BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Clinical Natural Language Processing
DTSTART:20190820T110000
DTEND:20190820T120000
DTSTAMP:20260407T134236Z
UID:c446362d5108be1270667b8fe62cda8df1af78b006a1cfde6a1a1fec
CATEGORIES:Conferences - Seminars
DESCRIPTION:Assistant Professor Carsten Eickhoff from the Brown University
 \nClinical research has never been more active and diverse than it is at t
 his moment. Research efforts span national and cultural borders and broad 
 online dissemination of results makes insights available at a global scale
  with ever decreasing latency. In the face of these developments\, individ
 ual researchers and practitioners are confronted with a seemingly intracta
 ble amount of material (approximately 1 Million scholarly articles are new
 ly published in the life sciences each year). While highly trained human e
 xperts excel at making precision diagnoses\, coverage\, especially for unc
 ommon conditions can be greatly improved. In this talk\, we will discuss a
  range of (deep) machine learning techniques that provide automatic clinic
 al decision support on the basis of large-scale data collections. I will p
 resent early and ongoing work on a) Predictive assistants in post-operativ
 e care of cardiac surgery patients\, that serve as early warning systems i
 n case of undesirable and dangerous complications. b) Automatic summarizat
 ion of individually long patient records to obtain concise and topically t
 argeted summaries for physicians. c) Data-driven diagnosis of rare disease
 s that individually occur too infrequently to allow clinical specialists t
 o establish the necessary routine and experience.\n\nBiography\nCarsten is
  an assistant professor of medical and computer science at Brown Universit
 y where he leads the Biomedical AI Lab\, specializing in the development o
 f data science and information retrieval techniques with the goal of impro
 ving patient safety\, individual health and quality of medical care. Befor
 e coming to Brown\, he studied artificial intelligence and machine learnin
 g at the University of Edinburgh\, TU Delft and ETH Zurich. Carsten has au
 thored more than 80 conference and journal articles on topics pertaining t
 o automatic large-scale text processing and retrieval as well as informati
 on extraction from unstructured natural language resources. Aside from his
  academic endeavors\, he is involved in several deep technology startups i
 n the health sector that strive to translate technological innovation to i
 mproved safety and quality of life for patients.\n\n(For your own informat
 ion\, the talk will be recorded and the webcast availlable few days after 
 the talk presentation. Please\, then check the following page for the webc
 ast:  https://www.idiap.ch/en/talks/)
LOCATION:Idiap Research Institute\, Rue Marconi 19\, 1920 Martigny https:/
 /goo.gl/maps/9uhoa
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR