Olga Demler: Catalogue data in Autumn Semester 2024 |
| Name | Ms Olga Demler |
| Address | Professur für Biomedizininformatik ETH Zürich, CAB F 53.1 Universitätstrasse 6 8092 Zürich SWITZERLAND |
| olga.demler@inf.ethz.ch | |
| Department | Computer Science |
| Relationship | Lecturer |
| Number | Title | ECTS | Hours | Lecturers | |||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 263-5057-00L | From Publication to the Doctor's Office  The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar. | 3 credits | 2S + 1A | O. Demler | |||||||||||||||||||||||||||||||||||
| Abstract | This seminar course is designed to provide students with an opportunity to review and critically evaluate recent publications in medical field focusing on examples when CS method or bioinformatics/statistical technique has lead to an instrumentation, technique or drug approved for clinical practice use. | ||||||||||||||||||||||||||||||||||||||
| Learning objective | Throughout the course, students will read and analyze recent publications that demonstrate successful applications and sometimes failures in medicine. Promissing research applications will also be duscussed. The publications will cover a wide range of topics, including drug discovery, image analysis, prognostic models, and learning healthcare. | ||||||||||||||||||||||||||||||||||||||
| Content | The course will be structured as half lecture content and half seminar content. Lectures will review state of the medical practice prior to the discovery, obstacles in moving the field forward, and the need for improvement. Lecture will be followed by the seminar part where students will take turns presenting the assigned publications and leading the discussions. Students‘ presentations will focus on the main findings, and specfic steps taken to translate the finding into clinical practice. Publications will include examples of: • specific CS/bioinformatics/statistics applications that has been brought to „bedside“ – has been approved by European Medicines Agency / Food and Drug Administration (USA) for clinical use or are widely used in medical research; • examples of failures of how a discovery did not translate into an endproduct and why; current active research areas. Covered topics will include some of the following: • Drug discovery: Computer-aided drug discovery has become an integral part of the drug development process, enabling researchers to design and screen large libraries of molecules in silico (i.e., using computer simulations) before synthesizing and testing them in the lab. This has led to the discovery of new drug candidates for a wide range of diseases, including cancer, Alzheimer's disease, and HIV/AIDS. • Genomics: Advances in computational genomics have enabled researchers to analyze and interpret large-scale genomic data, including DNA sequencing data, to identify disease-causing mutations, genetic risk factors, and drug targets. Examples of the development of personalized medicine, where treatments are tailored to an individual's genetic makeup. Examples when drug target identified by genetics has led to approved treatment. • Imaging: Computer vision and image processing techniques have revolutionized medical imaging, enabling researchers to extract quantitative information from medical images that were previously inaccessible. This has led to the development of new diagnostic and prognostic tools for a wide range of diseases, including cancer, cardiovascular disease, and neurological disorders. • Real-world data applications: emulation of clinical trials using electronic health records data. • Large language models: Generating clinical trial protocols using large language models. Natural Language Processing for information extraction and interpretation. • Learning healthcare systems: Advances in data analytics and information technology have enabled the development of learning healthcare systems, which use real-time data from electronic health records, medical devices, and other sources to improve patient outcomes and reduce healthcare costs. This has the potential to transform the way healthcare is delivered, making it more personalized, efficient, and effective. In addition to the presentations, students will also be required to write critical reviews of the assigned publications throughout the course. The reviews will be evaluated based on the students' ability to identify the strengths and weaknesses of the publications and to provide insightful and constructive feedback. | ||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | The course is intended for advanced undergraduate and graduate students with a background in computer science, bioinformatics, or a related field and interest in applying their skills to medical research. This course assumes a working knowledge of R/Python and intermediate statistical analysis, including linear, logistic, survival regressions or ability and interest to learn them outside of the class. | ||||||||||||||||||||||||||||||||||||||
Competencies |
| ||||||||||||||||||||||||||||||||||||||