GPT模型在心血管领域的应用：预测、诊断、治疗和科研教育的多维潜力

摘要/Abstract

摘要： 心血管疾病在我国发病率持续上升,给我国人民生命财产带来损失。人工智能技术逐步地发展,其中由OpenAI研发的GPT模型具有先进的自然语言处理能力、广泛的应用场景、以及个性化和高效的交互体验,给包含医学在内的多个领域带来便利。本文就GPT模型在心血管疾病预测、诊断、治疗以及心血管学科教育科研方面的应用潜力展开综述,总结了GPT模型在每方面的具体作用,以及其优点及缺陷。

关键词: 心血管疾病, 人工智能, GPT模型, 综述

廖一杭, 李拥军. GPT模型在心血管领域的应用：预测、诊断、治疗和科研教育的多维潜力[J]. 心血管病防治知识, 2025, 15(7): 141-144.

[1] Brown T, Mann B, Ryder N, et al.Language models are few-shot learners[J]. Advances in neural information processing systems, 2020, 33: 1877-901.
[2] Diseases N C F C, Health T W C O T R O C, China D I. 中国心血管健康与疾病报告2023概要[J]. 中国循环杂志, 2024, 39(7): 625-60.
[3] Han C, Kim D W, Kim S, et al.Evaluation of GPT-4 for 10-year cardiovascular risk prediction: Insights from the UK Biobank and KoGES data[J]. iScience, 2024, 27(2): 109022.
[4] GüNay S, öZtüRk A, öZerol H, et al. Comparison of emergency medicine specialist, cardiologist, and chat-GPT in electrocardiography assessment[J]. Am J Emerg Med, 2024, 80: 51-60.
[5] Dorfner F J, JüRgensen L, Donle L, et al. Comparing Commercial and Open-Source Large Language Models for Labeling Chest Radiograph Reports[J]. Radiology, 2024, 313(1): e241139.
[6] Kaya K, Gietzen C, Hahnfeldt R, et al.Generative Pre-trained Transformer 4 analysis of cardiovascular magnetic resonance reports in suspected myocarditis: A multicenter study[J]. J Cardiovasc Magn Reson, 2024, 26(2): 101068.
[7] Salam B, Kravchenko D, Nowak S, et al.Generative Pre-trained Transformer 4 makes cardiovascular magnetic resonance reports easy to understand[J]. J Cardiovasc Magn Reson, 2024, 26(1): 101035.
[8] Hoppe J M, Auer M K, StrüVen A, et al. ChatGPT With GPT-4 Outperforms Emergency Department Physicians in Diagnostic Accuracy: Retrospective Analysis[J]. J Med Internet Res, 2024, 26: e56110.
[9] Reyes-Rivera J, Castro Molina A, Romero-Lorenzo M, et al. Evaluating the Clinical Reasoning of GPT-4, Grok,Gemini in Different Fields of Cardiology [J]. Circulation, 2024, 150(Suppl_1): A4147550-A.
[10] Feleki A, Apostolopoulos I D, Moustakidis S, et al.Explainable Deep Fuzzy Cognitive Map Diagnosis of Coronary Artery Disease: Integrating Myocardial Perfusion Imaging, Clinical Data, and Natural Language Insights[J]. Applied Sciences, 2023, 13(21): 11953.
[11] Novak A, Zeljković I, Rode F, et al. The pulse of artificial intelligence in cardiology: a comprehensive evaluation of state-of-the-art large language models for potential use in clinical cardiology [J]. medRxiv, 2023: 2023.08. 08.23293689.
[12] Salihu A, Meier D, Noirclerc N, et al.A study of ChatGPT in facilitating Heart Team decisions on severe aortic stenosis[J]. EuroIntervention, 2024, 20(8): e496-e503.
[13] Fang Y, Ryan P, Weng C.Knowledge-guided generative artificial intelligence for automated taxonomy learning from drug labels[J]. J Am Med Inform Assoc, 2024, 31(9): 2065-2075.
[14] Jo E, Song S, Kim J H, et al.Assessing GPT-4's Performance in Delivering Medical Advice: Comparative Analysis With Human Experts[J]. JMIR Med Educ, 2024, 10: e51282.
[15] Scheschenja M, Viniol S, Bastian M B, et al.Feasibility of GPT-3 and GPT-4 for in-Depth Patient Education Prior to Interventional Radiological Procedures: A Comparative Analysis[J]. CardioVascular and Interventional Radiology, 2024, 47(2): 245-250.
[16] Anton Danholt L, Tobias H, Anna S-K, et al.Heart-to-heart with ChatGPT: the impact of patients consulting AI for cardiovascular health advice[J]. Open Heart, 2023, 10(2): e002455.
[17] Mishra V, Sarraju A, Kalwani N M, et al.Evaluation of Prompts to Simplify Cardiovascular Disease Information Generated Using a Large Language Model: Cross-Sectional Study[J]. J Med Internet Res, 2024, 26: e55388.
[18] Sarraju A.Evaluating misinformation regarding cardiovascular disease prevention obtained on a popular, publicly accessible artificial intelligence model (GPT-4)[J]. American Journal of Preventive Cardiology, 2024, 19: 100806.
[19] Ronquillo J G, Ye J, Gorman D, et al.Practical Aspects of Using Large Language Models to Screen Abstracts for Cardiovascular Drug Development: Cross-Sectional Study[J]. JMIR Med Inform, 2024, 12: e64143.
[20] Pabon M A, Vaduganathan M, Claggett B L, et al.In-hospital course of patients with heart failure with improved ejection fraction in the DELIVER trial[J]. Eur J Heart Fail, 2024, 26(12): 2532-40.
[21] Builoff V, Shanbhag A, Miller R J, et al.Evaluating AI proficiency in nuclear cardiology: Large language models take on the board preparation exam[J]. J Nucl Cardiol, 2024: 102089.
[22] Ebel S, Ehrengut C, Denecke T, et al.GPT-4o’s competency in answering the simulated written European Board of Interventional Radiology exam compared to a medical student and experts in Germany and its ability to generate exam items on interventional radiology: a descriptive study[J]. J Educ Eval Health Prof, 2024, 21: 21.

GPT模型在心血管领域的应用：预测、诊断、治疗和科研教育的多维潜力

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王彩娜. 远程信息平台的双心护理方案改善绝经期综合征伴高血压预后的研究[J]. 心血管病防治知识, 2025, 15(6): 137-139.
[2]	边昌贺, 冷德国, 王盛. 离心–膜滤过血浆置换（CFPP）成功治疗顽固性高脂血症一例[J]. 心血管病防治知识, 2025, 15(5): 134-136.
[3]	甘志新, 胡雍军, 杨倩, 黄建波. MicroRNA在心血管疾病中的研究进展[J]. 心血管病防治知识, 2025, 15(5): 137-144.
[4]	魏晓琴. 早期康复护理对老年心血管疾病患者Barthel及SDS评分的影响[J]. 心血管病防治知识, 2025, 15(1): 112-115.
[5]	庞樱容, 孙欣. CA125在心血管疾病中作用的研究进展[J]. 心血管病防治知识, 2024, 14(8): 141-144.
[6]	吴伟杰, 李思进, 陈靖, 张新霞. 深度学习结合眼底照片预测心血管疾病及相关危险因素研究进展[J]. 心血管病防治知识, 2024, 14(4): 139-144.
[7]	曾毅红. 多元化健康教育模式在老年心血管疾病患者临床护理中的运用价值研究[J]. 心血管病防治知识, 2024, 14(3): 127-130.
[8]	刘德忠, 史东. PCSK9抑制剂：一类降低动脉粥样硬化性心血管疾病患者血脂水平的新型药物[J]. 心血管病防治知识, 2024, 14(24): 133-140.
[9]	吕素如, 官淑芬, 陈晓燕. 医护一体化模式对急诊冠心病心绞痛患者自我效能及自我感受负担的影响[J]. 心血管病防治知识, 2024, 14(23): 69-72.
[10]	唐平, 赵洪磊, 阎德文. 代谢性心血管疾病基层综合防控专家共识[J]. 心血管病防治知识, 2024, 14(18): 3-13.
[11]	王紫云. NLRP3联合TYG指数对2型糖尿病并发动脉粥样硬化性心血管疾病的预测价值分析[J]. 心血管病防治知识, 2024, 14(18): 25-28.
[12]	曹慧娟. ICU重症心血管疾病患者护理中强化血糖控制的价值评价[J]. 心血管病防治知识, 2024, 14(17): 102-105.
[13]	王剑霞, 陈雅君. 溃疡性结肠炎患者伴发心血管疾病的影响因素分析[J]. 心血管病防治知识, 2024, 14(17): 127-131.
[14]	白燕芳, 黄华伦. 医护共情查房联合精细化人文关怀护理对急诊重症室老年心血管疾病患者焦虑抑郁和睡眠质量的效果[J]. 心血管病防治知识, 2024, 14(12): 134-137.
[15]	李子一, 薛进宜, 邹沅, 伍浩, 余海龙, 刘孟楠. 芳香类药物对心血管疾病临床症状改善作用的研究进展[J]. 心血管病防治知识, 2024, 14(1): 68-72.