Workshop
Bridging the Gap: from Machine Learning Research to Clinical Practice
Julia Vogt 路 Ece Ozkan 路 Sonali Parbhoo 路 Melanie F. Pradier 路 Patrick Schwab 路 Shengpu Tang 路 Mario Wieser 路 Jiayu Yao
Tue 14 Dec, 5:30 a.m. PST
Machine learning (ML) methods often achieve superhuman performance levels, however, most existing machine learning research in the medical domain is stalled at the research paper level and is not implemented into daily clinical practice. 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 by trying to answer questions like: what are the procedures that bring humans-in-the-loop for auditing ML systems for healthcare? Are the proposed ML methods robust to changes in population, distribution shifts, or other types of biases? What should the ML methods/systems fulfill to successfully deploy them in the clinics? What are failure modes of ML models for healthcare? How can we develop methods for improved interpretability of ML predictions in the context of healthcare? And many others. We will further discuss translational and implementational aspects and talk about challenges and lessons learned from integrating an ML system into clinical workflow.
Schedule
Tue 5:30 a.m. - 5:40 a.m.
|
Opening remarks by the organizers
(
Short intro
)
>
SlidesLive Video |
馃敆 |
Tue 5:40 a.m. - 6:00 a.m.
|
Invited talk (Clinical) - Sven Wellmann
(
Invited talk
)
>
SlidesLive Video |
Sven Wellmann 馃敆 |
Tue 6:00 a.m. - 6:01 a.m.
|
Platform remark
(
Platform remark
)
>
|
馃敆 |
Tue 6:05 a.m. - 6:25 a.m.
|
Invited talk (ML) - Michael Brudno
(
Invited talk
)
>
SlidesLive Video |
Michael Brudno 馃敆 |
Tue 6:30 a.m. - 7:10 a.m.
|
Moderated Q&A (Topic: pediatrics)
(
Moderated Q&A
)
>
SlidesLive Video |
馃敆 |
Tue 7:10 a.m. - 7:24 a.m.
|
Break
|
馃敆 |
Tue 7:24 a.m. - 7:25 a.m.
|
Platform remark
(
Platform remark
)
>
|
馃敆 |
Tue 7:25 a.m. - 8:10 a.m.
|
Round-table Discussion in gather.town ( Round table discussion ) > link | 馃敆 |
Tue 8:10 a.m. - 8:11 a.m.
|
Platform remark
(
Platform remark
)
>
|
馃敆 |
Tue 8:15 a.m. - 8:35 a.m.
|
Spotlight Presentations
(
Spotlight
)
>
|
馃敆 |
Tue 8:35 a.m. - 8:36 a.m.
|
Platform remark
(
Platform remark
)
>
|
馃敆 |
Tue 8:40 a.m. - 9:25 a.m.
|
Poster Session 1 ( Poster Session ) > link | 馃敆 |
Tue 9:30 a.m. - 10:14 a.m.
|
Lunch Break
|
馃敆 |
Tue 10:14 a.m. - 10:15 a.m.
|
Platform remark
(
Platform remark
)
>
|
馃敆 |
Tue 10:15 a.m. - 10:35 a.m.
|
Invited talk (ML) - Rich Caruana
(
Invited talk
)
>
SlidesLive Video |
Rich Caruana 馃敆 |
Tue 10:35 a.m. - 10:36 a.m.
|
Platform remark
(
Platform remark
)
>
|
馃敆 |
Tue 10:40 a.m. - 11:00 a.m.
|
Invited talk (Clinical) - Bram Stieltjes
(
Invited talk
)
>
|
Bram Stieljes 馃敆 |
Tue 11:05 a.m. - 11:45 a.m.
|
Moderated Q&A (Topic: Interpretable ML for Personalised Medicine)
(
Moderated Q&A
)
>
|
馃敆 |
Tue 11:45 a.m. - 11:59 a.m.
|
Break
|
馃敆 |
Tue 11:59 a.m. - 12:00 p.m.
|
Platform remark
(
Platform remark
)
>
|
馃敆 |
Tue 12:00 p.m. - 12:20 p.m.
|
Invited talk (Clinical) - Roy Perlis
(
Invited talk
)
>
SlidesLive Video |
Roy Perlis 馃敆 |
Tue 12:20 p.m. - 12:21 p.m.
|
Platform remark
(
Platform remark
)
>
|
馃敆 |
Tue 12:25 p.m. - 12:45 p.m.
|
Invited talk (ML) - Barbara Engelhardt
(
Invited talk (ML)
)
>
SlidesLive Video |
Barbara Engelhardt 馃敆 |
Tue 12:50 p.m. - 1:30 p.m.
|
Moderated Q&A (Topic: synergies and discordances between EHRs and biomedical data)
(
Moderated Q&A
)
>
SlidesLive Video |
馃敆 |
Tue 1:30 p.m. - 1:31 p.m.
|
Platform remark
(
Platform remark
)
>
|
馃敆 |
Tue 1:35 p.m. - 2:15 p.m.
|
Poster Session 2 ( Poster Session ) > link | 馃敆 |
Tue 2:20 p.m. - 2:30 p.m.
|
Closing remarks by the organizers
(
Short intro
)
>
SlidesLive Video |
馃敆 |
Tue 2:30 p.m. - 2:30 p.m.
|
Workshop ends
|
馃敆 |
-
|
Survival-oriented embeddings for improving accessibility to complex data structures
(
Poster
)
>
|
Tobias Weber 路 Bernd Bischl 路 David Ruegamer 馃敆 |
-
|
GAM Changer: Editing Generalized Additive Models with Interactive Visualization
(
Poster
)
>
|
Zijie Jay Wang 路 Harsha Nori 路 Duen Horng Chau 路 Jennifer Wortman Vaughan 路 Rich Caruana 馃敆 |
-
|
What Do You See in this Patient? Behavioral Testing of Clinical NLP Models
(
Poster
)
>
|
Betty van Aken 路 Alexander L枚ser 馃敆 |
-
|
Longitudinal Fairness with Censorship
(
Poster
)
>
|
Wenbin Zhang 路 Jeremy Weiss 馃敆 |
-
|
A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources
(
Poster
)
>
|
Xiaoqing Tan 馃敆 |
-
|
Interpretable Data Analysis for Bench-to-Bedside Research
(
Poster
)
>
|
Zohreh Shams 路 Botty Dimanov 路 Nikola Simidjievski 路 Helena Andres-Terre 路 Paul Scherer 路 Ur拧ka Matja拧ec 路 Mateja Jamnik 路 Pietro Li贸 馃敆 |
-
|
Transferring Multi-Omics Survival Models to Clinical Settings Through Linear Surrogate Models
(
Poster
)
>
|
David Wissel 馃敆 |
-
|
Contextualized Representation Learning in Biomedical Word Sense Disambiguation
(
Poster
)
>
|
Mozhgan saeidi 馃敆 |
-
|
Rethinking Generalization Performance of Surgical Phase Recognition with Expert-Generated Annotations
(
Poster
)
>
|
Seungbum Hong 路 Jiwon Lee 路 Bokyung Park 路 Ahmed Abbas Alwusaibie 路 Anwar Hudaish Alfadhel 路 SungHyun Park 路 Woo Jin Hyung 路 Min-Kook Choi 馃敆 |
-
|
Interpretable Electrocardiogram Mapping to Detect Decreased Cardiac Contraction
(
Poster
)
>
|
Hirotoshi Takeuchi 路 Mitsuhiko Nakamoto 馃敆 |
-
|
Identification of Subgroups With Similar Benefits in Off-Policy Policy Evaluation
(
Poster
)
>
|
Ramtin Keramati 路 Omer Gottesman 路 Leo Celi 路 Finale Doshi-Velez 路 Emma Brunskill 馃敆 |
-
|
Designing A Clinically Applicable Deep Recurrent Model to Identify Neuropsychiatric Symptoms in People Living with Dementia Using In-Home Monitoring Data
(
Poster
)
>
|
Francesca Palermo 路 Ramin Nilforooshan 路 David Sharp 路 Payam Barnaghi 馃敆 |
-
|
Type Safety and Disambiguation of Depression
(
Poster
)
>
|
Michael A Yee 馃敆 |
-
|
Automated Supervised Feature Selection for Differentiated Patterns of Care
(
Poster
)
>
|
Catherine Wanjiru 路 William Ogallo 路 Girmaw Abebe Tadesse 路 Charles Wachira 路 Isaiah Onando Mulang' 路 Aisha Walcott-Bryant 馃敆 |
-
|
Harmonizing Attention: Attention Map Consistency For Unsupervised Fine-Tuning
(
Poster
)
>
|
Ali Mirzazadeh 路 Florian Dubost 路 Daniel Fu 路 Khaled Saab 路 Christopher Lee-Messer 路 Daniel Rubin 馃敆 |
-
|
Post-discovery Analysis of Anomalous Subsets
(
Poster
)
>
|
Isaiah Onando Mulang' 路 William Ogallo 路 Girmaw Abebe Tadesse 路 Aisha Walcott-Bryant 馃敆 |
-
|
Robust Interpretable Rule Learning to Identify Expertise Transfer Opportunities in Healthcare
(
Poster
)
>
|
Willa Potosnak 路 Sebastian Caldas Rivera 路 Gilles Clermont 路 Kyle Miller 路 Artur Dubrawski 馃敆 |
-
|
Predicting Sufficiency for Hemorrhage Resuscitation Using Non-invasive Physiological Data without Reference to Personal Baselines
(
Poster
)
>
|
Xinyu Li 路 Michael Pinsky 路 Artur Dubrawski 馃敆 |
-
|
Neuroweaver: Towards a Platform for Designing Translatable Intelligent Closed-loop Neuromodulation Systems
(
Poster
)
>
|
Parisa Sarikhani 路 Hao-Lun Hsu 路 Sean Kinzer 路 Hadi Esmaeilzadeh 路 Babak Mahmoudi 馃敆 |
-
|
A Conservative Q-Learning approach for handling distributional shift in sepsis treatment strategies
(
Poster
)
>
|
Pramod Kaushik 路 Raju Bapi 馃敆 |