Biomedical Informatics (BMIN)

BMIN 5010 Introduction to Biomedical and Health Informatics

This course is designed to provide a survey of the major topic areas in medical informatics, especially as they apply to clinical research. Through a series of lectures and demonstrations, students will learn about topics such as medical data standards, electronic health record systems, natural language processing, clinical research informatics, clinical decision support, imaging informatics, public health informatics, consumer health informatics, perioperative informatics, and mental health informatics. It is recommended that students have basic familiarity with biomedical concepts. Non-majors need permission from the department.

Fall

1 Course Unit

BMIN 5020 Database and Data Integration in Biomedical Research

This course is intended to provide in-depth, practical exposure to the design, implementation, and use of databases in biomedical research, and to provide students with the skills needed to design and conduct a research project using primary and secondary data. Topics to be covered include: database architectures, data normalization, database implementation, client-server databases, concurrency, validation, Structured-Query Language (SQL) programming, reporting, maintenance, and security. All examples will use problems or data from biomedical domains. MySQL will be used as the database platform for the course, although the principles apply generally to biomedical research and other relational databases. NOTE: Non-majors need permission from the department

Spring

1 Course Unit

BMIN 5030 Data Science for Biomedical Informatics

In this course, we will use RStudio/R and other freely available software to learn fundamental data science applied to a range of biomedical informatics topics, including those making use of health and genomic data. After completing this course, students will be able to retrieve and clean data, perform explanatory analyses, build and evaluate models to answer scientific questions, and present visually appealing results to accompany data analyses; be familiar with various biomedical data types and resources related to them; and know how to create reproducible and easily shareable results with RStudio/R and GitHub. Recommended prerequisite: Introductory-level statistics course. Familiarity with programming or a willingness to devote time to learn it. NOTE: Non-majors need permission from the department.

Fall

Also Offered As: EPID 6000

1 Course Unit

BMIN 5040 Special Topics in Biomedical and Health Informatics

This course is designed to provide an in-depth look at topics that are of essential importance in biomedical informatics. Each topic will be arranged into thematic modules which will occur in consecutive weeks in the class schedule, with the intention that each module becomes its own "mini-course". The topics for each module may rotate from semester to semester, based on these criteria: Historical importance to the current field of biomedical informatics research and/or practice; Cutting-edge developments in biomedical informatics; Topics not covered in depth in BMIN 5010; Consensus of the program leadership and teaching faculty. It is recommended that students have completed BMIN 5020 and BMIN 5030 prior to enrolling in this course. NOTE: Non-majors need permission from the instructor.

Spring

Also Offered As: EPID 6020

1 Course Unit

BMIN 5060 Standards and Clinical Terminologies

This survey course is designed to provide an overview of health information standards and clinical terminologies. Through a series of lectures, demonstrations, and hands-on exercises, students will learn about topics such as standards, interoperability, data modeling, vocabularies, and health information exchange. It is recommended that students have completed BMIN 5010 prior to enrolling in this course. NOTE: Non-majors need permission from the department.

Spring

1 Course Unit

BMIN 5070 Human Factors

The course will addresses: 1. Sociotechnical and human-centered design in everyday life and in biomedical informatics--especially as applied to medical systems and professional expectations 2. Implementation and optimization of healthcare technology —including tensions among existing vs revised workflows, new software vs legacy systems, vendor software vs need for new builds, customization, retrofits, dongles, etc; 3. Evaluation and measurement of usability as applied to healthcare technology within the evolving complexities of medical systems, organizational hierarchies, professional norms, allocation of resources, and market realities; 4. Implications of healthcare technology and AI for medical ethics, changing disease and treatment protocols, government policy, cybersecurity, and advocacy. It is recommended that students have completed BMIN 5060 prior to enrolling in this course. NOTE: Non-majors need permission from the department.

Fall

0.5 Course Units

BMIN 5090 Consumer and Personal Health Informatics

This course is designed to develop intelligent consumers, managers, and researchers of telehealth and personal health/ consumer health informatics systems through guided exploration into the components of such systems. The course is designed to introduce many of the challenges facing designers and managers of telehealth/ mHealth and remote health care delivery networks. The spectrum of activity ranging from research into implications of system design for applications that bridge geographic distance to the development of practical applications to promote patient engagement is considered in both historical context and in case studies. The current status and future trends of this emerging domain are reviewed. It is recommended that students have some exposure to health care or health systems prior to enrolling in this course. NOTE: Non-majors need permission from the department.

Fall

Also Offered As: NURS 5290

1 Course Unit

BMIN 5100 Clinical Research Informatics in the Cloud: Analytic Workflows and Infrastructure

Machine learning, analysis, and meaningful visualizations can provide significant insights into clinical research datasets. One of the challenges is to make these tools, and workflows available at scale in a meaningful way for clinicians, data scientists, and patients. In this course, we will focus on cloud-based mechanisms and infrastructure to make analysis workflows broadly available to a wide range of potential users. Students will implement an analytic workflow related to a clinical research dataset and ultimately deploy the workflow as a publicly available service on the internet using AWS services. We will discuss all components related to the development life-cycle of cloud based analytic services including testing, logging, deploying infrastructure, APIs, front-end development and the value of doing research in the cloud. It is expected that students are comfortable with Python coding and have taken a data science class prior to enrolling in this course. Pre-requisites: - Students should have significant experience with programming in Python. - BMIN 5030 or BMIN 5200 or equivalent. - Students are interested in learning to work within the AWS environment.

Prerequisite: BMIN 5030 OR BMIN 5200

1 Course Unit

BMIN 5110 Biomedical Informatics Methods for Learning Health Systems

This course provides an introduction to the concepts and principles of learning health systems, focusing on the roles and methods of biomedical informatics in the data-knowledge-practice learning cycle that is the hallmark of such systems. Topics to be included in the course are history of health systems; information systems analysis and design as these apply to learning health systems; methods for integrating data from heterogeneous sources; analytic methods for establishing evidence and evaluating its usefulness in improving patient outcomes; and, working with teams in the learning health system context. There is a strong emphasis on applying these techniques to real-world issues with clinical and clinical research information systems. These include the electronic health record, information systems in clinical specialties, and systems to support the management of data used for clinical research and healthcare administration. This course is required for all MBMI students. Recommended prerequisite: BMIN 5010 and BMIN 5030

Spring

1 Course Unit

BMIN 5120 Human Computer Interaction for Healthcare

The course provides a foundation for practical, hands-on application of human computer interaction in the design and implementation of technology-based healthcare applications. Topics will include: 1. Human Computer Interaction history, key concepts, and relation to human factors; 2. Complex applications and multiple methods for design in applications such as electronic health records, mobile applications, and safety event reporting; 3. Practical application of methods such as problem definition, contextual interview, think-aloud protocol, cognitive walkthrough, and usability testing; 3. Artificial Intelligence in healthcare including of Natural Language Processing (NLP) and Large Language Models (LLMs) as tools for documentation and reducing clinician burnout. Students will be expected to conduct a course-long project applying human computer interaction methodologies to a problem to be chosen using problem definition methods addressed in class, as well as completing all reading assignments and presenting one topic to the class. Pre-requisite (required): BMIN 5070 Human Factors

Fall

0.5 Course Units

BMIN 5130 Quantitative Methods for Learning Health Systems Science

This course explores core principles, theories, and methods from epidemiology, causal inference, biostatistics, and data science, with an emphasis on their application to inform, address, and evaluate health systems-focused research questions and interventions. The ideal learner will have a general familiarity with data analysis, electronic medical records, and experience or planned health systems projects, and is likely a doctoral student, post-doctoral researcher, or faculty member; however, interested students may contact the professor to discuss. The course will cover a wide range of topics to enhance students' familiarity, literacy, and critical appraisal skills in health-system-based randomized trials (including cluster and pragmatic trials), quasi-experimental and observational study designs and methods (such as pre/post studies, differences-in-differences, and time series analysis), as well as general considerations related to multivariable regression modeling, measurement error, missing data, predictive modeling, data integration, and related and emerging topics in learning health system science. Additional topics will vary yearly based on the availability of guest lectures and student composition and needs and may include, for example, lectures on advanced methods (such as Bayesian statistics for clinical research and machine learning), scientific and grant writing, informed consent ,and research ethics. Classes will be centered around instructor-led lectures, journal clubs, student-led presentations, case studies, and expert panels.

Fall

Also Offered As: MTR 6280

1 Course Unit

BMIN 5200 Foundations of Artificial Intelligence in Health

Recent advances in artificial intelligence (AI) have revolutionized the practice of scientific and biomedical research. AI is often used interchangeably with the term 'machine learning', which itself is only one of the subfields within AI dealing with the broader concept of inductive reasoning. However, a wealth of key prerequisite topics that focus on deductive reasoning are central to the practice of AI in biomedical informatics. These founding principles and their intersection with biomedical informatics are the focus of this first course on artificial intelligence. This course is divided into modules that cover (1) introductory/background materials, (2) knowledge representation, (3) logic, (4) essentials of rule-based systems, (5) search, (6) information structure and inference, and (7) special topics. These topics offer a global foundation for the branches of AI in biomedicine and support a deeper understanding of inductive reasoning and machine learning. More broadly, we will explore how biomedical data can be organized, represented, interpreted, searched, and applied to derive knowledge, make decisions, and ultimately make predictions while avoiding bias. It is expected that students will be familiar with basic biomedical concepts, terminology, and statistics. Additionally, students should be competent in one or more computer programming languages (Python is preferred), and should be familiar with basic programming concepts including data structures, control flow, and I/O. It is recommended, but not required, that students have taken Introduction to Biomedical Informatics (BMIN 5010) and Data Science for Biomedical Informatics (BMIN 5030). No previous exposure to artificial intelligence is assumed.

Fall

1 Course Unit

BMIN 5210 Advanced Methods and Health Applications in Machine Learning

Machine learning studies how computers learn from data and has enormous potential to impact biomedical research and applications. This course will cover fundamental topics in machine learning, with a focus on applications in biomedical informatics. Specifically, the course will cover: supervised learning methods including linear regression, logistic regression, nearest neighbors, support vector machines, decision trees, and random forests; unsupervised learning topics such as clustering and dimensionality reduction; neural networks and deep learning approaches for both supervised and unsupervised tasks, including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Autoencoders (AE), Generative Adversarial Networks (GAN), Graph Neural Networks (GNN), Transformers, Generative Pretrained Transformers (GPT), Large Language Models (LLM), and emerging areas in generative, trustworthy, and agentic AI; and the application of these machine learning techniques to a variety of biomedical informatics problems through the analysis of genomic, imaging, biomarker, electronic health record, clinical, and other biomedical data. Students are required to have completed a Python Class or have equivalent programming experience. It is recommended that students have basic knowledge in data analysis and biomedical research. Basic knowledge of machine learning, linear algebra, statistics and probability is preferred. NOTE: Non-majors need permission from the instructor.

Fall

1 Course Unit

BMIN 5220 Natural Language Processing for Health

The growing volume of unstructured health-related data presents unparalleled challenges and opportunities for informaticians, clinicians, epidemiologists and other public health researchers that seek to mine the rich information "locked" within free-texts. Clinical records, social media, published literature, transcribed text, among other textual sources are designed for human eyes, but not necessarily for automatic processing. In this class, we will survey the most recent natural language processing methods used for identifying and classifying information present in these sources. The class provides learning of health language processing – that is, the fundamental principles and methods of both natural language processing and machine learning and how they are currently applied in the biomedical domain. The class will focus on real problems in the context of health research where data are inherently biased, e.g., noisy, missing, or extremely imbalanced. Methods for addressing these biases, such as text normalization, rules-based systems, machine learning (supervised, unsupervised, active learning), deep learning, and large language models will be discussed. In-class lectures will be most often taught using Jupyter notebooks and guest speakers presenting how an NLP/ML method was used to solve a driving biomedical use case. This course requires proficiency in python programming and machine learning. NOTE: Non-majors need permission from the instructor.

Spring

1 Course Unit

BMIN 5230 Informatics Prec Med

Spring

1 Course Unit

BMIN 5250 Introduction to Python Programming

This introductory course is designed to provide an overview of the Python programming language including data types, data structures, variables, packages, modules, programming practices, and more. Using lectures and hands-on demonstrations, students will learn how to write Python programs that store, retrieve, represent, transform, analyze, and visualize biomedical and clinical data. Upon completing this introductory course, students will have acquired foundational knowledge using Python to solve problems as well as gained the self-confidence to expand their knowledge of Python well beyond this course. Non-majors need permission from the department.

Fall

1 Course Unit

BMIN 5330 Statistics for Genomics and Biomedical Informatics

BMIN 5330 is an introductory course in probability theory and statistical inference for graduate students in Genomics and Computational Biology. The goal of the course is to provide foundation of basic concepts and tools as well as hands-on practice in their application to problems in genomics. At the completion of the course, students should have an intuitive understanding of basic probability and statistical inference and be prepared to select and execute appropriate statistical approaches in their future research.

Also Offered As: GCB 5330, IMUN 5770

1 Course Unit

BMIN 5490 Exploring Data Science Methods with Health Care Data

The growth and development of electronic health records, genetic information, sensor technologies and computing power propelled health care into the big data era. This course will emphasize data science strategies and techniques for extracting knowledge from structured and unstructured data sources. The course will follow the data science process from obtaining raw data, processing and cleaning, conducting exploratory data analysis, building models and algorithms, communication and visualization, to producing data products. Students will participate in hands-on exercises whenever possible using a clinical dataset.

Spring

Also Offered As: NURS 8490

1 Course Unit

BMIN 6010 Seminar in Advanced Topics in Biomedical Informatics

This course is designed to provide an in-depth look at several topics that are of essential or timely importance in biomedical informatics by examining historic and current peer-reviewed literature. Each topic will be allotted three to five consecutive weeks in the class schedule with the intention that each module becomes its own “mini- course”. The course activities will be organized into two segments. In the first section, we will focus on reviewing, presenting, and writing about primary literature. In the second section, we will also expand our writing to include developing new questions and approaches. For PhD students, they will ultimately prepare a short grant proposal using the NIH application format in the second half of the course. At the end of the semester, we will break the class into two “study sections” where students will review each other’s proposals.

1 Course Unit

BMIN 7990 Independent Study

An opportunity for the biomedical informatics student to become closely associated with a professor to develop a program of independent in-depth study in a subject area in which the professor and student have a common interest that is not covered (or covered in depth) in the biomedical informatics program curriculum. The challenge of the task undertaken must be consistent with the student's academic level. To register for this course, the student and supervising professor jointly submit a detailed proposal to the program Curriculum Committee via the Program Coordinator not later than two weeks before the beginning of the semester. This course is open only to students enrolled in one of the approved Biomedical Informatics programs. The course can be taken for 0.5 or 1.0cu, depending on the depth and breadth of the proposed independent study.

Fall or Spring

0.5-1 Course Unit

BMIN 9900 Capstone

The MBMI program requires that students engage in a mentored Capstone Project in clinical informatics during their final year. This is accomplished in the context of a weekly seminar in which students develop, propose, implement, and present their capstone project. During the semester, students meet with their Capstone Advisor, who is also invited to attend the seminars. The seminar affords both students and advisors the opportunity for cross-fertilization of ideas and skills, and ultimately the honing of projects to a high level of value for the students and the clinical environments in which they conduct their projects. Required Pre-requisite: Minimum of 7 CUs of the required coursework of the MBMI Program

1 Course Unit