Bridging the Gap: From Machine Learning Research to Clinical Practice
Tue Dec 14 8:30am -- 5:30pm EST @ NeurIPS 2021 (Virtual)
NeurIPS 2021 Link for Our Virtual World
Poster Session 1 & 2
Round Table Discussion
Overview
Current Machine learning (ML) methods can achieve high levels of performance on clinical data that matches or even exceeds human clinicians, e.g., by leveraging the power of deep neural networks and large data repositories. However, most existing methods are limited: they are either black-box models that are often incomprehensible for physicians and thus deemed too complex or not trustworthy, they show limited robustness and addressing the gap between the ML community and the clinical community remains a challenge for implementing the methods in clinical practice. As a result, the majority of ML research in the medical domain is mostly stalled at the research paper level and remains difficult to act on. To achieve the overarching goal of realizing the promise of cutting-edge ML techniques and bring this exciting research to fruition, we must bridge the gap between research and clinics. In this workshop, we aim to bring together ML researchers and clinicians to discuss the challenges and potential solutions on how to enable the use of state-of-the-art ML techniques in the daily clinical practice and ultimately improve healthcare.
We are specifically interested (but are not limited to) the following areas:
Procedures that bring humans-in-the-loop for auditing ML healthcare systems to improve human performance, machine performance, or both.
Methods that are robust to changes in population, distribution shifts, or other types of biases.
Properties of ML methods/systems to be fulfilled to successfully deploy them in the clinic where the feasibility of these properties should also be taken into account.
Analyses of how to assess the failure modes of ML models for healthcare and reduce over-reliance.
Developing methods for improved interpretability of ML predictions in the context of healthcare.
Translational and implementational aspects: challenges and lessons learned from integrating an ML system into clinical workflow.
The workshop will feature three main sessions, each with two invited talks (from ML and clinical experts), followed by a moderated Q&A with a specific focus and an informal round-table discussion that encourages a broader conversation and open discussions between the audience and the speakers of varying backgrounds. With these interactive sessions, we want to encourage productive exchange between machine learning researchers and clinical experts. There will be two spotlight presentations and poster sessions via gather.town for contributed submissions. One session will be in the middle of the day, and one at the end of the day to enable participation from different time zones.
Invited Speakers / Panelists
Michael Brudno
University of Toronto, CA
Barbara Engelhardt
Princeton University, USA
Sven Wellmann
Children's Hospital, Regensburg, DE
Roy Perlis
Harvard Medical School, USA
Sara Bachmann
Children's Hospital Basel, CH
Joseph Futoma
Apple Inc., USA
Leo Celi
Harvard/MIT, USA
Thomas H. McCoy
Massachusetts General Hospital
Rich Caruana
Microsoft Research, USA
Bram Stieltjes
University Hospital Basel, CH
Denis Vaughan
Boston IVF, USA
Stephanie Hyland
Microsoft Research, UK
Organizers
Harvard University
University of Michigan
Harvard University
Program Committee
We would like to thank the following program committee members for shaping our workshop together! (Names are listed in alphabetic order)
Adam Kortylewski (Johns Hopkins University)
Alexander Marx (ETH Zürich)
Alice Bizeul (ETH Zürich)
Eugene Bykovets (ETH Zürich)
Fabricio Arend Torres (University of Basel)
Fahad Kamran (University of Michigan)
Imant Daunhawer (ETH Zürich)
Laura Manduchi (ETH Zürich)
Maxim Samarin (University of Basel)
Meera Krishnamoorthy (University of Michigan)
Monika Nagy-Huber (University of Basel)
Ričards Marcinkevičs (ETH Zürich)
Sarah Jabbour (University of Michigan)
Thomas Sutter (ETH Zürich)
Trenton Chang (University of Michigan)
Vitali Nesterov (University of Basel)
Xinliang Frederick Zhang (University of Michigan)
Sponsors
GlaxoSmithKline (GSK) is a science-led global healthcare company with a special purpose to improve the quality of human life by helping people do more, feel better, live longer. Every day, we help improve the health of millions of people around the world by discovering, developing and manufacturing innovative medicines, vaccines and consumer healthcare products. We are building a stronger purpose and performance culture underpinned by our values and expectations - so that together we can deliver extraordinary impact for patients and consumers.
GSK uses AI to discover transformational medicines. AI is the key to interpret genetic datasets so we can understand the 'language' of the cell and develop medicines with a higher probability of success.
We are pleased to support this award for the best paper, describing innovative machine learning research focused on bridging the gap between machine learning research and application in clinical practice.
Note:
GSK is not involved in the selecting the winning paper.
To claim the award, the lead author of the paper selected will be required to complete the appropriate brief documentation in accordance with healthcare regulatory best practice and compliance requirements.