This is a winning submission from the 2024 AI Data Readiness Challenge.
Explores the AI Data Readiness of CRDC data.
This asset contains the submission from Jeff Van Oss and team of BAMF Health, the second place winner of the Tier 2: Multi-Modal Data Challenge. In this tier, participants must train an AI/ML model utilizing data from more than one data class.
Use case: Tier 2 (Multimodal data), Category 3 (Diagnosis)
General use case: Distinguish amongst different cancer subtypes
Specific use case: Use of radiological images from Imaging Data Commons and mutation data from The Cancer Genome Atlas to predict VHL mutation status
A data scientist can run the provided scripts after obtaining the appropriate data from the CGC.
The documentation, pre-processing, and model related files are available in Model and Data Clearinghouse (MoDaC). The data can be accessed via the Cancer Genomic Cloud (CGC).
Assessment of dataset readiness and model predictions.