M Odat Ramez, Marsool Marsool Mohammed D, Nguyen Dang, Idrees Muhammad, Hussein Ayham M, Ghabally Mike, A Yasin Jehad, Hanifa Hamdah, Sabet Cameron J, Dinh Nguyen H, Harky Amer, Jain Jyoti, Jain Hritvik
Faculty of Medicine, Jordan University of Science and Technology, Irbid.
Department of Internal Medicine. Al-Kindy College of Medicine, University of Baghdad, Baghdad, Iraq.
Int J Surg. 2024 Nov 1;110(11):7202-7214. doi: 10.1097/JS9.0000000000002003.
Infective endocarditis (IE) is a severe infection of the inner lining of the heart, known as the endocardium. It is characterized by a range of symptoms and has a complicated pattern of occurrence, leading to a significant number of deaths. IE poses significant diagnostic and treatment difficulties. This evaluation examines the utilization of artificial intelligence (AI) and machine learning (ML) models in addressing IE management. It focuses on the most recent advancements and possible applications. Through this paper, the authors observe that AI/ML can significantly enhance and outperform traditional diagnostic methods leading to more accurate risk stratification, personalized therapies, as well and real-time monitoring facilities. For example, early postsurgical mortality prediction models like SYSUPMIE achieved 'very good' area under the curve (AUROC) values exceeding 0.81. Additionally, AI/ML has improved diagnostic accuracy for prosthetic valve endocarditis, with PET-ML models increasing sensitivity from 59 to 72% when integrated into ESC criteria and reaching a high specificity of 83%. Furthermore, inflammatory biomarkers such as IL-15 and CCL4 have been identified as predictive markers, showing 91% accuracy in forecasting mortality, and identifying high-risk patients with specific CRP, IL-15, and CCL4 levels. Even simpler ML models, like Naïve Bayes, demonstrated an excellent accuracy of 92.30% in death rate prediction following valvular surgery for IE patients. Furthermore, this review provides a vital assessment of the advantages and disadvantages of such AI/ML models, such as better-quality decision support approaches like adaptive response systems on one hand, and data privacy threats or ethical concerns on the other hand. In conclusion, Al and ML must continue, through multicentric and validated research, to advance cardiovascular medicine, and overcome implementation challenges to boost patient outcomes and healthcare delivery.
感染性心内膜炎（IE）是一种严重的心脏内膜感染，即心内膜炎。它具有一系列症状，发病模式复杂，导致大量死亡。IE在诊断和治疗方面存在重大困难。本评估考察了人工智能（AI）和机器学习（ML）模型在IE管理中的应用。它关注的是最新进展和可能的应用。通过本文，作者观察到AI/ML可以显著增强并超越传统诊断方法，从而实现更准确的风险分层、个性化治疗以及实时监测功能。例如，像SYSUPMIE这样的术后早期死亡率预测模型的曲线下面积（AUROC）值达到了“非常好”的水平，超过了0.81。此外，AI/ML提高了人工瓣膜心内膜炎的诊断准确性，PET-ML模型在纳入ESC标准时，灵敏度从59%提高到了72%，特异性高达83%。此外，炎症生物标志物如IL-15和CCL4已被确定为预测标志物，在预测死亡率方面显示出91%的准确率，并能通过特定的CRP、IL-15和CCL4水平识别高危患者。即使是像朴素贝叶斯这样更简单的ML模型，在预测IE患者瓣膜手术后的死亡率时也表现出了92.30%的出色准确率。此外，本综述对这类AI/ML模型的优缺点进行了重要评估，一方面是像自适应响应系统这样质量更高的决策支持方法，另一方面是数据隐私威胁或伦理问题。总之，AI和ML必须通过多中心和经过验证的研究，继续推动心血管医学发展，克服实施挑战，以改善患者预后和医疗服务。
