发表机构
Michigan Technological University; International Atomic Energy Agency; University of Chicago; Cook County Health and Hospitals System; Rush Medical College（密歇根理工大学; 国际原子能机构; 芝加哥大学; 库克县健康与医院系统; 拉什医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究心脏淀粉样变性诊断中人工智能的应用，按筛查、检测等临床任务综合相关研究，揭示其成熟度梯度，骨闪烁显像和SPECT/CT的二元检测及量化接近临床转化，亚型识别等任务尚处早期。
AI 中文摘要
心脏淀粉样变性（CA）虽日益受到关注，但仍存在大量漏诊情况，因其临床和影像表现与常见心肌病重叠，明确亚型及管理需整合多模态证据。机器学习和深度学习已应用于诊断及管理途径，涵盖心电图、超声心动图、基于健康记录的病例发现、心脏磁共振成像和核医学解读等。本叙述性综述按临床任务（筛查、检测、量化、预后和治疗反应监测）而非输入模态综合这些研究，揭示了不同任务的成熟度梯度，如骨闪烁显像和SPECT/CT的二元检测及人工智能辅助量化最接近临床转化，而亚型识别分类、预后风险分层和治疗反应监测仍处于早期阶段。
英文摘要
Cardiac amyloidosis (CA) is increasingly recognized but remains substantially underdiagnosed because its clinical and imaging phenotype overlaps with more common cardiomyopathies. Definitive subtype assignment and management further require integration of multimodal evidence to distinguish transthyretin from light-chain disease. Machine learning and deep learning have been applied across the diagnostic and management pathway. These applications span electrocardiography (ECG), echocardiography, and health record-based case finding, as well as cardiac magnetic resonance (CMR) and nuclear interpretation, including single-photon emission computed tomography/computed tomography (SPECT/CT) biomarker quantification, prognostic modeling, and treatment response assessment. This narrative review synthesizes these studies by clinical tasks, namely screening, detection, quantification, prognosis, and longitudinal assessment after treatment initiation, rather than by input modality. This task-based organization clarifies why apparently similar AI models require different cohorts, reference standards, evaluation metrics, and implementation thresholds. The evidence reveals a maturity gradient. Binary detection and AI-assisted interpretation of cardiac scintigraphy with bone-avid tracers and SPECT/CT currently represent one of the more mature AI applications in cardiac amyloidosis, supporting standardized image interpretation and quantitative biomarker extraction. However, patient-level diagnosis still requires integration with monoclonal protein testing, SPECT/CT localization, clinical context, and biopsy or tissue typing when indicated.
CommentsDiana Shadibaeva and Rochak Dhakal contributed equally to this work. Total Pages = 35, No. of Figures = 4, No. of Tables on Manuscript = 1, Supplementary Tables = 6
