Interpretable Machine Learning in Healthcare

Overview

Applying machine learning (ML) in healthcare is gaining momentum rapidly.  However, the black-box characteristics of the existing ML approach inevitably lead to less interpretability and verifiability in making clinical predictions. To enhance the interpretability of medical intelligence, it becomes critical to develop methodologies to explain predictions as these systems are pervasively being introduced to the healthcare domain, which requires a higher level of safety and security. Such methodologies would make medical decisions more trustworthy and reliable for physicians, which could ultimately facilitate the deployment. On the other hand, it is also essential to develop more interpretable and transparent ML systems. For instance, by exploiting structured knowledge or prior clinical information, one can design models to learn aspects more aligned with clinical reasoning. Also, it may help mitigate biases in the learning process or identify more relevant variables for making medical decisions.

In this workshop, we aim to bring together researchers in ML, computer vision, healthcare, medicine, NLP, and clinical fields to facilitate discussions including related challenges, definitions, formalisms, and evaluation protocols regarding interpretable medical machine intelligence. Additionally, we will seek possible solutions such as logic and symbolic reasoning over medical knowledge graphs, uncertainty quantification, composition models, etc. We hope that the proposed workshop is fruitful in offering a step toward building autonomous clinical decision systems with a higher-level understanding of interpretability.

Important Dates

Submissions:  May 30, 2023, AoE

Notifications: June 19, 2023

Workshop: July 28, 2023

Call for Submissions

We invite participation in the 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH), to be held as part of the ICML2023 conference. 

Please check Submissions for more information about the topics and submission instructions.

Travel Awards and Best Paper Awards

Thanks to our workshop sponsors, we provide five travel awards (€200 each) to support students' attendance at ICML according to diversity, equity, and inclusion. To be eligible for the travel awards, the applicant should be a student with an accepted paper at IMLH 2023, and attend IMLH in person.

Congratulations to the recipients of IMLH 2023 Travel Awards:

Daniel Lundstrom, Aniek Markus, Alicja Chaszczewicz, Hailey Joren, and Gautam Machiraju.

IMLH 2023 Best Paper Awards:

• First place of the best paper award, two awards, $1,000 each

  • Signature Activation: A Sparse Signal View for Holistic Saliency

Authors: Jose Roberto Tello Ayala, Akl C. Fahed, Weiwei Pan, Eugene V. Pomerantsev, Patrick Thomas Ellinor, Anthony Philippakis, Finale Doshi-Velez

• • ADMIRE++: Explainable Anomaly Detection in the Human Brain via Inductive Learning on Temporal Multiplex Networks

Authors: Ali Behrouz, Margo Seltzer

• Second place of the best paper award, two awards, $500 each

  • An interpretable data augmentation framework for improving generative modeling of synthetic clinical trial data

Authors: Afrah Shafquat, Jason Mezey, Mandis Beigi, Jimeng Sun, Andy Gao, Jacob W. Aptekar

• • A Pipeline for Interpretable Clinical Subtyping with Deep Metric Learning

Authors: Haoran Zhang, Qixuan Jin, Thomas Hartvigsen, Miriam Udler, Marzyeh Ghassemi

Contact

Please contact Zongwei Zhou (zzhou82@jh.edu) or Yucheng Tang (yucheng.tang@vanderbilt.edu) if you have any questions.

Workshop History

• IMLH 2022

• IMLH 2021