News
- All Attendees, including speakers must register to KDD 2020 to access the virtual platform
- Program announced and Speaker lineup published
- Accepted paper list published. See Papers.
- In light of the various challenges due to the pandemic, we have decided to the extend the submission deadline to Jun 15th, 2020. See Updated dates for more details.
- Paper acceptance notification updated to Jul 15, 2020
Overview
Healthcare is, traditionally, a knowledge-driven enterprise with an enormous amount of data - both structured and unstructured. These data can impact positively on the development of data-driven health care including precision medicine and precision public health. However, in the era of big data, the mining of such data in a manner that leads to clinically actionable outcomes remains a challenge. In recent years, large scale medical/clinical datasets, such as “omics” data and radiology reports. are increasingly available. We have also witnessed an increasing number of successful AI/ML applications using such datasets to address problems such as drug repurposing and preliminary screening of radiology reports. In this deep learning era, what are the challenges and opportunities to deploy such solutions in practice? What is the current status of AI/ML applications in healthcare? Can the different facets of trust and explanations drive adoption of such methods in practice? Can knowledge-backed AI lead to more interpretable models? How do data scientists and physicians apply this knowledge in collaboration to further the field and improve healthcare? After witnessing so many great achievements from deep learning lately, we propose to invite world-leading experts from both data science and healthcare to discuss and debate the path forward for practical applications of AI/ML in healthcare, including demos, early work, and critiques on various aspects of actionable and trustworthy AI. More specifically, we plan to attract high-quality original research from emerging areas with significant implications in healthcare and invite open discussions on controversial yet crucial topics regarding healthcare transformation.
Previous Iterations
- DSHealth 2019: 2019 KDD Workshop on Applied Data Science for Healthcare: Bridging the Gap between Data and Knowledge
- MLMH 2018: 2018 KDD Workshop on Machine Learning for Medicine and Healthcare
Program
DSHealth 2020 will be held at
KDD 2020
on August 24, 2019 as a full day virtual workshop.
All attendees, including speakers, will need to register to KDD 2020 to access the virtual conference platform.
All timings below are in
Pacific Standard Time (PST)
Please refer to the KDD 2020 program
for up-to-date changes on timings.
DSHealth Schedule
Venue: Virtual. (Zoom link will be provided in the KDD virtual conference app)
| Start Time | End Time | Title | Speaker |
|---|---|---|---|
| 8:00 am | 8:10 am | Introduction and Welcome | TBD |
| 8:10 am | 9:10 am | Keynote Talk | Jianying Hu, IBM Fellow. |
| 9:10 am | 9:30 am | Spotlight Session 1 (3 mins each) 2: Challenging common bolus advisor for self-monitoring type-I diabetes patients using Reinforcement Learning 3: MCU-Net: A framework towards uncertainty representations for decision support system patient referrals in healthcare contexts 4: User-driven Analysis of Longitudinal Health Data with Hidden Markov Models for Clinical Insights 5: Clinical Recommender System: Predicting Medical SpecialtyDiagnostic Choices with Neural Network Ensembles 7: Local Interpretability of Calibrated Prediction Models: A Case of Type 2 Diabetes Mellitus Screening Test 11: Automatic Deep Learning-based Histopathologic Image Classification |
2: Frédéric Logé, Erwan Le Pennec and Habiboulaye Amadou-Boubacar 3: Nabeel Seedat 4: Bum Chul Kwon 5: Morteza Noshad, Ivana Jankovic and Jonathan Chen 7: Simon Kocbek, Primoz Kocbek, Leona Cilar and Gregor Stiglic 11: Mingyang Pu, Mengjun Tao, Xiaolu Zheng and Chang Yin |
| 9:30 am | 10:00 am | Break | N/A |
| 10:00 am | 11:30 am | Oral Paper Presentations (15 mins each) 14: Transfer Learning for Activity Recognition in Mobile Health 15: Impact of Medical Data Imprecision on Learning Results 17: Customize Deep Learning-based De-Identification Systems Using Local Clinical Notes - A Study of Sample Size 18: Information Extraction of Clinical Trial Eligibility Criteria 21: DeepPseudo: A Deep learning approach based on Pseudo values for Competing Risk Analysis |
14: Yuchao Ma, Andrew Campbell, Diane Cook, John Lach, Shwetak Patel, Thomas Ploetz, Majid Sarrafzadeh, Donna Spruijt-Metz and Hassan Ghasemzadeh 15: Mei Wang, Haiqin Lu and Jianwen Su 17: Xi Yang, Jiang Bian and Yonghui Wu 18: Yitong Tseo, M. I. Salkola, Ahmed Mohamed, Anuj Kumar and Freddy Abnousi 21: Md Mahmudur Rahman and Sanjay Purushotham |
| 11:30 am | 12:00 pm | Spotlight Session 2 (3 mins each) 12: Explicit-Blurred Memory Network for Analyzing Patient Electronic Health Records 13: Identifying patterns in cystic fibrosis physiotherapy using unsupervisedclustering 16: Visualizing Deep Graph Generative Models for Drug Discovery 19: A Canonical Architecture For Predictive Analytics on Longitudinal Patient Records 20: Improved Slice-wise Tumour Detection in Brain MRIs by Computing Dissimilarities between Latent Representations 22: An Enhanced Text Classification to Explore Health based Indian Government Policy Tweets |
12: Prithwish Chakraborty, Fei Wang, Jianying Hu and Daby Sow 13: Tempest A. van Schaik, Olga Liakhovich, Bianca Furtuna, Mihaela Curmei, Emma Raywood, Helen Douglas, Kunal Kapoor, Nicole Filipow, Eleanor Main 16: Karan Yang, Chengxi Zang and Fei Wang 19: Parthasarathy Suryanarayanan, Bhavani Iyer, Prithwish Chakraborty, Bibo Hao, Italo Buleje, Piyush Madan, James Codella, Antonio Foncubierta, Divya Pathak, Sarah Miller, Amol Rajmane, Shannon Harrer, Gigi Yuan-Reed, Daby Sow 20: Alexanda-Ioana Albu, Alina Enescu and Luigi Malagò 22: Aarzoo Dhiman and Durga Toshniwal |
| 12:00 pm | 1:00 pm | Lunch Break | N/A |
| 1:00 pm | 2:00 pm | Keynote Talk | Hamsa Bastani, Asst. Professor, U. Penn |
| 2:00 pm | 2:30 pm | Virtual Poster and Breakout Session | TBD |
| 2:30 pm | 3:00 pm | Break | N/A |
| 3:00 pm | 4:00 pm | Keynote Talk | Peter Walker, Product Manager, DoD. |
| 4:00 pm | 4:55 pm | Panel Discussion: Covid 19 and Data Science |
Jiang Bian (Moderator) Hua Xu Girish Nadkarni Edward Schenck Melissa Haendal Quanquan Gu |
| 4:55 pm | 5:00 pm | Closing Remarks | N/A |
Keynote Talks
Jianying Hu, Ph.D.; IBM Fellow; Global Science Leader, AI for Healthcare; Director, Center for Computational Health; IEEE Fellow, IAPR Fellow
Bio:
Dr. Jianying Hu is IBM Fellow and Global Science Leader, AI for
Healthcare at IBM Research. In this role, Dr. Hu is responsible
for working across IBM Research to define and drive an AI
science leadership strategy for healthcare at IBM.
Dr. Hu also leads the Center for Computational Health at IBM
Research, located in New York and Cambridge. The center
consists of a multidisciplinary team of over 30 Ph.D. and MD
researchers working on applying data science to Healthcare. It
conducts scientific research and technical innovations in the
broad areas of data driven healthcare analytics, with focuses
on predictive analytics, disease modeling, real world evidence
generation, translational informatics, connected health and
computational health behavior.
Dr. Hu has published over 120 peer reviewed scientific papers
and holds 35 patents. She chaired the American Medical
Informatics Association (AMIA) Knowledge Discovery and Data
Mining Working Group from
| Title | Computational Methods for Next Generation Healthcare Slides |
| Time | 8:10 am - 9:10 am |
Hamsa Bastani, Ph.D.; Assistant Professor, Wharton School, University of Pennsylvania
Bio: Hamsa Bastani is an assistant professor in Operations Information and Decisions at the Wharton School, University of Pennsylvania. Her research focuses on developing novel machine learning algorithms for data-driven decision-making, with applications to healthcare operations, pricing, recommendation systems, and social good. Her work has been recognized by the George Nicholson, MSOM, Service Science, and Health Applications Society best student paper awards, the Pierskalla best paper award in healthcare operations, and the early-career People’s Choice award in sustainable operations. She previously completed her PhD at Stanford University, and was a Herman Goldstine postdoctoral fellow at IBM Research.
| Title | Effective Decision-Making in Healthcare with Small Data Slides |
| Time | 1:00 pm - 2:00 pm |
Peter Walker, Ph.D.; Branch Chief Business Products Branch, DoD Joint Artifical Intelligence Center, USA.
Bio: LCDR Peter Walker. Ph. D., is the Branch Chief for the Business Products Branch at the DoD Joint Artificial Intelligence Center. He is an Experienced Project Officer whose portfolio has included topics ranging from basic science and technology, to applied topics. Prior to joining the JAIC, Dr. Walker was a Program Officer at the Office of Naval Research where his portfolio covered topics including data mining for electronic health records and manpower, personnel, training, and information sciences. His current portfolio includes Medical Imaging, Suicide Prevention, Electronic Health Records, and COVID supply chain.
| Title | Understanding the Medical Supply Chain in Support of COVID |
| Time | 3:00 pm - 4:00 pm |
Panel
| Topic | Covid 19 and Data Science |
| Time | 4:00 pm - 4:55 pm |
| Moderator | Jiang Bian |
Accepted Papers
We have accepted 17 papers for presentation at the workshop. Out of these 5 papers have been selected for oral and 12 for spotlight presentations, respectively. The list will be updated with the final camera ready links for the papers (authors should have received instructions on how to submit the camera ready papers).
Oral Presentations
|
#14
Transfer Learning for Activity Recognition in Mobile Health Yuchao Ma, Andrew Campbell, Diane Cook, John Lach, Shwetak Patel, Thomas Ploetz, Majid Sarrafzadeh, Donna Spruijt-Metz and Hassan Ghasemzadeh |
|
#15
Impact of Medical Data Imprecision on Learning Results Mei Wang, Haiqin Lu and Jianwen Su |
|
#17
Customize Deep Learning-based De-Identification Systems Using Local Clinical Notes - A Study of Sample Size Xi Yang, Jiang Bian and Yonghui Wu |
|
#18
Information Extraction of Clinical Trial Eligibility Criteria Yitong Tseo, M. I. Salkola, Ahmed Mohamed, Anuj Kumar and Freddy Abnousi |
|
#21
DeepPseudo: A Deep learning approach based on Pseudo values for Competing Risk Analysis Md Mahmudur Rahman and Sanjay Purushotham |
Spotlight Presentations
Call for Papers
We invite full papers, as well as work-in-progress on the application of data science in healthcare. Topics may include, but not limited to, the following topics (For more information see workshop overview) with special focus on techniques that are aimed at addressing the importance of trustable and actionable AI in healthcare.
- Trustworthiness
- Interpretable healthcare
- Actionable Insights
- Generalizability : multi-site studies
- Federated and privacy preserving Learning
- Behavioral studies
- Ethical AI and accountability
- Nudging and implications
- Multidisciplinary studies on Healthcare
- Demos of practical applications
- Platforms for enabling scalable studies for generalizability
Papers must be submitted in PDF format to easychair https://easychair.org/conferences/?conf=dshealth2020 and formatted according to the new Standard ACM Conference Proceedings Template . Papers must be a maximum length of 4 pages, including references.
The program committee will select the papers based on originality, presentation, and technical quality for spotlight and/or poster presentation.
Key Dates
- Paper Submission opens: Apr 20, 2020
- Paper Submission deadline: Jun 15th, 2020
May 20, 2020 - Acceptance Notice: Jul 10, 2020
Jul 03, 2020 - Camera Ready Submission Jul 17, 2020
- Workshop Date: Aug 24, 2020
All deadlines correspond to 11:59 PM Hawaii Standard Time ( HST).
Organizers
- Fei Wang, Cornell University, USA
- Prithwish Chakraborty, IBM Research, USA
- Pei-Yun Sabrina Hsueh, Viome Inc., USA
- Gregor Stiglic, University of Maribor, Slovenia
- Jiang Bian, University of Florida, USA
- Carly Eckert, Kensci Inc. and University of Washington, USA