.png&w=3840&q=75)
.png&w=3840&q=75)
Datathon · 2nd Annual
MD+ 2023 Datathon Value-Based Care.
The 2nd annual MDplus Datathon — a chance to work with medical students, graduate students, and healthcare workers to derive data-driven insights and innovate solutions that advance patient care.
- Dates
- 10/25/23 – 11/15/23
- Pitch competition
- Mon 11/20/23 · 5pm EST
- Dataset
- MIMIC-IV
- Prize
- $3,000 grand prize
About
The 2nd Annual Datathon.
Welcome to the 2023 MDplus Datathon! The datathon was a chance to work with medical students, graduate students, and healthcare workers from all backgrounds to derive data-driven insights and innovate solutions that advance patient care.
The theme was value-based care. Teams of 3–5 explored a common dataset (MIMIC-IV) to answer a question or innovate a solution in alignment with the theme, using quantitative analyses to form clinical insights and contextualize them into actionable proposals for relevant stakeholders.
Tutorials
Get up to speed.
Introduction to Python
Introduction to R
Introduction to MIMIC-IV: Python
Events schedule
Workshops, office hours, and pitches.
Datathon kickoff event
Wed 10/25 · 6pm EDTThe launch of the 2nd annual MD+ Datathon — event logistics, judging, and prizes.
Introduction to Python
Mon 10/30 · 7pm EDTFor beginner programmers and those who have never programmed with Python.
Navigating MIMIC-IV with Python
Wed 11/01 · 7pm EDTHow to load, parse, and analyze the MIMIC-IV dataset.
Office Hours #1 with Lathan: R, general
Tue 11/07 · 7pm ESTOffice Hours #2 with Michael: Python, general
Wed 11/08 · 7pm ESTOffice Hours #3 with Michael: Python, general
Sat 11/11 · noon ESTFinalist pitch competition
Mon 11/20 · 5pm ESTPitches from the seven finalist teams competing for the $3,000 grand prize.
Best Practices in Data Science
AsynchronousA talk by Olivier Humblet, Head of HEOR at Regeneron, from the prior year's datathon.
Judges
Who scored the submissions.
Johns Hopkins University, Quintuple Aim Solutions
Brigham & Women's Hospital, McKinsey & Company
Northwestern University, Doximity
ML/AI Product Leader & Advisor, prev. Cerebral
Progressive Insurance, prev. Cleveland Clinic
Finalists
The teams that pitched.
Finalist teams pitched live for the $3,000 grand prize.
Adrenergic Data-1 Receptor Agonists
Minimizing Chronic Kidney Disease (CKD) Underdiagnosis Using Machine Learning
Dany Alkurdi (Mt. Sinai), Felipe Giuste (Emory), Lawrence Huang (Brown), Keyvon Rashidi (Texas A&M), Sachin Shankar (Cincinnati)
ALEYA
Significant association of social work referral and 30-day unplanned hospital readmission for patients with alcohol-related disorders using MIMIC-IV data
Amy Oh (Brown), Archita Goyal (Tufts), Emily Leventhal (Mt. Sinai), Lei Zhou (Mendel)
Dodecahedron
Can We Curb Frequent ED Visits Due to Alcohol-Related Conditions?
Cailin Winston (UW Seattle), Caleb Winston (Stanford), Chloe Winston (Penn), Claris Winston (UW Seattle), Cleah Winston (UW Seattle)
Rational Rockets
Clinigrapher: Automatic Knowledge Graph Extraction from Medical Discharge Notes for Clinical Decision Support
J.T. Bassett, Kiran Boyinepally, Lauren Fang, John Vergis (all University of Toledo)
SuperLearners
Contrast Overuse in Patients with Renal Disease: A Targeted Analysis
Soryan Kumar (Brown), Ashwin Mahendra (Florida Atlantic), Arnav Kumar (Princeton)
Team Pivot
Analyzing Acuity as a Tool for Value-Based Care
Joao Arthur Kawase De Queiroz Goncalves (Miami), Ian Ong (Penn), Sophie Reznik (Minnesota), Nikola Susic (Miami)
Until It Compiles
Machine Learning-driven forecasting and characterization of the ICU-admitted Heart Failure Patient Population in the MIMIC-IV v.04 database
Nikith Erukulla, Jeff Kim, Simon Liu, Lucas Myint, Shashank Sandu (all University of Illinois)
FAQs
Common questions.
I have little/no data science or computational experience. Can I still participate?
Absolutely! Learning the computational tools is half the fun. Participants have access to tutorials covering the basics of Python and R and how to analyze the dataset. Judges care more about the insights derived and the data analysis than computational novelty or complexity.
What will we actually be doing?
Students are provided a dataset (e.g., claims and hospital data) and asked to identify an addressable problem, explore it by analyzing the dataset, and create an actionable recommendation.
I don't have the best laptop for data analysis... Can I still participate?
Yes! We partnered with Hugging Face to bring free access to powerful computational resources dedicated to the event. Join the MDplus Hugging Face community to get started.
What's the time commitment look like?
It's flexible and depends on your group and project.
Questions? Reach the organizers
Other editions