University of Cambridge > > aac10's list > IBM Watson from Jeopardy! to Healthcare: could a quiz-show winning computer advise your doctor?

IBM Watson from Jeopardy! to Healthcare: could a quiz-show winning computer advise your doctor?

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Ann Copestake.

“Chronic kidney disease for $500 please!” Although medical providers are unlikely to utter these words as they search for appropriate medical information and clinical guidelines to diagnose and manage patients, they may soon have an advanced computer system reading their notes and listening to their conversations with patients. Could IBM ’s automatic question-answering system Watson, which decisively bested the two greatest champions in the quiz show Jeopardy!, be reconfigured to gather evidence for professionals providing your health care? Could it answer questions about the latest medical knowledge, dig up hidden but crucial facts from your health record, and even help diagnose diseases that may have gone unrecognized? Challenges abound, from capturing the much deeper and subtler reasoning that medical reasoning demands, to identifying gaps of information in a patient’s records, and ultimately to transform Watson from a system which competed against people on a quiz show to one which can interactively work with them to better care for your health.

Dr. David Gondek leads the Knowledge Capture and Learning and Medical Adaptation groups for the Watson project, which develop and apply artificial intelligence techniques including natural language processing, machine learning, and knowledge representation and reasoning for the Watson question answering system, focusing on the tasks of analyzing questions, weighing evidence, and evaluating confidence in hypotheses. He was the lead for machine learning and game strategy on the IBM Jeopardy! Challenge to build a computer system capable of winning at the quiz show, Jeopardy!, and is currently working on extending Watson to help support evidence-based decision making in medicine. Dr. Gondek received his B.A. in Mathematics and Computer Science at Dartmouth College and his Ph.D. in Computer Science from Brown University.

Dr. Gondek’s lecture is part of the celebrations of the centenary of Alan Turing (1912-1954) and is sponsored by the programme Public Understanding of Artificial Intelligence (PUAI) of the AISB . Dr. Gondek will also give a talk at the event TiC@Kings taking place at King’s College on Saturday, 18 February 2012, and Sunday, 19 February 2012.

TiC@Kings as well as the special IBM Watson lecture are organized as part of the Alan Turing Year 2012 and sponsored by the King’s College, the Isaac Newton Institute for the Mathematical Sciences, and the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB).

This talk is part of the aac10's list series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity