Mayo Clinic launches 2 new companies to use patient data and AI to advance early disease detection

Mayo Clinic has launched a new initiative to collect and analyze patient data from remote monitoring devices and diagnostic tools and to use artificial intelligence to accelerate diagnoses and disease prediction.

The goal is to help physicians make better, faster and more accurate diagnoses and detect diseases even before symptoms develop, said John Halamka, M.D., a physician and president of Mayo Clinic Platform.

"We're seeing the emergence of sophisticated AI algorithms and in combination with novel data sources, this can result in breakthroughs in disease detection and wellness. This will require the assembly of technology, policy, and patient engagement with cultural change to make that happen," said Halamka during a media briefing Tuesday.

Mayo Clinic is developing a remote diagnostics and management platform that will connect data from remote medical devices with AI algorithms and augment human decision-making within existing clinical workflows, hospital executives said.

The platform will deliver clinical decision support tools, diagnostic insights and care recommendations to help clinicians make faster and more accurate diagnoses and provide continuous care to patients, rather than episodic care, according to Halamka.

RELATED: Mayo Clinic taps Google Cloud as strategic partner to accelerate innovation in AI, analytics and digital tools

With the platform, "clinicians will have access to best-in-class algorithms and care protocols and will be able to serve more patients effectively in remote care settings. The platform will also enable patients to take more control of their health and make better decisions based on insights delivered directly to them," Halamka said.

To support this effort, Mayo Clinic is launching two new companies, Anumana and Lucem Health, which are working with AI and medical algorithms that tap into the hospital's patient data.

Anumana, which Mayo Clinic formed in partnership with inference, will focus on developing and commercializing AI-enabled algorithms for early detection of "silent" conditions like a weak heart pump, silent arrhythmias or a thickened heart pump before they pose a risk to developing stroke or heart failure.

"For many conditions, such as a weak or thickened heart pump, or silent arrhythmias, effective evidence-based treatments exist that can prevent heart failure, stroke, or death. The key is to detect the disease before symptoms develop to prevent these events from happening," said Paul Friedman, M.D., chair of the Department of Cardiovascular Medicine at Mayo Clinic in Rochester, who led the team that developed the algorithms.

"The addition of AI to the ECG, a ubiquitous and inexpensive point-of-care test that is already integrated into medical workflows, makes this approach good for patients, convenient for clinicians, and massively scalable," he said during the briefing.

Anumana will focus initially on designing neural network algorithms based on billions of relevant pieces of heart health data in Mayo Clinic's clinical data analytics platform, including raw electrocardiogram (ECG) signals, to unlock hidden biomedical knowledge and enable early detection as well as accelerate treatment of heart disease, according to Mayo Clinic executives.

The company plans to seek Food and Drug Administration approval for an AI product, which is being tested at Mayo, to detect a weak heart pump so that it can make it available to other healthcare organizations.

"Our goal to bring many algorithms to market and create a library of ECG-based algorithms," said David McMullin, chief business officer at Anumana and nference, during the media briefing.

Anumana recently completed $25.7 million in series A financing led by founders nference and Mayo Clinic along with Matrix Capital Management, Matrix Partners and NTTVC.

RELATED: Tenet, Providence, other health giants band together to form new health data startup

Lucem Health, backed by Commure, a General Catalyst portfolio healthcare technology company, will focus on ingesting and connecting the remote patient telemetry devices with the algorithms developed by Mayo Clinic and partners. The company also will help Mayo integrate diagnostic insights generated by these algorithms into clinical workflows.

"The idea here is to connect devices with powerful algorithms and deliver the insights to the right place, right time and right context," said Sean Cassidy, CEO of Lucem Health.

The startup completed $6 million in series A financing led by founders Mayo Clinic and Commure.

Mayo Clinic has pushed ahead with several initiatives to harness patient data to develop digital innovations. The hospital inked a 10-year strategic partnership with Google in 2019 to accelerate its work in AI, analytics and digital health tools. The two organizations announced in October a new initiative to use artificial intelligence to improve radiation therapy planning for cancer care.

Other health systems and hospitals also are pursuing projects to collect and analyze patient data.

Some of the biggest names in healthcare including Tenet Health, Providence and CommonSpirit Health launched a new startup to pool and analyze patient data for research and drug development.

RELATED: Beth Israel Deaconess Medical Center joins Ascension to pilot Google's EHR search tool

Capitalizing on health systems' troves of patient data, 14 health systems are backing the new company, called Truveta. Among the backers are AdventHealth, Advocate Aurora Health, Baptist Health of Northeast Florida, Bon Secours Mercy Health, Hawaii Pacific Health, Henry Ford Health System, Memorial Hermann Health System, Northwell Health, Novant Health, Sentara Healthcare and Trinity Health.

Some of these partnerships, such as the tie-up between Google and Ascension, have faced scrutiny over patient privacy and the use of medical data.

There are also rising concerns about bias in medical algorithms that are built on data from a narrow population of patients, such as from a single health system.

Mayo plans to test its algorithms on diverse populations, Halamka said.  

Researchers at Mayo Clinic also are developing a framework, what Halamka called a "universal nutrition label for AI algorithms," that will disclose the sources and types of data used to develop its AI products.

"I hope that Mayo Clinic with collaborators can lead the country and the world to develop a standard methodology to label every AI algorithm in healthcare," Halamka said.