Tag:

Mayo Clinic

Self Care

At HLTH 2022, a New Chapter for AI [Sponsored]

by Bailey Amber
written by Bailey Amber

machine learning AI

The evolution of machine learning is still in its early stages, but at the HLTH 2022 conference this week, companies shared how they are working to fine tune their approaches to AI. Those efforts included everything from improving the quality of patient data that underpin the algorithms, which has been criticized for not reflecting a diverse enough patient population, to making it easier for healthcare organizations to validate their effectiveness. Health tech companies also highlighted different approaches they are taking to how they work with providers to pilot machine learning algorithms and market them.

Dr. John Halamka, president of Mayo Clinic Platform, used his talk at HLTH to highlight an initiative to assess and reduce bias in patient data to improve the effectiveness of machine learning algorithms. Launched three years ago, Mayo Clinic Platform built an ecosystem to coordinate collaborations with health tech companies to enable innovation in healthcare.

Halamka’s talk on the “algorithmically underserved” noted that currently, when healthcare organizations use an algorithm, they often have no idea whether it performs well or not. The goal of its AI validation platform, Mayo Clinic Platform _ Validate, is to provide clinical validation for machine learning algorithms.

Mayo Clinic Platform is also partnering with other healthcare organizations to set standards and reporting for models as part of The Coalition for Health AI. In addition to Mayo, other founding members include University of California Berkeley, Duke Health, Johns Hopkins University, MITRE, Stanford Medicine, and University of California San Francisco. Industry members include Change Healthcare, Google, Microsoft, and SAS.

Halamka announced that a webinar is planned for December 7, which will offer a preview of plans for a public-private partnership to create a national register to assess the usefulness of a variety of healthcare algorithms.

“We feel we need a national set of assurance standards for algorithms,” Halamka said. The registry will host the metadata for algorithms produced in healthcare.

AI marketplace

Health tech companies are also developing marketplaces to improve the way collaboration partners, such as providers, payers and research groups, select algorithms.

“Data may be the new oil but the data needs to be refined,” said Wavemaker Three-Sixty Health General Partner Jay Goss. One of its portfolio companies, Gradient Health, partners with medical data providers around the globe (generally hospitals and imaging centers) to curate annotated medical images for AI research labs and corporations, so that they don’t have to do one-off deals with hospitals to obtain the data. Companies can search through segmented and labeled studies, or request a custom dataset, spending less time tracking down data and more time developing new tools.

AI hubs

Ferrum Health developed a program to enable health systems to assess machine learning algorithms without exposing their de-identified patient data to a cloud or otherwise forcing them to centralize that data. The company, which is part of the United Healthcare Accelerator 2022 cohort, exhibited on the accelerator’s pavilion.  Ferrum’s approach enables these tests to be done on-premises, behind a firewall, an approach David Miller, Ferrum’s vice president of sales – West, said is designed to de-risk their business for hospitals and health systems. The algorithms in its marketplace are FDA approved.

“We run a test of the algorithms using the hospital’s de-identified patient data to show how they perform for them,” said West. “We let our clients try it before they buy it.”

The company’s four AI Hubs include: oncology, orthopedics, cardiovascular, and breast care.

Reducing physician burnout

DeepScribe exhibited as part of the Plug and Play accelerator’s footprint at the conference. Its automated physician natural language processing software automatically summarizes a physician’s conversation with their patient and auto-populates those notes into EMR fields. Among the EMR companies it works with are athenahealth, dr chrono, AdvancedMD and Claimpower.

Earlier this year, DeepScribe closed a $30 million Series A round to support the company’s growth. The business is designed to negate the need for an in-person medical scribe, saving clinicians money.

The validation approach to algorithms seems like a natural progression in machine learning, similar to the rise of digital health apps followed by the need to validate them to ensure adoption by healthcare organizations skeptical of overhyped tech. It’s a natural progression balancing the interest in machine learning with the recognition that healthcare algorithms are not created equal.

Photo: Hemera Technologies, Getty Images

0 comment
0 FacebookTwitterPinterestEmail
Self Care

Novartis turns to algorithms developer Anumana to apply AI to cardio conditions

by Bailey Amber
written by Bailey Amber

heart, doctor, cardiac

Novartis’s main offerings for cardiovascular disease are drugs prescribed as a response to symptoms. However, heart problems can develop years before signs appear and the pharmaceutical giant wants to find new approaches to these disorders. A new partnership aims to develop artificial intelligence-based software that detects hidden cardiovascular conditions.

The collaboration is with Anumana, which develops algorithms that are applied to electrocardiograms (ECG). The agreement calls for Cambridge, Massachusetts-based Anumana to develop algorithms that could be applied to patients with previously undetected life-threatening heart disease. These algorithms are intended to help identify problems so physicians can intervene sooner.

“Cardiovascular disease is a widespread and multifactorial disease and, in order to mitigate its impact, we must look beyond therapeutic innovation and reimagine how we approach cardiovascular care,” Victor Bulto, president of Novartis Innovative Medicines U.S., said in a prepared statement. “Novartis is proud to collaborate with Anumana on innovative and data-driven solutions to better predict the risk of life-threatening heart disease, further driving forward our commitment to improving patient experiences and population health outcomes in this patient population.”

No financial terms of the multi-year collaboration were disclosed.

Anumana was formed by the Mayo Clinic and Nference, a company that uses unstructured electronic medical records data from medical centers to develop new diagnostics and treatments. The Anumana joint venture builds on an existing partnership between the Mayo Clinic and Nference. They launched the startup last year and backed it with a $25.7 million Series A investment. Anumana says it has since closed a $60 million Series B round of funding.

The Novartis collaboration could make the ECG, a widely used and inexpensive test, a wealth of information for cardiovascular analysis. Anumana said the alliance builds on its own efforts to develop AI-enabled software that detects signals from ECGs that humans cannot interpret. The new partnership is focused on developing software that can detect previously undiagnosed left ventricular dysfunction, which is also referred to as a weak heart pump. This condition can lead to heart failure.

In addition, Anumana said that the AI will screen for atherosclerotic cardiovascular disease, which can lead to heart attack and stroke. The research includes development of a digital point-of-care solution that can guide the use of drugs. The goal is to reduce the risks of hospitalizations and cardiovascular death. Under the Novartis partnership, Anumana will work with experts at the Mayo Clinic.

“This collaboration has the potential to transform the use of a ubiquitous inexpensive test, the ECG, with the aim of democratizing disease detection and helping medical care teams to proactively manage heart disease ahead of time and prevent some clinical events from ever happening,” Dr. Paul Friedman, chair of the department of cardiovascular medicine at Mayo Clinic and chair of Anumana’s Mayo Clinic board of advisors, said in a prepared statement.

0 comment
0 FacebookTwitterPinterestEmail
Self Care

Mayo Clinic, Microsoft, Cerner join coalition to provide digital access to Covid-19 vaccine records

by Bailey Amber
written by Bailey Amber

A coalition, comprising of health technology companies, providers and nonprofits, announced Thursday that they will establish an initiative to provide people with digital access to their Covid-19 vaccination records.

Two vaccines have so far been approved for administration in the U.S. — one developed by Pfizer and BioNTech, and the other by Moderna. The collaborative effort comes as doses of the vaccines are slowly making their way across the country, and people are figuring out what the next phase of the pandemic will look like.

That new phase will likely present unique challenges, including tracking who gets which vaccine, whether they get a one-or two-dose vaccine, where they receive their vaccine and so on, said Dr. John Halamka, president of Mayo Clinic Platform, in a phone interview. Currently, both Modera and Pfizer/BioNTech’s vaccine require two doses three to four weeks apart.

As the country thinks about opening back up and resuming to pre-pandemic levels of activity, “we [will] need a vaccine credential we can trust,” he said.

Mayo Clinic is just one of the high-profile organizations that have joined the coalition to create the Vaccination Credential Initiative. Others include Microsoft, Mitre, The Commons Project Foundation as well as EHR giants Epic and Cerner.

“We saw this as a critical opportunity to help our healthcare organizations and the world start the recovery process,” said David Bradshaw, senior vice president, consumer and employer solutions at Cerner, in an email. “We know vaccines will play a critical role in that and we wanted to be able to proactively inform and design to the specifications.”

The Vaccination Credential Initiative is developing a QR code that will enable individuals to easily provide their vaccination credentials when needed, Halamka explained.

The coalition has agreed on the standard for how the vaccine credential gets displayed in the QR code, he said. The standard was created by Josh Mandel, chief architect at Microsoft Healthcare, and is called the SMART Health Cards specification. It was developed with a short-term goal of allowing an individual to receive the Covid-19 vaccine or lab results and present these results to another party in a verifiable manner. The specification is based on the W3C Verifiable Credential — a credential that has authorship that can be cryptographically verified — and HL7 Fast Healthcare Interoperability Resources standards.

Now, the coalition needs to work on the “underlying plumbing behind it,” Halamka said. This includes figuring out how the patient gets access to the code after receiving the vaccine from whichever site they select — their doctor’s office, a Walgreens, a CVS, or any other vaccination site. Patients will have full control over their QR code and will be able to access it through any smartphone. They will have also the option of printing it out and keeping a physical copy. 

The coalition’s efforts come on the heels of a much-maligned vaccine rollout. More than 30 million doses of the Covid-19 vaccines have been distributed, but only a little over 11 million have been administered, according to data from the Centers for Disease Prevention and Control.

In an effort to speed up the process, the Trump administration announced Tuesday that it plans to release all reserves of vaccine doses that were initially held back to administer second doses, The New York Times reported. The administration also told states to begin vaccinating every individual 65 and older and people with underlying medical conditions.

Looking ahead, the incoming administration has made it clear that vaccine distribution will be an early priority, with President-elect Joe Biden saying in a speech Thursday that his relief plan will include “hundreds of billions” of dollars for a national vaccination program and public health initiatives like testing and contact tracing, NPR reported. Biden has also committed to having 100 million people vaccinated in his first 100 days.

While that goal seems ambitious, were it to be achieved, getting back to normal will require a verifiable record of people being vaccinated.

Halamka believes that coalitions like this one can have a huge impact on easing that transition.

“When I see nontraditional coalitions coming together — and that means government, academia, industry — all work[ing] together for the benefit of society, we can achieve great change,” he said.

Photo: Teka77, Getty Images

0 comment
0 FacebookTwitterPinterestEmail