机器学习在心脏淀粉样变辅助诊断中的研究进展

梁雨; 乔瑞玲; 潘雨凌; 张帅; 梁纯子

doi:10.14188/j.1671-8852.2023.0535

您当前的位置：

首页 >

文章列表页 >

机器学习在心脏淀粉样变辅助诊断中的研究进展

综述与Meta分析 | 更新时间：2026-11-05

- 机器学习在心脏淀粉样变辅助诊断中的研究进展
- Research progress of machine learning in assistant diagnosis of cardiac amyloidosis
- 武汉大学学报（医学版） 2025年46卷第6期页码：806-811
- 作者机构：
  
  1.湖北中医药大学检验学院湖北武汉 430065
  2.湖北时珍实验室湖北武汉 430065
  3.中国科学院计算机技术研究所北京 100190
- 作者简介：
  
  梁雨，女，2002—，医学硕士生，主要从事心血管疾病的深度学习预测模型研究，E‑mail: 2331000006@stmail.hbucm.edu.cn
  梁纯子，女，1985—，副教授，硕士生导师，主要从事检验医学人工智能研究，E‑mail: liangcz2021@hbucm.edu.cn
- 基金信息：
  
  湖北中医药大学高层次人才科研启动经费(100501070302)
- DOI：10.14188/j.1671-8852.2023.0535
  中图分类号： R541
- 收稿：2023-10-11，
  
  纸质出版：2025-06-25
- 稿件说明：
移动端阅览
梁雨,乔瑞玲,潘雨凌等.机器学习在心脏淀粉样变辅助诊断中的研究进展[J].武汉大学学报（医学版）,2025,46(06):806-811.

LIANG Yu,QIAO Ruiling,PAN Yuling,et al.Research progress of machine learning in assistant diagnosis of cardiac amyloidosis[J].Medical Journal of Wuhan University,2025,46(06):806-811.
梁雨,乔瑞玲,潘雨凌等.机器学习在心脏淀粉样变辅助诊断中的研究进展[J].武汉大学学报（医学版）,2025,46(06):806-811. DOI： 10.14188/j.1671-8852.2023.0535.

LIANG Yu,QIAO Ruiling,PAN Yuling,et al.Research progress of machine learning in assistant diagnosis of cardiac amyloidosis[J].Medical Journal of Wuhan University,2025,46(06):806-811. DOI： 10.14188/j.1671-8852.2023.0535.

摘要

心脏淀粉样变（CA）是一种较为罕见的限制性心肌病，以不溶性淀粉样蛋白异常沉积于心肌间质为主要特征。根据沉积蛋白种类不同，大部分CA被区分为AL和ATTR亚型并制定了相应的诊疗方案。然而，由于CA病情重、进展快、临床识别率低，常规诊断技术极易出现漏诊或延误诊断，使患者失去了早期治疗机会，普遍预后不良。机器学习作为近年来新兴的人工智能技术之一，能够从复杂的原始医学数据中自动量化、提取、分析显著性特征，无需人力先验知识的预处理干预，在临床诊疗决策中显示出先进的诊断性能和应用价值。本文将综述机器学习模型利用不同类型医学数据，在CA诊断预测方面的应用，综合评估其性能、泛化能力和可解释性。

Abstract

Cardiac amyloidosis (CA) is characterized as a relatively uncommon restrictive cardiomyopathy

predominantly identified by the abnormal accumulation of insoluble amyloid proteins in the myocardial interstitium. Based on the category of deposited proteins

a majority of CA patients are differentiated into AL and ATTR subtypes

for which corresponding diagnostic and therapeutic strategies have been developed. Nonetheless

owing to the severity

rapid progression

and low clinical recognition rates of CA

standard diagnostic approaches are prone to overlook or delay diagnosis

depriving patients of early treatment opportunities and generally resulting in poor prognoses. Machine learning

emerging as a novel technology in artificial intelligence in recent years

is capable of automatically quantifying

extracting

and analyzing significant features from complex original medical data without the necessity for human intervention in preprocessing based on prior knowledge

demonstrating advanced diagnostic performance and applicative value in clinical decision‑making. This article will present a comprehensive review of the applications of machine learning diagnostic models based on varying types of medical data in the diagnosis and prediction of CA

conducting a holistic evaluation of their performance

generalizability

and interpretability.

关键词

Keywords

references

FONTANA M , ĆOROVIĆ A , SCULLY P , et al . Myocardial amyloidosis: The exemplar interstitial disease [J ] . JACC Cardiovasc Imaging , 2019 , 12 ( 11 Pt 2 ): 2345 ‑ 2356 .

BLOOM M W , GOREVIC P D . Cardiac amyloidosis [J ] . Ann Intern Med , 2023 , 176 ( 3 ): ITC33 ‑ ITC48 .

MACEDO A V S , SCHWARTZMANN P V , DE GUSMÃO B M , et al . Advances in the treatment of cardiac amyloidosis [J ] . Curr Treat Options Oncol , 2020 , 21 ( 5 ): 36 .

KASTRITIS E , PALLADINI G , MINNEMA M C , et al . Daratumumab‑based treatment for immunoglobulin light‑chain amyloidosis [J ] . N Engl J Med , 2021 , 385 ( 1 ): 46 ‑ 58 .

PALLADINI G , MERLINI G . How I treat AL amyloidosis [J ] . Blood , 2022 , 139 ( 19 ): 2918 ‑ 2930 .

YANG T J , WAN K , SONG R Z , et al . Serum high‑density lipoprotein cholesterol serves as a prognostic marker for light‑chain cardiac amyloidosis [J ] . Int J Cardiol , 2021 , 325 : 96 ‑ 102 .

GARCIA‑PAVIA P , RAPEZZI C , ADLER Y , et al . Diagnosis and treatment of cardiac amyloidosis: A position statement of the ESC Working Group on Myocardial and Pericardial Diseases [J ] . Eur Heart J , 2021 , 42 ( 16 ): 1554 ‑ 1568 .

GROGAN M , SCOTT C G , KYLE R A , et al . Natural history of wild‑type transthyretin cardiac amyloidosis and risk stratification using a novel staging system [J ] . J Am Coll Cardiol , 2016 , 68 ( 10 ): 1014 ‑ 1020 .

何山 , 田庄 , 张抒扬 . 转甲状腺素蛋白心脏淀粉样变无创诊断的研究进展 [J ] . 中华心血管病杂志 , 2020 , 48 ( 4 ): 276 ‑ 279 .

HE S , TIAN Z , ZHANG S Y . State‑of‑the‑art review on the non‑invasive diagnosis approaches of patients with transthyretin cardiac amyloidosis [J ] . Chin J Cardiol , 2020 , 48 ( 4 ): 276 ‑ 279 .

沈立松 , 曾俊祥 . 机器学习在检验医学应用的现状与思考 [J ] . 中华检验医学杂志 , 2022 , 45 ( 12 ): 1197 ‑ 1200 .

SHEN L S , ZENG J X . Thinking of the current status and application of machine learning in the field of laboratory medicine [J ] . Chin J Lab Med , 2022 , 45 ( 12 ): 1197 ‑ 1200 .

GREENER J G , KANDATHIL S M , MOFFAT L , et al . A guide to machine learning for biologists [J ] . Nat Rev Mol Cell Biol , 2022 , 23 ( 1 ): 40 ‑ 55 .

RABBANI N , KIM G Y E , SUAREZ C J , et al . Applications of machine learning in routine laboratory medicine: Current state and future directions [J ] . Clin Biochem , 2022 , 103 : 1 ‑ 7 .

HARTNETT J , JABER W , MAURER M , et al . Electrophysiological manifestations of cardiac amyloidosis: JACC: CardioOncology state‑of‑the‑art review [J ] . JACC CardioOncol , 2021 , 3 ( 4 ): 506 ‑ 515 .

KITAOKA H , IZUMI C , IZUMIYA Y , et al . JCS 2020 guideline on diagnosis and treatment of cardiac amyloidosis [J ] . Circ J , 2020 , 84 ( 9 ): 1610 ‑ 1671 .

GOTO S , MAHARA K , BEUSSINK‑NELSON L , et al . Artificial intelligence‑enabled fully automated detection of cardiac amyloidosis using electrocardiograms and echocardiograms [J ] . Nat Commun , 2021 , 12 ( 1 ): 2726 .

SCHRUTKA L , ANNER P , AGIBETOV A , et al . Machine learning‑derived electrocardiographic algorithm for the detection of cardiac amyloidosis [J ] . Heart , 2022 , 108 ( 14 ): 1137 ‑ 1147 .

ZHANG J , GAJJALA S , AGRAWAL P , et al . Fully automated echocardiogram interpretation in clinical practice [J ] . Circulation , 2018 , 138 ( 16 ): 1623 ‑ 1635 .

ZHANG X F , LIANG T Y , SU C X , et al . Deep learn‑based computer‑assisted transthoracic echocardiography: Approach to the diagnosis of cardiac amyloidosis [J ] . Int J Cardiovasc Imaging , 2023 , 39 ( 5 ): 955 ‑ 965 .

马璇 , 赵世华 . 机器学习在心脏磁共振成像中的应用进展 [J ] . 中华心血管病杂志 , 2023 , 51 ( 4 ): 434 ‑ 439 .

MA X , ZHAO S H . Progress in the clinical application of machine learning in cardiac magnetic resonance imaging [J ] . Chin J Cardiol , 2023 , 51 ( 4 ): 434 ‑ 439 .

MARTINI N , AIMO A , BARISON A , et al . Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance [J ] . J Cardiovasc Magn Reson , 2020 , 22 ( 1 ): 84 .

SATRIANO A , AFZAL Y , SARIM AFZAL M , et al . Neural‑network‑based diagnosis using 3‑dimensional myocardial architecture and deformation: Demonstration for the differentiation of hypertrophic cardiomyopathy [J ] . Front Cardiovasc Med , 2020 , 7 : 584727 .

JIANG S , ZHANG L L , WANG J , et al . Differentiating between cardiac amyloidosis and hypertrophic cardiomyopathy on non‑contrast cine‑magnetic resonance images using machine learning‑based radiomics [J ] . Front Cardiovasc Med , 2022 , 9 : 1001269 .

ECKSTEIN J , MOGHADASI N , KÖRPERICH H , et al . A machine learning challenge: Detection of cardiac amyloidosis based on Bi‑atrial and right ventricular strain and cardiac function [J ] . Diagnostics , 2022 , 12 ( 11 ): 2693 .

KHOR Y M , CUDDY S A M , SINGH V , et al . (99m)Tc bone‑avid tracer cardiac scintigraphy: Role in noninvasive diagnosis of transthyretin cardiac amyloidosis [J ] . Radiology , 2023 , 306 ( 2 ): e221082 .

DELBARRE M A , GIRARDON F , ROQUETTE L , et al . Deep learning on bone scintigraphy to detect abnormal cardiac uptake at risk of cardiac amyloidosis [J ] . JACC Cardiovasc Imaging , 2023 , 16 ( 8 ): 1085 ‑ 1095 .

AGIBETOV A , SEIRER B , DACHS T M , et al . Machine learning enables prediction of cardiac amyloidosis by routine laboratory parameters: A proof‑of‑concept study [J ] . J Clin Med , 2020 , 9 ( 5 ): 1334 .

GARCÍA‑GARCÍA E , GONZÁLEZ‑ROMERO G M , MARTÍN‑PÉREZ E M , et al . Real‑world data and machine learning to predict cardiac amyloidosis [J ] . Int J Environ Res Public Health , 2021 , 18 ( 3 ): 908 .

DI STEFANO V , PRINZI F , LUIGETTI M , et al . Machine learning for early diagnosis of ATTRv amyloidosis in non‑endemic areas: A multicenter study from Italy [J ] . Brain Sci , 2023 , 13 ( 5 ): 805 .

HUDA A , CASTAÑO A , NIYOGI A , et al . A machine learning model for identifying patients at risk for wild‑type transthyretin amyloid cardiomyopathy [J ] . Nat Commun , 2021 , 12 ( 1 ): 2725 .

ALLEGRA A , MIRABILE G , TONACCI A , et al . Machine learning approaches in diagnosis, prognosis and treatment selection of cardiac amyloidosis [J ] . Int J Mol Sci , 2023 , 24 ( 6 ): 5680 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

多种机器学习模型预测膀胱癌肺转移预后

基于超声特征构建甲状腺微小乳头状癌侧颈淋巴结转移的列线图风险预测模型

基于免疫相关基因的HER2阳性乳腺癌新辅助化疗联合靶向治疗疗效预测模型

基于机器学习的抽动障碍共患注意缺陷与多动障碍的风险评估模型研究

静脉血栓栓塞症预防健康教育的研究进展