Healcisio Taps AI to Improve Early Diagnosis

LA JOLLA – Healcisio, a health-tech startup developing AI-based tools for health care providers and hospitals, has received $1 million in federal grant funding from the National Institute of Allergy and Infectious Diseases (NIAID).

Founded by an ex-Illumina engineer and associate professor at UC San Diego, the funding will be allocated towards the development of its AI-powered software solution. This is the third federal award for the company, which was founded three years ago.

The funding will be used to further its mission and help bring state-of-the-art “AI-based diagnostic tools” to the bedside.

“The $1 million STTR award will support Healcisio’s efforts towards development of new AI-powered solutions for abstraction and reporting of quality measures,” said Aaron Boussina, chief executive officer and co-founder of Healcisio.

“In continued expansion of our critical care AI platform, we are in the process of deployments at two additional health systems. Additionally, we are deploying new generative AI tools related to automated quality assessment for the in-hospital care of sepsis patients.”

Improving Patient Care

Founded in 2021, Healcisio aims to improve patient care through early prediction of sepsis.
The startup’s deep-learning AI model continuously monitors more than 150 patient variables, including information such as vital signs, lab results, current medications, and medical history.

Using multiple layers of artificial neural networks, it identifies patients at high risk for sepsis while limiting false positives. The algorithm can more quickly and accurately identify patients at risk for the serious blood infection sepsis than do existing protocols.

“Our approach has been to first tackle those technical barriers to seamless clinical intelligence. We’ve previously published our work on a scalable cloud-based healthcare analytics platform that is rooted in interoperability,” Boussina said.

“What’s exciting about this is it allows us to deploy arbitrarily complex AI directly onto the electronic health record and fuse many data modalities, such as text, wearables, and more.

We have a large language model and 4 time series models constantly surveilling all patients for signs of deterioration in two San Diego hospitals,” Boussina said.

Algorithm Detects Sepsis

Healcisio is one of the first clinically validated machine-learning solutions that notifies health care providers about patients at high risk of sepsis, allowing them to begin treatments sooner.

“Very few AI solutions actually make it into the clinic,” Boussina said. Sepsis, which happens when the body’s response to an infection spirals out of control, can lead to organ failure, limb loss and death.

“We deployed our sepsis AI into clinical use in two emergency departments and observed a 17% reduction in sepsis mortality as well as a 10% improvement in the CMS Severe Sepsis and Septic Shock (SEP-1) quality measure. This represents the only AI that has reduced sepsis-related mortality,” Boussina said.

Roughly 1.7 million adults in the U.S. develop sepsis each year, and about 270,000 of them contribute to in-hospital deaths in the U.S., according to the Centers for Disease Control and Prevention.

Although most cases originate outside the hospital, the condition is a major cause of patient mortality in this setting. Catching the problem as quickly as possible is crucial to preventing the worst outcomes.

Potential to Save Lives

The STTR award will help with the multi-site deployment of Healcio’s sepsis AI and SEP-1 automation products. Healcisio has received several federal grants since its inception.

In August 2022, it received $400,000 from Rapid Acceleration of Diagnostics (RADx Tech) and $1.7 million grant from the National Institutes of Health (NIH) in July 2023.

Other machine-learning algorithms to test for sepsis already exist. However, only a handful of companies have put the algorithms into clinical practice. While there’s more work to be done, the implications are significant.

Shamim Nemati, a director of predictive health analytics at UCSD and co-founder of Healcisio, said he believes the clinically informed technology could save lives.

A nearly 2% reduction in sepsis mortality would translate to many thousands of saved lives nationally, for example.

“Early sepsis detection is on everyone’s mind,” Nemati said. “I’m cautiously optimistic.
Future generations will hopefully look back at this period as the miracle years of AI in Medicine.”

Healcisio Inc.
FOUNDED: 2021
CEO: Aaron Boussina
HEADQUARTERS: La Jolla
BUSINESS: Health-tech software company
FUNDING: More than $3 million
EMPLOYEES: Under 10
WEBSITE: www.healcisio.com
NOTABLE: This is the third federal award for the startup.