基于心电图的深度学习用于慢性病检测和心血管风险预测
Ping-Huang Tsai1, Shang-Yang Lee2,3, Chia-Ling Helen Wei1,4
1Division of Nephrology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical University, Taipei, Taiwan, R.O.C.
BMC medical informatics and decision making
|December 3, 2025
概括
分析心电图 (ECG) 的深度学习模型 (DLM) 可以在实验室测试之前识别慢性病 (CKD) 风险. 这种人工智能工具有助于早期检测和风险分层,以获得更好的患者结果.
科学领域:
- 心脏病学 心脏病学
- 腎臟病學 (nephrology) 是一種醫學專業.
- 人工智能的人工智能
背景情况:
- 慢性病 (CKD) 是一个全球性的健康挑战,人们对此的认识很低.
- 深度学习模型 (DLM) 显示了用于疾病检测的ECG解释的潜力.
- 基于心电图的DLM可能为早期CKD识别提供新的途径.
研究的目的:
- 开发和验证用于使用心电图检测CKD的DLM.
- 评估DLM识别患有CKD及其并发症风险的个人的能力.
- 将DLM的预测性能与传统的eGFR分类进行比较.
主要方法:
- 使用了49632名门诊患者的心电图 (共66587名注册患者) 和eGFR数据 (2010年1月至2020年10月).
- 使用72,618个ECG开发了DLM,对16955名患者进行了内部验证,对10476名患者进行了外部验证.
- 主要结局:CKD检测 (eGFR<60mL/min/1.73m2);次要结局:所有原因死亡率和主要心血管事件.
主要成果:
- 对于CKD检测,DLM的AUC为0.885 (内部) 和0.861 (外部).
- DLM识别的CKD患者表现出更高的CKD进展和心血管疾病的风险.
- 在没有基线CKD的患者中,积极的DLM查显著增加了发生CKD的风险 (HRs 2.14和1.38).
- 在预测诸如中风,心力衰竭和心房动等不良结果方面,DLM分层表现优于eGFR.
结论:
- 基于心电图的DLM可以识别患有CKD和相关并发症风险的个体.
- 这种人工智能方法在临床环境中促进了早期检测和风险分层.
- 该模型在实验室标志物显现之前有望识别亚临床CKD.
相关概念视频
Chronic Kidney Disease I: Introduction
545
Chronic Kidney Disease (CKD) arises when the kidneys progressively lose their ability to function, ultimately leading to end-stage renal disease. At this advanced stage, the kidneys can no longer filter waste or maintain essential body functions, requiring renal replacement therapy (RRT) through dialysis or a kidney transplant for survival.Early-stage chronic kidney disease and detection challengesIn CKD's early stages, symptoms often remain absent because healthy nephrons compensate for...
545
Chronic Kidney Disease III: Interprofessional Care
323
Chronic kidney disease (CKD) requires collaborative and comprehensive management. CKD progresses through stages and can lead to end-stage kidney disease (ESKD) if untreated. Interprofessional collaboration and patient education are crucial, enabling patients to manage their health and improve their quality of life.Diagnostic approach for chronic kidney diseaseThe diagnosis of CKD primarily focuses on the glomerular filtration rate (GFR), which assesses kidney function by measuring how well...
323
Chronic Kidney Disease IV: Nursing Management
299
Nursing management is essential for preventing complications, maintaining stability, and improving patients' quality of life in chronic kidney disease (CKD). By using a structured approach, nurses help slow CKD progression and support effective patient care.1. Comprehensive patient assessmentEffective management begins with nurses reviewing the patient’s medical history, and identifying key risk factors like diabetes, hypertension, and nephrotoxic drug use. Nurses assess signs of...
299
Chronic Kidney Disease II: Clinical Manifestations
529
Chronic Kidney Disease (CKD) progressively impairs multiple body systems due to the accumulation of uremic toxins, which disrupt cellular functions across various organs.Neurologic symptomsNeurologic symptoms often arise early in CKD, as uremic toxin buildup drives changes in cognitive and motor functions. Patients frequently experience fatigue, headache, confusion, difficulty concentrating, and, in severe cases, seizures. Peripheral neuropathy commonly manifests as burning sensations in the...
529
Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration
174
Glomerular filtration rate (GFR) can be estimated from serum creatinine using the modification of diet in renal disease (MDRD) formula or the chronic kidney disease–epidemiology collaboration (CKD–EPI) equation. Both methods are widely used in clinical practice to assess kidney function and guide treatment decisions.The MDRD equation does not require weight or height measurements and is normalized to the body surface area of 1.73 m², considered the average adult surface area.
174
Acute Kidney Injury IV: Diagnostic Studies and Prevention
244
Accurate diagnosis and effective prevention are critical in managing Acute Kidney Injury (AKI), which is linked to high mortality rates ranging from 10% to 80%. Timely recognition of at-risk patients and careful monitoring can significantly reduce the likelihood of kidney damage.Diagnostic Assessments:The diagnostic process starts with a comprehensive medical history to identify prerenal, intrarenal, and postrenal causes.Prerenal causes, such as dehydration, hypotension, or blood loss, should...
244


