Development of the AI-Cirrhosis-ECG Score: An Electrocardiogram-Based Deep Learning Model in Cirrhosis.
Development of the AI-Cirrhosis-ECG Score: An Electrocardiogram-Based Deep Learning Model in Cirrhosis.
复制标题
DOI：
10.14309/ajg.0000000000001617
复制
发表时间：
2022-03-01
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
肝硬化与心脏功能障碍和明显的心电图异常有关。本研究旨在开发一种基于深度学习的概念验证人工智能 (AI) 模型，该模型可以检测心电图上的肝硬化相关信号，并生成与疾病严重程度相关的 AI-肝硬化心电图 (ACE) 评分。对 Mayo Clinic 电子健康记录的审查发现，1988 年至 2019 年间，有 5,212 名年龄≥18 岁的晚期肝硬化患者在三个 Mayo Clinic 移植中心接受了肝移植 (LT)。这些患者按年龄和性别以 1:4 的比例与无肝病的对照进行匹配，然后使用 70%–10%–20% 的比例分为训练组、验证组和测试组。主要结果是该模型使用心电图区分肝硬化患者与对照组的性能。此外，还评估了 ACE 评分与患者肝病严重程度之间的关联。该模型在测试集中的 AUC 为 0.908，敏感性为 84.9%，特异性为 83.2%，并且在对医疗合并症进行额外匹配后，这一性能保持一致。随着 MELD-Na 的增加，ACE 分数显着升高。 LT 前后 ACE 评分的纵向趋势反映了肝病的进展和消退。 ACE评分是一种深度学习模型，可以准确地区分肝硬化患者和非肝硬化患者的心电图。人工智能心电图分析与肝硬化之间的这种新颖关系有望成为未来肝病患者护理中低成本工具和应用的基础。
Cirrhosis is associated with cardiac dysfunction and distinct ECG abnormalities. This study aimed to develop a proof-of-concept deep learning-based artificial intelligence (AI) model that could detect cirrhosis-related signals on ECG and generate an AI-Cirrhosis-ECG (ACE) score that would correlate with disease severity. A review of Mayo Clinic’s electronic health records identified 5,212 patients with advanced cirrhosis ≥18 years of age who underwent liver transplantation (LT) at the three Mayo Clinic transplant centers between 1988 and 2019. The patients were matched by age and sex in a 1:4 ratio to controls without liver disease, then divided into training, validation, and test sets using a 70%–10%–20% split. The primary outcome was the performance of the model in distinguishing patients with cirrhosis from controls using their ECGs. Additionally, the association between the ACE score and the severity of patients’ liver disease was assessed. The model’s AUC in the testing set was 0.908 with 84.9% sensitivity and 83.2% specificity, and this performance remained consistent after additional matching for medical comorbidities. Significant elevations in the ACE scores were seen with increasing MELD-Na. Longitudinal trends in the ACE scores before and after LT mirrored the progression and resolution of liver disease. The ACE score, a deep learning model, can accurately discriminate ECGs from patients with and without cirrhosis. This novel relationship between AI-enabled ECG analysis and cirrhosis holds promise as the basis for future low-cost tools and applications in the care of patients with liver disease.
登录
查看更多内容
影响因子：
25.7
作者：
Asrani, Sumeet K.;Devarbhavi, Harshad;Kamath, Patrick S.
通讯作者：
Kamath, Patrick S.
影响因子：
3.9
作者：
Bernardi, Mauro;Maggioli, Caterina;Zaccherini, Giacomo
通讯作者：
Zaccherini, Giacomo
影响因子：
168.9
作者：
Attia, Zachi, I;Noseworthy, Peter A.;Friedman, Paul A.
通讯作者：
Friedman, Paul A.
影响因子：
13.5
作者：
Trevisani, F;Sica, G;Bernardi, M
通讯作者：
Bernardi, M
影响因子：
2.6
作者：
Salgado AA;Barbosa PRB;Ferreira AG;Reis CASS;Terra C
通讯作者：
Terra C