hentel KD, Reig B, Shih G, et al. ChatGPT and Other Large Language Models Are Double-edged Swords. Radiology. 2023; 307: e230163. doi: 10.1148/radiol.230163.
6. Goodman RS, Patrinely JRJ, Osterman T, Wheless L, Johnson DB. On the cusp: Considering the impact of artificial intelligence language models in healthcare. Med (New York, NY). 2023; 4: 139-40. doi: 10.1016/j.medj.2023.02.008.
7. Vaishya R, Misra A, Vaish A. ChatGPT: Is this version good for healthcare and research? Diabetes Metab Syndr Clin Res Rev. 2023; 17: 102744. doi: 10.1016/j.dsx.2023.102744.
8. Hulman A, Dollerup OL, Mortensen JF, Fenech ME, Norman K, Støvring H, et al. ChatGPT- versus humangenerated answers to frequently asked questions about diabetes: A Turing test-inspired survey among employees of a Danish diabetes center. PLoS One. 2023; 18: e0290773. doi: 10.1371/journal.pone.0290773.
9. Khan I, Agarwal R. Can ChatGPT Help in the Awareness of Diabetes? Ann Biomed Eng. 2023; 51: 2125-9. doi: 10.1007/s10439-023-03356-1.
10. Zheng Y, Wu Y, Feng B, Wang L, Kang K, Zhao A. Enhancing Diabetes Self-management and Education: A Critical Analysis of ChatGPT’s Role. Ann Biomed Eng. 2023. doi: 10.1007/s10439-023-03317-8.
11. Sharma S, Pajai S, Prasad R, Wanjari MB, Munjewar PK, Sharma R, et al. A Critical Review of ChatGPT as a Potential Substitute for Diabetes Educators. Cureus. 2023; 15: e38380. doi: 10.7759/cureus.38380.
12. Sng GGR, Tung JYM, Lim DYZ, Bee YM. Potential and Pitfalls of ChatGPT and Natural-Language Artificial Intelligence Models for Diabetes Education. Diabetes Care. 2023; 46: e103-5. doi: 10.2337/dc23-0197.
13. Huang C, Chen L, Huang H, Cai Q, Lin R, Wu X, et al. Evaluate the accuracy of ChatGPT’s responses to diabetes questions and misconceptions. J Transl Med. 2023; 21: 502. doi: 10.1186/s12967-023-04354-6.
14. Mathur K, Agrawal RK, Nagpure S, Deshpande D. Effect of artificial sweeteners on insulin resistance among type-2 diabetes mellitus patients. J Fam Med Prim Care. 2020; 9: 69-71. doi: 10.4103/jfmpc.jfmpc_329_19.
15. Zhou X, Zeng C. Diabetes remission of bariatric surgery and nonsurgical treatments in type 2 diabetes patients who failure to meet the criteria for surgery: a systematic review and meta-analysis. BMC Endocr Disord. 2023; 23: 46. doi: /10.1186/s12902-023-01283-9.
Review
For citations:
Andreev D.A., Kamynina N.N. Prospects for the application of Chat-GPT in organizing medical care for patients with diabetes (brief review of international literature). Medical Doctor and Information Technologies. 2024;(2):6-11. (In Russ.) https://doi.org/10.25881/18110193_2024_2_6
Views:
86
Email this article 