( events)   Timezone: »  
Tue Dec 14 07:00 AM -- 02:10 PM (PST)
Machine learning from ground truth: New medical imaging datasets for unsolved medical problems.
Katy Haynes · Ziad Obermeyer · Emma Pierson · Marzyeh Ghassemi · Matthew Lungren · Sendhil Mullainathan · Matthew McDermott

This workshop will launch a new platform for open medical imaging datasets. Labeled with ground-truth outcomes curated around a set of unsolved medical problems, these data will deepen ways in which ML can contribute to health and raise a new set of technical challenges.

Machine learning from ground truth: introductory remarks (Introductory remarks)
Transition break (Break)
What are “meaningful” ML datasets and the opportunities and challenges in creating them? (Panel)
Transition break (Break)
Spotlight talks: new datasets and research finalists (Spotlight talks - accepted papers)
Lunch break (Break)
A conversation around medical mysteries, featuring Kevin Volpp & Eric Topol (Discussion panel)
Transition break (Break)
Data science for healthcare in academia and government (Panel)
Transition break (Break)
Data Opportunities: unsolved medical problems and where new data can help (Panel)
Transition break (Break)
Pain Prediction in Neurological Spine Disease Patient Using Digital Phenotyping (Poster)
Assessing Changes in BNP from Chest Radiographs using Convolutional Neural Networks (Poster)
Disability prediction in multiple sclerosis using performance outcome measures and demographic data (Poster)
Transition break (Break)
What problems get funded in computational medicine? (Panel)
Transition break (Break)
Nightingale Open Science platform launch and video demonstration (Live talk)
Transition break (Break)
Closing remarks