221 - 230 of 366 results for: CS

Biomedical systems translate complex biological and medical data into computable formats that can be used for tasks such as diagnosis, decision support, or drug discovery. At the core of these systems is the challenge of creating fully computable, machine-actionable models of biomedical information so that knowledge can be shared and reused across different applications. This course explores methods for modeling biomedical systems, including topics in knowledge representation, controlled terminologies, ontologies, interoperability, and symbolic AI. Students will acquire hands-on experiences with several systems and tools, such as Protégé, Fast Healthcare Interoperability Resources (FHIR), and semantic web technologies. Prerequisites: CS106A or equivalent. Basic familiarity with programming, probability, and logic are helpful for taking this course.

Healthcare is one of the most exciting application domains of artificial intelligence, with transformative potential in areas ranging from medical image analysis to electronic health records-based prediction and precision medicine. This course will involve a deep dive into recent advances in AI in healthcare, focusing in particular on deep learning approaches for healthcare problems. We will start from foundations of neural networks, and then study cutting-edge deep learning models in the context of a variety of healthcare data including image, text, multimodal and time-series data. In the latter part of the course, we will cover advanced topics on open challenges of integrating AI in a societal application such as healthcare, including interpretability, robustness, privacy and fairness. The course aims to provide students from diverse backgrounds with both conceptual understanding and practical grounding of cutting-edge research on AI in healthcare. Prerequisites: Proficiency in Python or ability to self-learn; familiarity with machine learning and basic calculus, linear algebra, statistics; familiarity with deep learning highly recommended (e.g. prior experience training a deep learning model).

Capstone Biomedical Data Science experience. Hands-on software building. Student teams conceive, design, specify, implement, evaluate, and report on a software project in the domain of biomedicine. Creating written proposals, peer review, providing status reports, and preparing final reports. Issues related to research reproducibility. Guest lectures from professional biomedical informatics systems builders on issues related to the process of project management. Software engineering basics. Because the team projects start in the first week of class, attendance that week is strongly recommended. Prerequisites: BIOMEDIN 210 or 214 or 215 or 217 or 260. Preference to BMI graduate students. Consent of instructor required.NOTE: For students in the Department of Biomedical Data Science Program, this core course MUST be taken as a letter grade only.

Methods for Reproducible Population Health and Clinical Research is focused on key principles of rigorous and reproducible population health and clinical research. The course provides introductory technical training in collaborative workflows and reproducible programming practices using GitHub and R as well as core topics related to research integrity and scholarly publishing, including academic incentives, authorship, code and data sharing requirements, preregistration, conflicts of interest, and reporting guidelines. Content is designed for health policy, biomedical data science, epidemiology, and computer science graduate students supported by NIH training grants with reproducibility training requirements. Students in such programs should consult with their program director to ensure that this course will fulfill specific requirements of their program. Prerequisite: Basic knowledge of R.

Recent breakthroughs in high-throughput genomic and biomedical data are transforming biological sciences into "big data" disciplines. In parallel, progress in deep neural networks are revolutionizing fields such as image recognition, natural language processing and, more broadly, AI. This course explores the exciting intersection between these two advances. The course will start with an introduction to deep learning and overview the relevant background in genomics and high-throughput biotechnology, focusing on the available data and their relevance. It will then cover the ongoing developments in deep learning (supervised, unsupervised and generative models) with the focus on the applications of these methods to biomedical data, which are beginning to produced dramatic results. In addition to predictive modeling, the course emphasizes how to visualize and extract interpretable, biological insights from such models. Recent papers from the literature will be presented and discussed. Experts in the field will present guest lectures. Students will be introduced to and work with popular deep learning software frameworks. Students will work in groups on a final class project using real world datasets. Prerequisites: College calculus, linear algebra, basic probability and statistics such as CS 109, and basic machine learning such as CS 229. No prior knowledge of genomics is necessary.

Big Data is radically transforming healthcare. To provide real-time personalized healthcare, we need hardware and software solutions that can efficiently store and process large-scale biomedical datasets. In this class, students will learn the concepts of cloud computing and parallel systems' architecture. This class prepares students to understand how to design parallel programs for computationally intensive medical applications and how to run these applications on computing frameworks such as Cloud Computing and High Performance Computing (HPC) systems. Prerequisites: familiarity with programming in Python and R.

While modern machine learning models often achieve superhuman performance on biohealth benchmarks, they frequently fail to generalize to new hospitals, patient populations, or biological contexts. This course investigates the theoretical and practical foundations of generalizable inference in biomedicine, focusing on the critical gap between predictive performance and mechanistic validity. We will examine how to build "world models" that leverage biological structure, enabling generalization beyond the training distribution. Key topics include: inductive biases (biologically relevant priors), causal representation learning (discovering latent state variables), hybrid models (combining mechanistic ODEs with neural networks), learning from interventional data (spanning high-throughput perturbation screens to policy learning from clinical interventions), and causal transportability. Students will engage with cutting-edge literature, dissecting success stories and analyzing "failure modes" where black-box models fall short of clinical reality.

Topics: This is a graduate level introduction to bioinformatics and computational biology, algorithms for alignment of biological sequences and structures, computing with strings, phylogenetic tree construction, hidden Markov models, basic structural computations on proteins, protein structure prediction, molecular dynamics and energy minimization, statistical analysis of 3D biological data, integration of data sources, knowledge representation and controlled terminologies for molecular biology, microarray analysis, chemoinformatics, pharmacogenetics, network biology. Note: For Fall 2021, Dr. Altman will be away on sabbatical and so class will be taught from lecture videos recorded in fall of 2018. The class will be entirely online, with no scheduled meeting times. Lectures will be released in batches to encourage pacing. A team of TAs will manage all class logistics and grading. Firm prerequisite: CS 106B.

Analytic and interpretive methods to optimize the transformation of genetic, genomic, and biological data into diagnostics and therapeutics for medicine. Topics: access and utility of publicly available data sources; types of genome-scale measurements in molecular biology and genomic medicine; linking genome-scale data to clinical data and phenotypes; and new questions in biomedicine using bioinformatics. Case studies. Prerequisites: programming ability at the level of CS 106A and familiarity with statistics and biology.