`

Timezone: »

 
Workshop
Machine Learning for Health (ML4H): Advancing Healthcare for All
Stephanie Hyland · Allen Schmaltz · Charles Onu · Ehi Nosakhare · Emily Alsentzer · Irene Y Chen · Matthew McDermott · Subhrajit Roy · Benjamin Akera · Dani Kiyasseh · Fabian Falck · Griffin Adams · Ioana Bica · Oliver J Bear Don't Walk IV · Suproteem Sarkar · Stephen Pfohl · Andrew Beam · Brett Beaulieu-Jones · Danielle Belgrave · Tristan Naumann

Fri Dec 11 06:00 AM -- 04:20 PM (PST) @ None
Event URL: https://ml4health.github.io/2020/ »

The application of machine learning to healthcare is often characterised by the development of cutting-edge technology aiming to improve patient outcomes. By developing sophisticated models on high-quality datasets we hope to better diagnose, forecast, and otherwise characterise the health of individuals. At the same time, when we build tools which aim to assist highly-specialised caregivers, we limit the benefit of machine learning to only those who can access such care. The fragility of healthcare access both globally and locally prompts us to ask, “How can machine learning be used to help enable healthcare for all?” - the theme of the 2020 ML4H workshop.

Participants at the workshop will be exposed to new questions in machine learning for healthcare, and be prompted to reflect on how their work sits within larger healthcare systems. Given the growing community of researchers in machine learning for health, the workshop will provide an opportunity to discuss common challenges, share expertise, and potentially spark new research directions. By drawing in experts from adjacent disciplines such as public health, fairness, epidemiology, and clinical practice, we aim to further strengthen the interdisciplinarity of machine learning for health.

See our workshop for more information: https://ml4health.github.io/

Fri 6:00 a.m. - 6:10 a.m.
Opening Remarks (Opening)
Fri 6:10 a.m. - 6:30 a.m.

Large scale characterization for health equity assessment

Noemie Elhadad
Fri 6:30 a.m. - 6:50 a.m.
  

Health disparities in the United States are one of the largest factors in reducing the health of the population. Disparities means some groups have lower life expectancy, are dying at higher rates from COVID-19, and utilize less mental health services, to name just a few examples. The future of medicine will be based on Artificial Intelligence and new technological platforms that promise to improve outcomes and reduce cost. Our role as AI researchers should be to ensure that these new technologies also reduce health disparities. In this talk I will describe recent work showing how we can work to reduce health disparities in the future of medicine. By ensuring that our task, datasets, algorithms and evaluations are equitable and representative of all types of patients, we can ensure that the research we develop will reduce health disparities.

Mark Dredze
Fri 6:50 a.m. - 7:25 a.m.

Please use the video feed above to watch the panel. Post your questions at any time in RocketChat.

Fri 7:25 a.m. - 7:40 a.m.
 link »

Click on "Open Link" to mingle with other attendees in the Gather.Town Lounge

Fri 7:40 a.m. - 8:00 a.m.

Please use the video feed above to watch this talk. Post your questions at any time in RocketChat.

Fri 8:00 a.m. - 8:10 a.m.
Spotlight A-1: "ML4H Auditing: From Paper to Practice" (Spotlights)   
Luis Oala
Fri 8:10 a.m. - 8:20 a.m.
Spotlight A-2: "The unreasonable effectiveness of Batch-Norm statistics in addressing catastrophic forgetting across medical institutions" (Spotlights)   
Sharut Gupta
Fri 8:20 a.m. - 8:30 a.m.
Spotlight A-3: "DeepHeartBeat: Latent trajectory learning of cardiac cycles using cardiac ultrasounds" (Spotlights)   
Fabian Laumer
Fri 8:30 a.m. - 9:30 a.m.
 link »

Click on "Open Link" to attend the poster session in Gather.Town

Fri 9:30 a.m. - 12:30 p.m.
 link »

Click on "Open Link" to mingle with other attendees in the Gather.Town Lounge

Fri 12:30 p.m. - 12:50 p.m.
  

The year 2020 has brought into focus a second pandemic of social injustice and systemic bias with the disproportionate deaths observed for minority patients infected with COVID. As we observe an increase in development and adoption of AI for medical care, we note variable performance of the models when tested on previously unseen datasets, and also bias when the outcome proxies such as healthcare costs are utilized. Despite progressive maturity in AI development with increased availability of large open source datasets and regulatory guidelines, operationalizing fairness is difficult and remains largely unexplored. In this talk, we review the background/context for FAIR and UNFAIR sequelae of AI algorithms in healthcare, describe practical approaches to FAIR Medical AI, and issue a grand challenge with open/unanswered questions.

Judy Gichoya
Fri 12:50 p.m. - 1:10 p.m.
Ziad Obermeyer: Explaining Pain Disparities (Keynote)   
Ziad Obermeyer
Fri 1:10 p.m. - 1:45 p.m.

Please use the video feed above to watch this panel. Post your questions at any time in RocketChat.

Fri 1:45 p.m. - 1:55 p.m.
Spotlight B-1: "A Bayesian Hierarchical Network for Combining Heterogeneous Data Sources in Medical Diagnoses" (Spotlights)   
Claire Donnat
Fri 1:55 p.m. - 2:05 p.m.
Spotlight B-2: "Assessing racial inequality in COVID-19 testing with Bayesian threshold tests" (Spotlights)   
Emma Pierson
Fri 2:05 p.m. - 2:15 p.m.
Spotlight B-3: "EEG-GCNN: Augmenting Electroencephalogram-based Neurological Disease Diagnosis using a Domain-guided Graph Convolutional Neural Network" (Spotlights)   
Neeraj Wagh
Fri 2:15 p.m. - 3:15 p.m.
 link »

Click on "Open Link" to attend the poster session in Gather.Town

Fri 3:15 p.m. - 3:30 p.m.
 link »

Click on "Open Link" to mingle with other attendees in the Gather.Town Lounge

Fri 3:30 p.m. - 3:50 p.m.
  

Recent advances in training deep learning algorithms have demonstrated potential to accommodate the complex variations present in medical data. In this talk, I will describe technical advancements and challenges in the development and clinical application of deep learning algorithms designed to interpret medical images. I will also describe advances and current challenges in the deployment of medical imaging deep learning algorithms into practice. This talk presents work that is jointly done with Matt Lungren, Curt Langlotz, Nigam Shah, and several more collaborators.

Andrew Ng
Fri 3:50 p.m. - 4:10 p.m.

Please use the video feed above to watch this panel. Post your questions at any time in RocketChat.

Fri 4:10 p.m. - 4:20 p.m.
Closing remarks (Closing)

Author Information

Stephanie Hyland (Microsoft Research)
Allen Schmaltz (Harvard University)
Charles Onu (McGill University)
Ehi Nosakhare (Microsoft)
Emily Alsentzer (MIT)
Irene Y Chen (MIT)

Irene is a PhD student at MIT focusing on applications on health care and fairness. She did her undergrad at Harvard where I studied applied math and computational engineering. Before starting at MIT, she worked for two years at Dropbox as a data scientist and machine learning engineer.

Matthew McDermott (MIT)
Subhrajit Roy (Google)
Benjamin Akera (Mila - Quebec AI Institute)
Dani Kiyasseh (University of Oxford)
Fabian Falck (University of Oxford)
Griffin Adams (Columbia University)

I am an NLP researcher with a focus on text generation of clinical data. After completing a masters in Computational Data Science at Carnegie Mellon's Language Technologies Institute (LTI), I worked at Flatiron Health where I developed and deployed algorithms to extract clinical information from unstructured oncology data at scale. I introduced deep learning to the company and architected a generalized model that improves the status quo of information extraction from large-scale longitudinal clinical notes. I am now a computer science PhD student at Columbia University with Noemie Elhadad. My research focuses on controllable factual text generation of clinical narratives.

Ioana Bica (University of Oxford)
Oliver J Bear Don't Walk IV (Columbia University)
Suproteem Sarkar (Harvard)
Stephen Pfohl (Stanford University)
Andrew Beam (Harvard)
Brett Beaulieu-Jones (Harvard Medical School)
Danielle Belgrave (Microsoft Research)
Tristan Naumann (Microsoft Research)

More from the Same Authors