This challenge is closed to submissions.
Unsupervised Wisdom: Explore Medical Narratives on Older Adult Falls
Unsupervised machine learning to extract insights about falls from Emergency Dept data
Submission period:
Closed on 10/07/23 03:59 AM UTCTotal cash prizes:
$70,000Falls among adults 65 and older are the leading cause of injury-related deaths. Medical record narratives are a rich yet under-explored source of potential insights about how, when, and why people fall. Modern machine learning approaches to working with narrative data have the potential to effectively extract insights about older adult falls from narrative medical record data at scale.
The goal in this challenge is to identify effective methods of using unsupervised machine learning to extract insights about older adult falls from Emergency Department narratives. Insights extracted from medical record narratives can potentially inform interventions for reducing falls.
This work aligns with the CDC/NCIPC priority of improving data science work in injury and violence prevention (Data Science and Public Health | Injury Center | CDC).
Total cash prizes
Prize description
1st place: $20,000
2nd place: $15,000
3rd place: $10,000
4th place: $5,000
Bonus prizes: $20,000
Eligibility requirements
Please refer to official data challenge rules here: Competition: Unsupervised Wisdom: Explore Medical Narratives on Older Adult Falls (drivendata.org)
Rules
Please refer to official data challenge rules here: Competition: Unsupervised Wisdom: Explore Medical Narratives on Older Adult Falls (drivendata.org)
Winners will be selected by a judging panel of domain experts and researchers. Submissions will be judged according to the following weighted criteria:
● Novelty (35%)
To what extent does this submission utilize creative, cutting-edge, or innovative techniques? This can be demonstrated in any or all parts of the submission (e.g., preprocessing, embeddings, models, visualizations).
● Communication (25%)
To what extent are findings clearly and effectively communicated? This includes both text and visuals.
● Rigor (20%)
To what extent is this submission based on appropriate and correctly implemented methods and approaches (e.g., preprocessing, embeddings, models) with adequate sample sizes?
● Insight (20%)
To what extent does this submission contain useful insights about the effectiveness of unsupervised machine learning methods at uncovering patterns in this data and/or informative findings that can advance the research on circumstances related to older adult falls?
To enter, visit https://www.drivendata.org to register for a DrivenData account then navigate to the Challenge Website https://falls.drivendata.org to sign up as a participant. If you already have a DrivenData account, you can sign up directly as a challenge participant on the Challenge website.
A full submission for this challenge is a zip archive with the extension .zip, which includes the following two items:
1. Notebook of analysis
2. Executive summary
You are allowed to make only one submission. To make changes, you can delete and re-upload your submission as many times as you like. Only the last entry submitted will be considered.
For more information on how to enter: Competition: Unsupervised Wisdom: Explore Medical Narratives on Older Adult Falls (drivendata.org)
