The field of medical diagnosis and analysis is witnessing significant advancements with the integration of multimodal AI approaches. Recent research has focused on developing innovative frameworks and models that can effectively analyze and interpret complex medical data, including images, text, and time series signals. One of the key trends in this area is the use of large language models (LLMs) in combination with other AI techniques, such as computer vision and signal processing, to improve the accuracy and reliability of medical diagnosis. For instance, researchers have proposed novel architectures that leverage LLMs to analyze medical images, such as whole-slide pathology images, and generate informative reports. Another area of research is the application of multimodal AI to analyze eye and head movements to gain insights into skill development in clinical settings. Furthermore, there is a growing interest in using causal graph fuzzy LLMs for time series forecasting and analyzing abnormal emergence in service ecosystems. Overall, these advancements have the potential to revolutionize the field of medical diagnosis and analysis, enabling more accurate and personalized healthcare. Noteworthy papers in this area include the proposal of Alzheimer's Disease Prediction with Cross-modal Causal Intervention (ADPC), which implicitly eliminates confounders through causal intervention, and the development of SpiroLLM, a multimodal large language model that can understand spirogram time series with clinical validation in COPD reporting.