The field of remote health monitoring and clinical text analysis is rapidly advancing, with a focus on developing innovative methods for estimating physiological signals from video and text data. Recent research has centered on improving the accuracy and robustness of remote photoplethysmography (rPPG) estimation, particularly in challenging scenarios such as ultra-short video clips. Additionally, there is a growing interest in applying deep learning techniques to clinical text analysis, including multi-disease prediction and treatment effect estimation. Noteworthy papers in this area include those proposing novel frameworks for rPPG estimation, such as periodic video masked autoencoders and periodicity-guided rPPG estimation methods. Other notable works include the development of high-throughput bench-testing platforms for smartphone-based heart rate measurements and the application of dense passage retrieval for patient cohort retrieval in the echocardiography domain. These advancements have the potential to significantly improve the accuracy and efficiency of remote health monitoring and clinical decision-making.