Objective:

To explore the diagnostic accuracy of machine learning (ML) in diagnosing cardiac amyloidosis (CA) and provide evidence-based data for the development of smart detection tools, addressing the lack of systematic evidence regarding ML's accuracy.

Approach:

• Literature Search: Searched Cochrane Library, PubMed, Embase, and Web of Science up to September 25, 2025, following PRISMA 2020 guidelines.
• Quality Evaluation: Study quality assessed using the QUADAS-2 instrument.
• Subgroup Analyses: Stratified by disease type (light chain CA and transthyretin CA) and imaging modality (echocardiography) to explore heterogeneity.

Key Findings:

• ML for overall CA showed sensitivity 0.87 [95% CI: 0.83–0.91], specificity 0.88 [95% CI: 0.81–0.92], PLR 7.0 [95% CI: 4.4–11.4], NLR 0.14 [95% CI: 0.10–0.20], and SROC AUC 0.93 [95% CI: 0.91–0.95].
• For AL-CA, ML demonstrated sensitivity 0.85 [95% CI: 0.76–0.91], specificity 0.82 [95% CI: 0.75–0.87], PLR 4.8 [95% CI: 3.4–6.7], NLR 0.18 [95% CI: 0.11–0.30], and SROC AUC 0.88 [95% CI: 0.85–0.91].
• For ATTR-CA, ML revealed sensitivity 0.84 [95% CI: 0.77–0.89], specificity 0.85 [95% CI: 0.78–0.91], PLR 5.7 [95% CI: 3.6–9.2], NLR 0.19 [95% CI: 0.12–0.28], and SROC AUC 0.91 [95% CI: 0.88–0.93].
• Echocardiography-only ML models showed sensitivity 0.83 [95% CI: 0.81–0.85], specificity 0.86 [95% CI: 0.82–0.89], PLR 5.9 [95% CI: 4.4–7.9], NLR 0.20 [95% CI: 0.17–0.23], and SROC AUC 0.88 [95% CI: 0.85–0.91].

Interpretation:

ML demonstrates favorable diagnostic accuracy for CA; however, findings should be interpreted cautiously due to methodological limitations.

Limitations:

• Inherent methodological limitations in the existing evidence.
• Need for future investigations with diverse cases from broader geographic regions.

Conclusion:

ML shows promise in diagnosing cardiac amyloidosis, but further validation is necessary to advance AI-based assessment tools.

Sources:

• Systematic Review Registration