Virtual Workshop - On Demand
Unified Data Analytics Virtual Workshop | Healthcare Payers and Providers
Unifying Data Pipelines and Machine Learning with Apache Spark™
Now more than ever, healthcare payers and providers are looking to data to improve how they manage care and treat patients. In fact, big data analytics and machine learning have become essential for use cases such as population claims analysis, fraud detection and prevention, patient risk scoring, health plan recommendation and more. However, most healthcare organizations struggle with preparing large clinical and claims datasets for analytics, managing the proliferation of ML tools, and moving models from development to production all while maintaining stringent data security and complying with HIPAA.
During this on demand virtual session, we’ll cover best practices for using powerful open source technologies to simplify and scale your data analytics and ML efforts. We’ll discuss how to leverage Apache Spark™ and Delta Lake to build a secure, scalable clinical and claims data lake for downstream analytics. You’ll also learn how to use popular ML frameworks (i.e. TensorFlow, XGBoost, Scikit-Learn, etc.) to train models for various healthcare use cases. And finally, you can learn how to use MLflow to track ML experiments between multiple users within a secure and reproducible environment.
Join this on demand virtual session to learn how a unified approach to data analytics can accelerate data analytics and machine learning projects in the Healthcare industry.
Agenda at a Glance
- Opening Remarks - Unifying Data Science and Engineering in Healthcare
- Guest Speaker: How One of the Largest Public Health Organizations Built a
- Modern Data Lake to Analyze Population-scale Claims Data, Jack Fletcher, Former Sr. IT Advisor for CMS
- Break | Q&A
- Data Engineering Demo: Automated ETL and Exploratory Analysis of Electronic Health Record Data
- Data Science Demo: Using ML to Predict Patient Care Utilization
- Wrap Up | Q&A