Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 12, 2026BMC MedicineOpen Access

The Super Learner model achieved an AUC of 0.97 (95% CI: 0.95–0.98) in the derivation cohort and 0.96 (95% CI: 0.95–0.98) for CA in the external validation cohort.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Does an AI model integrating ECG and echocardiography accurately diagnose cardiac amyloidosis among patients with left-ventricular hypertrophy?

Population

1,221 patients with left-ventricular hypertrophy including cardiac amyloidosis, hypertrophic cardiomyopathy…

Design

Cross-sectional

Authors

SZShuyuan ZhangSZShuyuan ZhangZWZhiqiang Wan

Discussion

Loading...

Member takes

Overview

High AUC supports ML ensembles for CA discrimination in cohorts; leaves open prospective validation before clinical use.

Key Points

  • To develop and validate an AI model that distinguishes cardiac amyloidosis from other causes of left-ventricular hypertrophy.
  • Conducted a multicenter retrospective study in China.
  • Used a derivation cohort of 290 CA patients, 215 HCM patients, and 160 HHD patients.
  • Evaluated model performance using metrics such as macro-AUC, accuracy, and precision.
  • The Super Learner model achieved the highest AUC of 0.97 (95% CI: 0.95–0.98).
  • In external validation, the model achieved AUCs of 0.96 for CA and 0.91 for HHD.
  • The simplified scoring system showed robust diagnostic performance with an AUC of 0.90 (95% CI 0.86–0.93).

Structured PICO

Does an AI model integrating ECG and echocardiography accurately diagnose cardiac amyloidosis among patients with left-ventricular hypertrophy?

P
Population
1,221 patients with left-ventricular hypertrophy (LVH) including cardiac amyloidosis (CA), hypertrophic cardiomyopathy (HCM), and hypertensive heart disease (HHD). Derivation cohort (n=665): 290 CA, 215 HCM, 160 HHD; mean age 55.8, 66.8% male. External validation cohort (n=556): 126 CA, 240 HCM, 190 HHD; mean age 63.1, 63.3% male. Multicenter in China.
I
Intervention
AI model (Super Learner) and a simplified scoring system integrating 7 features from ECG and echocardiography (Sokolow-Lyon index, interventricular septal thickness, systolic blood pressure, left-ventricular posterior wall thickness, tricuspid annular plane systolic excursion, average E/e′, and left-ventricular ejection fraction) for CA screening and diagnosis.
O
Outcome
Diagnostic accuracy (AUC) for distinguishing cardiac amyloidosis from hypertrophic cardiomyopathy and hypertensive heart disease

An AI model and simplified scoring system using routine ECG and echocardiography parameters can accurately distinguish cardiac amyloidosis from other causes of left ventricular hypertrophy.

Limitations

  • performance and generalizability should be further validated in larger prospective multicenter studies

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a2bd1386550ea4541ffe9aehttps://doi.org/10.1186/s12916-026-04987-6
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Multimodal Artificial Intelligence for Cardiac Amyloidosis Diagnosis: Integrating Echocardiography With Clinical and Laboratory Data for Improved Detection2026
  2. 2International Validation of Echocardiographic Artificial Intelligence Amyloid Detection Algorithm2025
  3. 3Artificial Intelligence in Cardiac Amyloidosis: A Systematic Review and Meta-Analysis of Diagnostic Accuracy Across Imaging and Non-Imaging Modalities2025
  4. 4AI-driven ECG diagnostics: A game-changer for hypertrophic cardiomyopathy. A systematic review and diagnostic test accuracy meta-analysis2025
  5. 5Artificial Intelligence-Based Algorithms for Early Detection of Heart Failure Using Electrocardiography and Echocardiography2025