Workshop Date: 2022, August 14
Follow us on Twitter
Machine learning (ML) and artificial intelligence (AI) are powerful tools in data mining and knowledge discovery in healthcare. There is a wide array of use-cases that range from the analysis of Electronic Health Records (EHR) and drug discovery to digital pathology and the analysis of high-throughput sequencing data. However, a wider uptake of AI/ML systems by practitioners, especially in a clinical environment such as Clinical Decision Support System, is slowed down by a distinct set of requirements. These include a need for a stringent evaluation of AI/ML systems not only in terms of safety of intended use of these algorithms and the ability to account for and communicate uncertainty. In addition, both regulatory and the clinical practitioners need transparency of the AI/ML enabled systems, including considering usability factors during development, reliability of the deployment, interpretability of the AI/ML models, which overall calls for a human-centred approach for the assurance of safety and effectiveness have been proving challenging. 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.
DSHealth 2022 will be held
on August 14, 2022. See detailed schedule below.
Selected papers will be invited to publish in
Journal of Healthcare Informatics Research
Please refer to the KDD 2022 program for up-to-date changes on venues and timings.
|Aug 14, 08:00 am - 12:00 pm||Session 1|
|8:00 am - 8:10 am||Introduction|
|8:10 am - 09:10 am||Invited Talk: Li Zhou|
|09:10 am - 09:40 am||Lightening Talk (9 papers)
#161: Distillation to Enhance the Portability of Risk Models Across Institutions with Large Patient Claims Databases
#744: FedPseudo: Pseudo value-based Deep Learning Models for Federated Survival Analysis
#2322: Joint Application of the Target Trial Causal Framework and Machine Learning Modeling to Optimize Antibiotic Therapy: Use Case on Acute Bacterial Skin and Skin Structure Infections due to Methicillin-resistant Staphylococcus aureus
#3660: Pseudo value-based Deep Neural Networks for Multistate Survival Analysis
#4905: Using Interpretable Machine Learning to Predict Maternal and Fetal Outcomes
#6154: Variational Temporal Deconfounder for Individualized Treatment Effect Estimation from Longitudinal Observational Data
#6186: Towards Neural Numeric-To-Text Generation From Temporal Personal Health Data
#6772: Exploring Runtime Decision Support for Trauma Resuscitation
#7099: Boosting the interpretability of clinical risk scores with intervention predictions
#9095: Flexible Group Fairness Metrics for Survival Analysis
|9:40 am - 10:00 am||Break + Poster|
|10:00 am - 11:00 am||Invited talk: Jimeng Sun|
|11:00 am - 12:00 am||Invited Talk: Lina Sulieman|
|12:00 pm - 1:00 pm||Lunch Break|
|Aug 14, 1:00 pm - 5:00 pm||Session 2|
|1:00 pm - 2:00 pm||Invited Talk: Michel Friesenhahn|
|2:00 pm - 3:00 pm||Invited Talk: Victor Garcia|
|3:00 pm - 3:30 pm||Break|
|3:30 pm - 4:00 pm||Poster|
|4:00 pm - 4:50 pm||Panel discussion|
|4:50 pm - 5:00 pm||Closing session|
We have accepted 10 papers for presentation at the workshop. All papers will be presented as posters within the workshop. PDF version of the final papers, if provided by the authors, are hyperlinked below.
|#161 Distillation to Enhance the Portability of Risk Models Across Institutions with Large Patient Claims Databases Steve Nyemba, Chao Yan, Ziqi Zhang, Amol Rajmane, Pablo Meyer, Prithwish Chakraborty and Bradley Malin|
|#744 FedPseudo: Pseudo value-based Deep Learning Models for Federated Survival Analysis Md Mahmudur Rahman and Sanjay Purushotham|
|#2322 Joint Application of the Target Trial Causal Framework and Machine Learning Modeling to Optimize Antibiotic Therapy: Use Case on Acute Bacterial Skin and Skin Structure Infections due to Methicillin-resistant Staphylococcus aureus Inyoung Jun, Simone Marini, Christina A. Boucher, J. Glenn Morris, Jiang Bian and Mattia Prosperi|
|#3660 Pseudo value-based Deep Neural Networks for Multistate Survival Analysis Md Mahmudur Rahman and Sanjay Purushotham|
|#4905 Using Interpretable Machine Learning to Predict Maternal and Fetal Outcomes Tomas Bosschieter, Zifei Xu, Hui Lan, Ben Lengerich, Harsha Nori, Kristin Sitcov, Vivienne Souter and Rich Caruana|
|#6154 Variational Temporal Deconfounder for Individualized Treatment Effect Estimation from Longitudinal Observational Data Zheng Feng, Mattia Prosperi and Jiang Bian|
|#6186 Towards Neural Numeric-To-Text Generation From Temporal Personal Health Data Jonathan Harris and Mohammed Zaki|
|#6772 Exploring Runtime Decision Support for Trauma Resuscitation Keyi Li, Sen Yang, Travis M. Sullivan, Randall S. Burd and Ivan Marsic|
|#7099 Boosting the interpretability of clinical risk scores with intervention predictions Eric Loreaux, Ke Yu, Jonas Kemp, Martin Seneviratne, Christina Chen, Steve Yadlowsky, Alexander D'Amour and Ming-Jun Chen|
|#9095 Flexible Group Fairness Metrics for Survival Analysis Raphael Sonabend, Florian Pfisterer, Alan Mishler, Moritz Schauer, Lukas Burk and Sebastian Vollmer|
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 papers on transparent and human-centered AI in healthcare.
Papers must be submitted in PDF format to easychair https://easychair.org/conferences/?conf=dshealth2022 and formatted according to the new Standard ACM Conference Proceedings Template . Authors are encouraged to use the Overleaf template . Papers must be a maximum length of 4 pages, excluding references.
The program committee will select the papers based on originality, presentation, and technical quality for spotlight and/or poster presentation.
Selected papers will be invited to publish in Journal of Healthcare Informatics Research