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, and consumer health informatics. It is recommended that students have basic familiarity with biomedical concepts.

Close

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.

Close

As a subfield of computer science, artificial intelligence is often used interchangeably with the term ‘machine learning’, which itself is more accurately a subfield of AI dealing with the broader concept of inductive reasoning. However, a wealth of key prerequisite topics that focus on deductive reasoning align with the bulk of biomedical informatics applications being actively utilized today. These founding principles of AI and their intersection with biomedical informatics are the focus of this first course on artificial intelligence. The 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 branches of AI application and research in biomedical domains, including concepts that will later support a deeper understanding of inductive reasoning and machine learning. In a practical sense, this course focuses on how biomedical data can be organized, represented, interpreted, searched, and applied in order to derive knowledge, make decisions, and ultimately make predictions while avoiding bias. It is expected that all students will be somewhat familiar with basic biomedical concepts and terminology, statistics. Additionally, students must be familiar with basic computer programming concepts including data structures, control flow, and I/O. Recommended, but not required, that students have taken Introduction to Biomedical Informatics (BMIN 5010), Data Science for Biomedical Informatics (BMIN 5030), and a programming course (any language). No previous exposure to artificial intelligence is assumed.

Close

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 an application focus on biomedical informatics. Specifically, the course will cover: supervised learning methods such as 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 methods for supervised or unsupervised learning tasks, including Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Auto Encoder (AE), Generative Adversarial Network (GAN), and Graph Neural Network (GNN); and the applications of these machine learning techniques to various biomedical informatics problems via analyzing imaging, biomarker, electronic health record, clinical and/or other biomedical data. The precise topics may vary from year to year based on student interest and developments in the field. Students are required to have completed BMIN 5250 (Python Class) or 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.

Close

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, are all sources 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 (where instances of interest are rare in the data). 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 demonstrated through examination.

Close

Close