The field of cardiovascular disease diagnosis is witnessing significant advancements with the development of innovative machine learning models and frameworks. Researchers are focusing on improving the accuracy and robustness of automated diagnosis systems, particularly in the analysis of electrocardiogram (ECG) and electroencephalography (EEG) signals. The integration of attention mechanisms, contrastive learning, and generative networks is enabling the development of more effective and generalizable models. Notably, the use of poly-window contrastive learning and temporal prompt alignment is showing promising results in ECG analysis and fetal congenital heart defect classification. Noteworthy papers include: AICRN, which proposes a novel deep learning architecture for interpretable ECG analysis. MCLPD, which introduces a semi-supervised learning framework for EEG-based Parkinson's disease detection. Learning ECG Representations via Poly-Window Contrastive Learning, which presents a poly-window contrastive learning framework for learning robust ECG representations. TPA, which proposes a method leveraging foundation image-text model and prompt-aware contrastive learning for fetal congenital heart defect classification.