Ejection fraction (EF) is a crucial metric for assessing cardiac function and diagnosing conditions such as heart failure. Traditionally, EF estimation requires manual tracing and domain expertise, making the process time-consuming and subject to inter-observer variability. Most current deep learning methods for EF prediction are black-box models with limited transparency, which reduces clinical trust. Some post-hoc explainability methods have been proposed to interpret the decision-making process after the prediction is made. However, these explanations do not guide the model’s internal reasoning and therefore offer limited reliability in clinical applications. To address this, we introduce ProtoEFNet, a novel video-based prototype-learning model for continuous EF regression. The model learns dynamic spatio-temporal prototypes that capture clinically meaningful cardiac motion patterns. Additionally, the proposed Prototype Angular Separation (PAS) loss enforces discriminative representations across the continuous EF spectrum. Our experiments on the Echonet-Dynamic dataset show that ProtoEFNet can achieve accuracy on par with its non-interpretable counterpart while providing clinically relevant insight. The ablation study shows the proposed loss boosts the performance with a 2 \(\%\) increase in F1 score from \(77.67\pm 2.68\) to \(79.64\pm 2.10\) . Our source code is available at: https://github.com/DeepRCL/ProtoEF .