Appearance
Artificial intelligence in cardiovascular pharmacotherapy: applications and perspectives.
文献信息
| DOI | 10.1093/eurheartj/ehaf474 |
|---|---|
| PMID | 40662528 |
| 期刊 | European heart journal |
| 影响因子 | 35.6 |
| JCR 分区 | Q1 |
| 发表年份 | 2025 |
| 被引次数 | 1 |
| 关键词 | 人工智能, 心血管药物治疗, 冠状动脉疾病, 糖尿病, 高血压 |
| 文献类型 | Journal Article, Review |
| ISSN | 0195-668X |
| 页码 | 3616-3627 |
| 期号 | 46(37) |
| 作者 | Francesco Costa, Juan Jose Gomez Doblas, Arancha Díaz Expósito, Marianna Adamo, Fabrizio D'Ascenzo, Lukasz Kołtowski, Luca Saba, Guiomar Mendieta, Felice Gragnano, Paolo Calabrò, Lina Badimon, Borja Ibañez, Roxana Mehran, Dominick J Angiolillo, Thomas Lüscher, Davide Capodanno |
一句话小结
本文回顾了人工智能在心血管药物治疗中的应用，指出其通过优化药物选择和预测治疗效果，能够改善患者的治疗结果并加速新药发现。然而，为实现这些潜力，需验证模型的准确性和可推广性，并解决数据质量和隐私等问题，以确保安全有效地将AI整合进临床实践。
在麦伴科研 (maltsci.com) 搜索更多文献
人工智能 · 心血管药物治疗 · 冠状动脉疾病 · 糖尿病 · 高血压
摘要
近年来，人工智能（AI）的进展显示出在改善心血管药物治疗方面的巨大潜力，通过优化药物选择、预测治疗效果和不良反应，最终改善患者的治疗结果。利用机器学习和计算机模拟等技术，人工智能能够识别可能从特定治疗中获益的人群，加速新药的发现并降低成本。计算方法还可以促进药物相互作用的检测，并根据真实世界的数据量身定制干预措施，从而支持个性化护理。基于人工智能的方法在简化临床试验设计和执行方面也显示出前景，通过实时数据提高患者反应的监测和招募效率。然而，为了充分实现这些益处，需要在不同患者人群中进行强有力的验证，以确保准确性和可推广性。此外，解决数据质量、隐私和偏见等问题同样至关重要，以避免加剧现有的医疗差距。科学学会和监管机构最终必须建立数据管理、模型认证和透明度的标准化框架，以便安全有效地将人工智能整合到临床实践中。本文旨在系统性地回顾当前人工智能在心血管药物治疗中的前沿应用，描述其在指导治疗决策、优化试验方法和支持药物发现方面的现有潜力。
英文摘要
Recent advances in artificial intelligence (AI) have shown great potential in improving cardiovascular pharmacotherapy by optimizing drug selection, predicting therapeutic efficacy and adverse effects, ultimately improving patient outcomes. Leveraging techniques like machine learning and in silico modelling, AI can identify populations likely to benefit from specific treatments, expedite novel drug discovery and reduce costs. Computational methods can also facilitate the detection of drug interactions and tailor interventions based on real-world data, supporting personalized care. Artificial intelligence-based approaches also show promise in streamlining clinical trial design and execution, leveraging on real-time data on patient responsiveness, enhancing recruitment efficiency. However, in order to fully realize these benefits, robust validation across diverse patient populations is necessary to ensure accuracy and generalizability. In addition, addressing concerns regarding data quality, privacy, and bias is equally critical to avoid exacerbating existing healthcare disparities. Scientific societies and regulatory agencies must ultimately establish standardized frameworks for data management, model certification, and transparency, to enable safe and effective integration of AI into clinical practice. This manuscript aims at systematically reviewing the current state-of-the-art applications of AI in cardiovascular pharmacotherapy, describing their current potential in guiding treatment decisions, refine trial methodologies and support drug discovery.
麦伴智能科研服务
主要研究问题
- 在心血管药物治疗中，AI如何优化药物选择以提高患者的治疗效果？
- 除了药物选择，AI在心血管药物研发的其他应用有哪些？
- 如何评估AI在心血管药物治疗中的有效性和安全性？
- AI在个性化心血管药物治疗中的作用是什么，如何实现？
- 当前在心血管药物治疗中应用AI时，存在哪些主要的伦理和隐私问题？
核心洞察
研究背景和目的
近年来，人工智能（AI）的进步在改善心血管药物治疗方面展现出巨大潜力。研究旨在系统性回顾AI在心血管药物治疗中的应用现状，探讨其在优化药物选择、预测疗效和不良反应、加速新药发现等方面的能力，以期改善患者的治疗结果。
主要方法/材料/实验设计
本研究主要采用文献综述的方法，分析现有的AI技术在心血管药物治疗中的应用。以下是技术路线的概述：
关键结果和发现
- 药物选择优化：AI能够识别适合特定治疗的人群，优化药物选择。
- 疗效与不良反应预测：利用机器学习，能够更准确地预测药物的疗效及潜在的不良反应。
- 新药发现：AI技术加速了新药的研发过程，并降低了相关成本。
- 个性化干预：基于现实世界数据的干预设计能够更好地满足患者的个体需求。
- 临床试验效率：AI在临床试验设计和执行中，通过实时数据分析提升了患者招募的效率。
主要结论/意义/创新性
本研究表明，AI在心血管药物治疗中具有显著的应用潜力，能够改善药物选择、提升治疗效果和优化临床试验过程。这些技术的应用不仅有助于个性化医疗的实现，还可能推动整个医疗行业的变革。然而，为了确保这些技术的有效性和安全性，必须进行广泛的验证，并建立标准化的数据管理和模型认证框架。
研究局限性和未来方向
- 局限性：当前的研究多集中于特定人群，缺乏对多样化患者群体的验证，可能影响结果的普遍适用性。
- 未来方向：
- 加强对AI模型的验证，以确保其在不同患者群体中的准确性和通用性。
- 解决数据质量、隐私和偏见问题，以避免加剧现有的医疗差距。
- 科学社团和监管机构需建立标准化框架，促进AI在临床实践中的安全有效整合。
本研究为心血管药物治疗领域的AI应用提供了重要的理论基础和实践指导。
参考文献
- Using artificial intelligence to identify anti-hypertensives as possible disease modifying agents in Parkinson's disease. - Naomi P Visanji;Piyush Madan;Alix M B Lacoste;Italo Buleje;Yanyan Han;Scott Spangler;Lorraine V Kalia;Sharon Hensley Alford;Connie Marras - Pharmacoepidemiology and drug safety (2021)
- Evaluation of machine learning algorithms for renin-angiotensin-aldosterone system inhibitors associated renal adverse event prediction. - Alper Tuna Güven;Murat Özdede;Yusuf Ziya Şener;Ali Osman Yıldırım;Sabri Engin Altıntop;Berkay Yeşilyurt;Oğuz Abdullah Uyaroğlu;Mine Durusu Tanrıöver - European journal of internal medicine (2023)
- Effect of Home Blood Pressure Monitoring via a Smartphone Hypertension Coaching Application or Tracking Application on Adults With Uncontrolled Hypertension: A Randomized Clinical Trial. - Stephen D Persell;Yaw A Peprah;Dawid Lipiszko;Ji Young Lee;Jim J Li;Jody D Ciolino;Kunal N Karmali;Hironori Sato - JAMA network open (2020)
- Evaluating eligibility criteria of oncology trials using real-world data and AI. - Ruishan Liu;Shemra Rizzo;Samuel Whipple;Navdeep Pal;Arturo Lopez Pineda;Michael Lu;Brandon Arnieri;Ying Lu;William Capra;Ryan Copping;James Zou - Nature (2021)
- Machine Learning Applied to Cholesterol-Lowering Pharmacotherapy: Proof-of-Concept in High-Risk Patients Treated in Primary Care. - Andrew J Krentz;Gabe Haddon-Hill;Xiaoyan Zou;Natalie Pankova;André Jaun - Metabolic syndrome and related disorders (2023)
- Using deep learning-based natural language processing to identify reasons for statin nonuse in patients with atherosclerotic cardiovascular disease. - Ashish Sarraju;Jean Coquet;Alban Zammit;Antonia Chan;Summer Ngo;Tina Hernandez-Boussard;Fatima Rodriguez - Communications medicine (2022)
- Demographic and epidemiologic drivers of global cardiovascular mortality. - Gregory A Roth;Mohammad H Forouzanfar;Andrew E Moran;Ryan Barber;Grant Nguyen;Valery L Feigin;Mohsen Naghavi;George A Mensah;Christopher J L Murray - The New England journal of medicine (2015)
- Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices. - Akshay Khunte;Veer Sangha;Evangelos K Oikonomou;Lovedeep S Dhingra;Arya Aminorroaya;Bobak J Mortazavi;Andreas Coppi;Cynthia A Brandt;Harlan M Krumholz;Rohan Khera - NPJ digital medicine (2023)
- New artificial intelligence prediction model using serial prothrombin time international normalized ratio measurements in atrial fibrillation patients on vitamin K antagonists: GARFIELD-AF. - Shinichi Goto;Shinya Goto;Karen S Pieper;Jean-Pierre Bassand;Alan John Camm;David A Fitzmaurice;Samuel Z Goldhaber;Sylvia Haas;Alexander Parkhomenko;Ali Oto;Frank Misselwitz;Alexander G G Turpie;Freek W A Verheugt;Keith A A Fox;Bernard J Gersh;Ajay K Kakkar - European heart journal. Cardiovascular pharmacotherapy (2020)
- Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. - Varun Gulshan;Lily Peng;Marc Coram;Martin C Stumpe;Derek Wu;Arunachalam Narayanaswamy;Subhashini Venugopalan;Kasumi Widner;Tom Madams;Jorge Cuadros;Ramasamy Kim;Rajiv Raman;Philip C Nelson;Jessica L Mega;Dale R Webster - JAMA (2016)
引用本文的文献
- Myocardial infarction, stroke and arterial stenosis: time to reassess a major misunderstanding. - Luca Saba;Peter Libby - Nature reviews. Cardiology (2025)
© 2025 MaltSci 麦伴科研 - 我们用人工智能技术重塑科研