"Clinical Text Understanding and Decision Support"

Carsten Eickhoff, ETH Zurich

Tuesday, November 14, 2017 at 12:00 Noon

Room 368 (3rd Floor CIT)

Clinical research has never been more active and diverse than it is at this moment. Research efforts span national and cultural borders and broad online dissemination makes insights available at a global scale with ever decreasing latency. In the face of these developments, individual researchers and practitioners are confronted with a seemingly intractable amount of material (approximately 1 Million scholarly articles are newly published in the life sciences each year). While highly trained human experts excel at making precision diagnoses, coverage, especially for uncommon conditions could be greatly improved. In this talk, we will discuss a range of (deep) machine learning techniques that provide automatic clinical decision support on the basis of large-scale data collections. Concretely, I will present early and ongoing work on a) Patient-centric clinical literature retrieval, automatically identifying research papers, clinical trials and case reports that are relevant given the case at hand. b) Predictive assistants in post-operative care of cardiac surgery patients, that serve as early warning systems in case of undesirable and dangerous complications. c) Data-driven diagnosis of rare diseases that individually occur too infrequently to allow clinical specialists to establish the necessary routine and experience.

To close, I will give a brief outlook on a wider range of future directions towards providing medical professionals with powerful aggregates of their large-scale clinical information resources. In this way, our work facilitates everyday medical practice as well as clinical research beyond their current, perceived limitations, leading to the development of new treatments, and, ultimately, improved patient well-being.

Carsten is a researcher and lecturer at ETH Zurich, Switzerland, specializing in clinical data science and information retrieval. He obtained his Ph.D. in computer science from the Technical University of Delft in the Netherlands and an M.Sc. in artificial intelligence from the University of Edinburgh in Scotland. He has authored more than 50 conference and journal articles on topics pertaining to large-scale text processing and retrieval, crowdsourcing, as well as information extraction from unstructured natural language resources.

Host: Professor Jeff Huang