Health Catalyst launches free open source machine learning and artificial intelligence tool

The company said its goal is to make healthcare outcomes improvement accessible to all and, in turn, boost collaboration industrywide.
By Bernie Monegain
08:01 AM

Health Catalyst has created, a website that offers free open source predictive analytics software for hospitals and other healthcare organizations.

“Wherever you have a data set that you pull together, you can create a model based on that by using these tools,” said Levi Thatcher, director of data science at Health Catalyst.

Machine learning and predictive analytics to improve health outcomes has so far been limited to an elite group of data scientists, mostly in the nation’s top academic medical centers, he pointed out. – open source predictive analytics software – is part of a mission to make machine learning accessible to the thousands of healthcare professionals with only basic technical skills, but who share an interest in using the technology to improve patient care, Thatcher explained. 

[Also: CIOs reveal emerging technologies with the biggest potential]

By making its central repository of proven machine learning algorithms freely available, opens the doors to a large, diverse group of technical healthcare professionals to quickly use machine learning tools to build accurate models.

Moreover, the site provides one central place to download the tools, read documentation, request new features, submit questions, follow the blog, and even contribute code.

“We are not just being altruistic here,” said Dale Sanders, Health Catalyst executive vice president. “By submitting our tools and algorithms to the open source community, we and our clients will benefit from the collective intelligence that exists beyond our team of data scientists.” is unlike any other machine learning tool, Thatcher said, in that the platform features packages for two common languages in healthcare data science – R and Python. They are designed to streamline healthcare machine learning by simplifying the workflow of creating and deploying models, and delivering functionality specific to healthcare.

Both packages provide an easy way to create models on a health system’s own data, Thatcher explained. They include linear and random models, ways to handle missing data, guidance on feature selection, proper performance metrics and easy database connections.

The tools in are designed to enable business intelligence developers, data architects, and SQL developers to create appropriate and accurate models with healthcare data, without hiring a data scientist. users might also tap Health Catalyst, however, to create models that ensure top accuracy. Examples would be to build a model aimed at reducing readmissions, Thatcher said, or one to improve heart failure care and outcomes.

“We have used to build predictive models that drive outcomes improvement efforts by our clients and span across our product lines,” said Sanders.

Such models include, but are not limited to a CLABSI predictive model, readmission models for COPD and other chronic conditions, schedule optimization, and financial predictions like propensity to pay.

“Success would be improved patient outcomes,” Thatcher added. “That is the primary driver of this.”

Machine learning was among the topics at the recent HIMSS and Healthcare IT News Big Data and Healthcare Analytics Forum. Read the top takeaways and see our complete coverage here. 

Twitter: @Bernie_HITN
Email the writer:

Like Healthcare IT News on Facebook and LinkedIn