When Measurement Conventions Masquerade as Calibration Gains in Cardiac Digital Twins
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors studied how digital heart models (cardiac digital twins) measure heart function from echo images, especially focusing on how different reference methods affect accuracy. They found that what seemed like improvements in error reduction were actually due to differences in the reference standards used, not the models themselves. By carefully aligning their measurements to a consistent heart view and replicating previous studies, they eliminated baseline errors and clarified true model performance. They also developed a protocol to distinguish real measurement improvements from artifacts caused by conventions in data processing.
Cardiac digital twinsEjection fraction (EF)EchocardiographyPhase conditioningObservation operatorsGround-truthBiplane vs. single-plane EFCAMUS datasetEchoNet-DynamicCalibration
Authors
Dang P. M. Cao, Hieu Pham
Abstract
Cardiac digital twins convert clinical images into physiological measurements through observation operators, yet calibration studies often assume a fixed reference convention. Across four shared-backbone echocardiographic EF front-ends, phase conditioning appears to remove CAMUS baseline bias. Matched-reference analysis rejects this gain: singleplane ground-truth EF error is statistically indistinguishable across models, while single-plane ground-truth EF exceeds CAMUS biplane clinical EF by +6.30 points, explaining nearly all baseline bias. A prespecified EchoNet-Dynamic replication, with released data and our extractor aligned to the apical four-chamber plane, removes baseline overestimation and reverses the CAMUS ranking. We also quantify haemodynamic effects, conformal residual-width budgets, and EF-stratum changes, yielding a Convention-Aware EF Audit protocol that separates genuine observation operator calibration from measurement artefacts. GitHub: EjectionFraction-Bias-in-Cardiac-Digital-Twin.git