Predictive Disease Risk Modeling at 23andMe with Subarna Sinha - #436
Published:Dec 11, 2020 21:35
•1 min read
•Practical AI
Analysis
This article summarizes a podcast episode from Practical AI featuring Subarna Sinha, a Machine Learning Engineering Leader at 23andMe. The core discussion revolves around 23andMe's use of genomic data for disease prediction, moving beyond its ancestry business. The conversation covers the development of an ML pipeline and platform, including the tools, tech stack, and the use of synthetic data. The article also touches upon internal challenges and future plans for the team and platform. The focus is on the practical application of AI in healthcare, specifically in the realm of genomics and disease risk assessment.
Key Takeaways
- •23andMe leverages genomic data for disease prediction, expanding beyond ancestry analysis.
- •The article highlights the development and operationalization of an ML pipeline and platform.
- •The discussion includes challenges and future directions in applying AI to healthcare.
Reference
“Subarna talks us through an initial use case of creating an evaluation of polygenic scores, and how that led them to build an ML pipeline and platform.”