Databricks Intelligence Platform for HLS: Patient Readmission

The Databricks Intelligence Platform is an open architecture that combines the best elements of data lakes and data warehouses. In this demo, we’ll show you how to build an end-to-end healthcare data platform to ingest patient information.

We will focus on predicting and explaining patient readmission risk to improve care quality.

This demo covers the end-to-end lakehouse platform:

• Ingest healthcare data (from Synthea), and then transform them to the OMOP data model using Delta Live Tables (DLT), a declarative ETL framework for building reliable, maintainable and testable data processing pipelines
• Secure your ingested data to ensure governance and security on top of PII data
• Build patient cohorts and leverage Databricks SQL and the warehouse endpoints to visualize your population
• Build a machine learning model with Databricks AutoML to predict 30-day patient readmission risk
• Orchestrate all these steps with Databricks Workflows

To run the demo, get a free Databricks workspace and execute the following two commands in a Python notebook:

%pip install dbdemos

import dbdemos
dbdemos.install('lakehouse-hls-readmission')