Case Study

Article

Saving lives with big data analytics that predict patient outcomes

Insights derived from data can help healthcare providers understand health outcomes not just for individuals but for entire groups of individuals or populations. They can identify and predict high risk segments within a population and help take preventive action, creating long term benefits for patients, hospitals, governments and society at large.

To unlock the true potential of data for population health, data from a range of disparate sources, including clinics, hospitals, pharmacies, fitness centres and even homes and employment places, would have to be brought together and analysed. However, traditional healthcare IT solutions tended to be limited in scope and restricted to a particular source of data

This was the challenge being faced by Cerner Corporation (Cerner), a leader in the healthcare IT space, whose solutions are used in over 35 countries at more than 27,000 provider facilities, such as hospitals, integrated delivery networks, ambulatory offices, and physicians’ offices.

Cerner was expanding its historical focus on electronic medical records (EMR) to help improve health and care across the board. To do so, it aimed to assimilate and normalise the world's healthcare data in order to reduce cost and increase efficiency of delivering healthcare, while improving patient outcomes.

Mr David Edwards, Vice President and Fellow at Cerner explained, "Our vision is to bring all of this information into a common platform and then make sense of it -- and it turns out, this is actually a very challenging problem."

The firm accomplished this by building a comprehensive view of population health on a Big Data platform that’s powered by a Cloudera enterprise data hub (EDH). Management tooling, scalability, performance, price, security, partner integration, training, and support options were key criteria for the selection of a partner.

Today, the EDH contains more than two petabytes (PB) of data in a multi-tenant environment, supporting several hundred clients. It brings together data from an almost unlimited number of sources, and that data can be used to build a far more complete picture of any patient, condition, or trend. The end-result is better use of health resources.

Building the data hub

The platform ingests multiple different Electronic Medical Records (EMRs), Health Level Seven International (HL7[1]) feeds, Health Information Exchange information, claims data, and custom extracts from a variety of proprietary or client-owned data sources,

It uses Apache Kafka, a high-throughput, low-latency open-source software platform to ingest real-time data streams. The data is then pushed back to the appropriate data storage, HDFS (Hadoop Distributed File System) cluster or HBase (a noSQL database which enables random, real-time read/write access to data).

A blog post by Micah Whitacre, a senior software architect on Cerner Corp.’s Big Data Platforms team, explains how Apache Kafka helped Cerner overcome challenges related to scalability for the near real-time streaming system and in streamlining data ingestion from multiple sources, including ones outside Cerner’s data centres.

Cerner has also taken steps to ensure the security and data integrity of its Big Data platform. A technical solution must provide a mechanism for threat mitigation in order to be considered a viable data management technology in the healthcare space.

Cloudera advised Cerner’s approach to encrypting data at rest and on its Kerberos (a network authentication protocol for client/ server applications) integra­tion.

Mr Edwards said that their real aim to get the technology out of the way so all that users see is the value that comes from their efforts.

"Our real aim is to get the technology out of the way so all that users see is the value that comes from their efforts. We really want the focus to be on the outcomes and results, not on what it takes to deliver them. The Cloudera platform is the technology that’s driving the value and it’s allowing us to build applications that help healthcare systems improve how they manage the chronic conditions of their populations. We're now able to aggregate the information, stratify it, and offer the opportunity to look at this data in a way that has never been possible before,” he said.

Improved insights

The uniqueness of Cerner’s EDH is that it allows data to be brought together from an almost unlimited number of sources, and that data can be used to build a far more complete picture of any patient, condition or trend.

The end result: better use of health resources.

Cerner’s EDH helps them understand the most significant risks and opportunities for improvement across a population of people. Cerner computes quality scores for manag­ing a number of chronic conditions, and analysts can see which conditions could gain the most by improving those scores.

For instance, Cerner can accurately determine the probability that a person has a bloodstream infection, such as sepsis.

Sepsis is an uncontrolled inflammatory response to an infection. It is a complex condition which is difficult for a junior doctor or nurse to recognise. From the time sepsis first takes hold, healthcare professionals have only the initial 6 hours after the diagnosis to deliver a group of interventions to the patient. These interventions require close and rapid interaction between teams in the Emergency Department, in the general ward and in Critical Care. For an individual patient, getting the interventions right at the right time may mean a 20-30% better chance of surviving.

Cerner developed an evidence-based algorithm, called the St. John Sepsis agent, allowing early intervention for patients at risk, and preventing deterioration into severe sepsis. The algorithm continuously monitors key clinical indicators and recognises a potentially septic pattern. The integrated system, which was created in cooperation with Methodist North Hospital in Memphis, Tenn., gathers patient information from many sources, helping clinicians early identify patients at risk for sepsis and providing an accurate diagnosis and treatment.

Ryan Brush, Senior Director and Distinguished Engineer, Cerner, said, “Our clients are reporting that the new system has actually saved hundreds of lives by being able to predict if a patient is septic more effectively than they could before."

Content from Cloudera customer success story on www.cloudera.com and related resources.

[1] HL7 provides a comprehensive framework and related standards for the exchange, integration, sharing, and retrieval of electronic health information that supports clinical practice and the management, delivery and evaluation of health services.

Visit site to retreive White Paper:
Download
FB Twitter LinkedIn YouTube