MEDS KDD 2025 Tutorial
Building a model with MEDS: from the key design principles through data extraction, task definition, and model building.
This page hosts the complete form of the notebooks explored interactively at the MEDS KDD 2025 Tutorial.
📄️ Getting Familiar with MEDS
Before we start building datasets and models using the MEDS ecosystem, we need to understand what the MEDS
📄️ Converting to MEDS
In this tutorial, we'll extract a dataset in MEDS format for downstream use. See below for the jupyter
📄️ Extracting a Prediction Task
To easily extract prediction tasks from MEDS Data, we will use the
📄️ Build a (Tabular Baseline) Model over MEDS data
In this tutorial, we'll use the dataset we extracted previously and build a neural network model to predict
📄️ Build a (Neural Network) Model over MEDS data
In this tutorial, we'll use the dataset we extracted previously and build a neural network model to predict
In-person Tutorial Information
- Date: Sunday August 3, 2025
- Time: 8:00 AM - 11:00 AM
- Location: Toronto Convention Centre (255 Front St W, Toronto, ON M5V 2W6), Room 707
In-person Presenters
Matthew McDermottAssistant Professor, Columbia University
Suhana BediPh.D. Student, Stanford University
Additional Tutorial Notebook Authors
Kamilė StankevičiūtėPh.D. Student, University of Cambridge
Justin XuPh.D. Student, University of Oxford
Ethan SteinbergResearcher, Prealize Health
Other Contributors
(Ordered alphabetically by last name)
Teya BergamaschiPh.D. Student, Massachusetts Institute of Technology
Hyewon Jeong, MDPh.D. Student, Massachusetts Institute of Technology
Simon A. LeePh.D. Student, UCLA, Computational Medicine
Nassim OufattolePh.D. Student, Massachusetts Institute of Technology
Patrick RockenschaubPostdoctoral Researcher, Medical University of Innsbruck
Jimeng SunHealth Innovation Professor, UIUC
Robin P. van de WaterPh.D. Student, Hasso Plattner Institute
Michael WornowPh.D. Student, Stanford University
John H. WuPh.D. Student, UIUC
Zhenbang WuPh.D. Student, UIUC