Medical Information Management Research Decision Modeling with Multimodal Information Advanced Techniques in Probabilistic Graphical Models Time Critical Decision Modeling Text Mining and Generation of Brain CT Radiology Reports Decision Modeling with Multimodal Information We aim to combine multimodal information, such as text-based, structured, and/or image data, in support of biomedical decision making. The objective of an initial project is to develop an intelligent human organ segmentation system using 3D medical magnetic resonance images (MRIs) to support medical decision making. We have proposed hybrid image processing algorithms, and evaluated them on a set of kidney images. We continue to explore and develop other image processing algorithms and decision support system models. Advanced Techniques in Probabilistic Graphical Models We explore and develop analytical techniques in the realm of probabilistic graphical models and influence diagrams. We are currently working on context-aware probabilistic reasoning, multiple-level probabilistic game representation and knowledge discovery using Bayesian learning. The results are being evaluated in selected prototype applications in biomedicine and e-commerce. Time Critical Decision Modeling We investigate methodologies and build computer-based tools for managing complex decisions under limited resources. Such techniques take into account the dynamic nature of the problem, uncertainties, preferences of decision makers, as well as the time criticality of the problem. They help ensure that the decision models being built are of optimum size for timely recommendations of effective actions. Our ongoing work includes outcome and risk profile analysis, guideline implementation, and learning from imbalanced data in various critical care domains. Text Mining and Generation of Brain CT Radiology Reports With the advances of medical techniques, large amounts of medical data are produced in hospitals every day. However, most of current works are focusing on mining the medical images, whereas very little work has been done for the text information associated with the medical images. Radiology reports contain rich information about the corresponding medical images but are often under mined. Therefore, the present project focuses on information extraction from brain CT (Computer Tomography) radiology reports, text assisted medical image content retrieval, and automatic generation of brain CT reports based on domain knowledge and associated images. Current medical record search systems will benefit from our research so that searching for information is more efficient and convenient. Doctors and radiologists can also be more efficient to conduct their research in the area using the improved system. The automatic generation of reports can give reference to radiologists. Our research will also be helpful to facilitate an education system for junior doctors and researchers in the area.