The field of electronic health record (EHR) analysis is rapidly evolving, with a focus on developing innovative methods to extract insights from complex and heterogeneous data. Recent research has emphasized the importance of integrating multiple modalities, such as clinical notes, laboratory results, and demographic information, to improve predictive modeling and risk stratification. Time-aware modeling and temporal graph neural networks have shown promise in capturing longitudinal dynamics and clinical knowledge, enabling more accurate predictions and personalized care. Noteworthy papers in this area include: MedM2T, which proposes a time-aware multimodal framework for EHR analysis, achieving state-of-the-art performance in cardiovascular disease prediction and in-hospital mortality prediction. KAT-GNN, which introduces a knowledge-augmented temporal graph neural network for risk prediction, demonstrating strong results in coronary artery disease prediction and in-hospital mortality prediction. ProQ-BERT, which presents a transformer-based framework for predicting chronic kidney disease progression, consistently outperforming existing methods and achieving high ROC-AUC and PR-AUC scores.