Presented By O'Reilly and Cloudera
Make Data Work
March 13–14, 2017: Training
March 14–16, 2017: Tutorials & Conference
San Jose, CA

Applying machine learning to live patient data

Joseph Blue (MapR), ed00425e 963b0803 (MapR Technologies)
2:40pm3:20pm Wednesday, March 15, 2017
Real-time applications
Location: LL20 D Level: Intermediate
Secondary topics:  Healthcare
Average rating: ****.
(4.50, 2 ratings)

Who is this presentation for?

  • Data scientists, Hadoop administrators, and healthcare professionals

Prerequisite knowledge

  • Basic knowledge of big data use cases
  • General familiarity with the Hadoop ecosystem
  • Awareness of the concept of machine learning (experience not required)

What you'll learn

  • Explore a system for handling semistructured data in real time and applying machine learning to live data
  • Discover healthcare use cases for archived data


The business of healthcare in the 21st century is all about reducing costs without sacrificing quality of care. Traditional methods for analyzing health-related data have reached a plateau, but businesses are developing data platforms to leverage challenging data sources to produce new insights and incremental savings. It’s time to stop talking about the promise of big data and start delivering.

Joseph Blue and Carol Mcdonald walk you through a streaming system to detect anomalies in data from a heart monitor transported using HL7, demonstrating how data from the monitor flows to an auto-encoder model that compares signals in the context of recent history to detect irregular heartbeats in near real time. Joseph and Carol explain how combining visualization and alerting enables healthcare professionals to improve outcomes and reduce costs and share lessons learned from their experience dealing with real data in real medical situations.

Photo of Joseph Blue

Joseph Blue


Joseph Blue is a data scientist at MapR. Previously, Joe developed predictive models in healthcare for Optum (a division of UnitedHealth) as chief scientist and was the first fellow for Optum’s startup, Optum Labs. Before his time at Optum, Joe accumulated 10 years of analytics experience at LexisNexis, HNC Software, and ID Analytics (now LifeLock), specializing in business problems such as fraud and anomaly detection. He is listed on several patents.

Photo of ed00425e 963b0803

ed00425e 963b0803

MapR Technologies

Carol Mcdonald is a solutions architect at MapR focusing on big data, Apache HBase, Apache Drill, Apache Spark, and machine learning in healthcare, finance, and telecom. Previously, Carol worked as a Technology Evangelist for Sun, an architect/developer on: a large health information exchange, a large loan application for a leading bank, pharmaceutical applications for Roche, telecom applications for HP, OSI messaging applications for IBM, and sigint applications for the NSA. Carol holds an MS in computer science from the University of Tennessee and a BS in geology from Vanderbilt University and is an O’Reilly Certified Spark Developer and Sun Certified Java Architect and Java Programmer. Carol is fluent in French and German.