Groundbreaking results reveal AI can reduce sepsis deaths

• Read original article here

Patients are 20% less likely to die of sepsis because of a groundbreaking new AI system which can catch symptoms hours earlier than traditional methods, a study has revealed.

Bayesian Healthand John Hopkins University announced the innovative results which, for the first time ever, associate lives saved with a clinically-deployed AI platform. 

Where earlier AI deployments have failed to produce real-world results, Bayesian demonstrates reduced mortality. It also shows long-term efficacy, high adoption and fewer false alerts in a trio of prospective, peer-reviewed studies.

Bayesian Health, artificial intelligence (AI)-based Intelligent CareAugmentation platform developer, announced the release of three large, prospective multisite cohort studies – which are a first of their kind.

They offer a comprehensive and rigorous evaluation of the efficacy of their adaptive AI approach and showing patient lives saved.

The adaptive AI technology is based on nearly a decade of academic research and it succeeds where prior applications of AI in clinical care have failed. 

Unlike traditional AI that follows a “one-size-fits-all” approach to patients and hospitals, Bayesian’s adaptive approach to AI takes into consideration the diversity of the patient population.

It considers the unique ways in which doctors and nurses deliver care on the frontlines, and the unique characteristics of each health system. Ultimately it is able to be  significantly more accurate and to gain provider trust and adoption. 

The three studies, published inNature Medicine and Nature Digital Medicine, wereconducted in collaboration with researchers from Johns Hopkins University.

Using data from 764,707 patient encounters (17,538 with sepsis). Across five hospitals in both academic and community-based hospital settings with 2,000+ providers using the software.

This research shows accurate early detection (1 in 3 cases were physician confirmed) at high sensitivity (82%) and significant lead time (5.7 hours earlier).

It also shows high provider adoption (89%), and associated significant reductions in mortality, morbidity and length of stay.

Most significantly, the studies show timely use of Bayesian’s AI platform is associated with a relative reduction in mortality of 18.2%.

“There aren’t many things left in medicine that have a 30% mortality rate like sepsis,” said Neri Cohen, MD, PhD, President of The Center for Healthcare Innovation and Bayesian collaborator.

“What makes it so vexing, is that it is relatively common and we still have made very little progress in recognizing it early enough to materially reduce themorbidity and mortality. 

“To reduce mortality by nearly 20% is remarkable and translates to many lives saved.”

“While we all understand the value of leveraging AI to improve the delivery of care, achieving measurable impact has proven to be much harder than advertised,” said Suchi Saria, PhD, CEO of Bayesian Health and Director of Machine Learning, AI and Healthcare Lab at Johns Hopkins University. 

“These results showing high physician adoption and associated mortality and morbidity reductions are a milestone for the field of AI and are the culmination of nearly a decade of significant technological investment, deep collaboration, the development of noveltechniques and rigorous evaluation.”

“Bayesian Health’s evidence-based AI/machine learning platform can leverage health systems’ substantial investment in the EMR as a base layer for patient data and help increase capacity of frontline healthcare providers,” said Lee Sacks, MD, former Chief Medical Officer at Advocate Aurora Health and Clinical Advisor for BayesianHealth. 

“This is especially important in our current context, where we’re struggling with staffing shortages, reducinginequalities, high patient acuity, cognitive overload and other intrinsic challenges being faced by health systemstoday.”