With almost 20 years of experience, UCLA Medical & Imaging Informatics (MII) is at the heart of multiple efforts on our campus involving biomedical informatics and data science training. We are a core part of the Graduate Program in Biosciences (GPB) Medical Informatics Home Area. MII faculty support a longstanding NIH-funded training program in medical imaging informatics; and newer T32s in biomedical big data, cardiovascular data science, and the UCLA Clinical and Translational Science Institute TL1.We believe students should understand how research can be impactful by being a part of interdisciplinary team science that changes our understanding of disease and ultimately improves patient lives. Through active collaborations in multiple, diverse areas, our trainees have opportunities to participate in cutting-edge research with thought-leaders in science, engineering, and medicine.
training the next generation of biomedical informaticians and data scientists
teaching tomorrow’s leaders to transform healthcare by moving theory into real-world practice
Our innovative, nationally-recognized training programs provide UCLA students novel opportunities for a range of advanced studies for graduate and post-graduate education.
MEDICAL IMAGING INFORMATICS
MII’s signature graduate training program, this T32 supports PhD students interested in new approaches addressing the spectrum of research using imaging (and associated data) to improve the understanding of a disease (e.g., cancer, stroke, diabetes). Individuals in this program are exposed to the role of imaging and other types of observational data (e.g., from electronic health records, EHRs; mobile health, mHealth; etc.) in biomedical research and healthcare. Coursework provides a breadth of understanding across areas of biomedical informatics and data science, and an introduction to cutting-edge computational methods for analysis and clinical decision support (CDS). Research spans from basic science to translational efforts, with examples of technical topics include methodological developments in artificial intelligence (AI) including machine/deep learning and reinforcement learning; medical natural language processing (NLP); CDS evaluation; and emergent digital health areas (e.g., patient portals).
The Integrated Data Science Training in CardioVascular Medicine (iDISCOVER) T32 trains a new generation of cardiovascular informaticians who will lead the development of innovative approaches that inform and enable precision cardiovascular medicine. iDISCOVER provides a cross-campus, interdisciplinary environment for future scientists involved in cutting-edge computational and data science methods; and encourages novel, team science research opportunities for engineering graduate students to work with and learn from leading experts in cardiovascular medicine. iDISCOVER trainees are exposed to the breadth of contemporary biomedical informatics research, and are ultimately prepared to be productive, independent scientists that will participate in shaping the discipline of modern data science-driven cardiovascular research and healthcare.
CTSI BIOMEDICAL INFORMATICS
For physicians interested in additional training, either as part of a clinical informatics fellowship or towards a formal degree (MS, PhD), UCLA’s Clinical and Translational Science Institute TL1 program provides formal training opportunities. Individuals take biomedical informatics and data science coursework with graduate students from engineering and the Medical Informatics Home Area, providing a rich environment for collaborative learning. Projects focus on demonstration implementations, particularly around the EHR, implementation science, and realizing a real-world learning health system
contemporary, interdisciplinary training for the future of biomedical informatics and data science
We offer a number of biomedical informatics and data science courses through MII’s training programs and initiatives. Classes are given annually and cover foundational concepts to provide students with an overview of the field and current methods.
|TITLE & DESCRIPTION
|Introduction to Medical & Imaging Informatics. Weekly seminar providing new students exposure to current topics and research in biomedical informatics. Talks on ongoing research are given by faculty engaged in biomedical informatics and data science research from across UCLA.
|Medical Information Infrastructures & Internet Technologies. Introductory course on networking, communications, and information infrastructures in the healthcare environment. Students are exposed to basic concepts related to networking at several levels: low-level implementation (e.g., services), medium-level (network topologies), and high-level (distributed/cloud computing, web-based services, etc.). Topics cover common medical data protocols and standards/formats (e.g., HL7, DICOM); developments and issues in electronic health records (EHRs) and other types of clinical/biomedical repositories; and new trends in informatics related to computational infrastructure (e.g., mHealth).
|Medical Decision Making. The objective of this course is to understand the statistical fundamentals related to medical decision making, with emphasis on modeling the process using informatics principles and machine learning approaches. The course covers concepts relating to the process of differential diagnosis; a review of basic concepts related to study design, statistics and probability theory;and modeling techniques. Course materials will be in taught in the context of how healthcare decision making processes are conducted.
|Imaging for Medical Informatics. This course covers various aspects of medical imaging physics and informatics. Topics include image signal generation, signal localization, cognitive perception of presented imaging features, noise models, and multiscale interpretations of medical images. Informatics issues emphasize mappings between low-level physical generation phenomena (e.g., nuclear, atomic) to higher-scale environments (e.g., molecular lattices, micro-physiology, and tissue characteristics), looking at generative physical and biological processes that affect image appearance.
|Medical Knowledge Representation. This course covers issues related to knowledge representation from the perspective of medical and imaging informatics. It covers topics related to context free and context sensitive declarative knowledge; probabilistic representations dealing with sequences and cause and effect chains; and methods for free-text document analysis. Lectures on how to represent a clinical observation as well as how to represent an experimental clinical trial are given. All examples are drawn from the medical domain.
|Advances in Medical & Imaging Informatics. This course provides an overview of informatics-based applications of medical imaging with focus on various advances in the field, such as content-based image retrieval, computer-aided detection/diagnosis, and imaging genomics. It includes an introduction to core concepts in information retrieval (IR), reviewing seminal papers on evaluating IR systems and their use in medicine (e.g., teaching files, case-based retrieval, etc.), as well as an examination of specific techniques for image feature extraction and processing, feature representation, indexing and querying, and classification (machine/deep learning). Lectures include a survey of clinical applications of these techniques and discuss ongoing challenges in the field.
|Programming Lab Rotation. This lab provides students an opportunity to appreciate interdisciplinary team science, working together on a project defined by an MII faculty member. Projects change each quarter, providing insight into software development/engineering; evaluation; and other aspects of translational informatics and data science.