New AI tool helping to seriously slash deaths from this

By Mark Waghorn via SWNS

An artificial intelligence tool slashes deaths from sepsis by a fifth, according to new research.

It spots symptoms almost six hours earlier than traditional methods - when antibiotics are most likely to work.

The system, created by a scientist whose young nephew died from the disease, reduced mortality rates by 20 percent, the study found.

Professor Suchi Saria, of Johns Hopkins University, Baltimore, said: "It is the first instance where AI is implemented at the bedside, used by thousands of providers, and where we are seeing lives saved."

It scours the medical records and clinical notes of more than half a million patients over two years to identify those at risk of life-threatening complications.

Prof Saria said: "This is an extraordinary leap that will save thousands of sepsis patients annually.

"And the approach is now being applied to improve outcomes in other important problem areas beyond sepsis."

The bloodstream infection claims 11 million lives each year worldwide.

It is triggered by staph (Staphylococcus aureus) bacteria, a germ found on the skin - and is one of the major complications of COVID-19.

Sepsis causes one in five deaths globally - more than cancer. Almost a third of cases lead to organ damage or failure.

It is easy to miss since symptoms such as fever and confusion are common in other conditions. The faster it’s caught, the better a patient’s chances for survival.

Prof Saria said: "One of the most effective ways of improving outcomes is early detection and giving the right treatments in a timely way, but historically this has been a difficult challenge due to lack of systems for accurate early identification."

The machine-learning technique shows doctors when someone is at risk for sepsis and suggests treatment protocols - such as starting antibiotics.

It has been named the Targeted Real-Time Early Warning System.

It tracks patients from when they arrive in hospital through to discharge - ensuring critical information isn't overlooked even if they move wards or staff change.

During the study, more than 4,000 doctors from five hospitals used the Targeted Real-Time Early Warning System to treat 590,000 people.

The Targeted Real-Time Early Warning System also reviewed 173,931 previous cases - accurately diagnosing sepsis around half the time.

Previous attempts to use electronic tools to detect sepsis caught fewer than half as many - and were accurate two to five percent of the time.

All sepsis cases are eventually caught, but with the current standard of care, the condition kills 30% of the people who develop it.

In the most severe sepsis cases where an hour delay is the difference between life and death, the AI detected it an average of nearly six hours earlier than traditional methods.

Co-author Dr. Albert Wu, also from Johns Hopkins, said: "This is a breakthrough in many ways.

"Up to this point, most of these types of systems have guessed wrong much more often than they get it right. Those false alarms undermine confidence."

Unlike conventional approaches, the system allows doctors to see why the tool is making specific recommendations.

The work is extremely personal to Prof Saria, who lost her nephew as a young adult to sepsis.

She said: "Sepsis develops very quickly and this is what happened in my nephew's case. When doctors detected it, he was already in septic shock."

University spin-off Bayesian Health led and managed the deployment across all testing sites.

The team also partnered with the two largest electronic health record system providers, Epic and Cerner, to ensure that the tool can be implemented at other hospitals.

They have adapted the technology to identify patients at risk for pressure injuries, commonly known as bed sores, and those at risk for sudden deterioration caused by bleeding, acute respiratory failure and cardiac arrest.

Prof Saria added: "The approach used here is foundationally different. It is adaptive and takes into consideration the diversity of the patient population, the unique ways in which doctors and nurses deliver care across different sites, and the unique characteristics of each health system, allowing it to be significantly more accurate and to gain provider trust and adoption."

The AI described in the journal Nature Medicine could combat a growing health crisis fuelled by resistance to antibiotics.

Sepsis is among the worst problems facing intensive care patients. One in three who die in a hospital has it.

It occurs when the body responds extremely to an infection - wrecking the immune system. Drugs often fail to work - because they are administered too late.

Sepsis can affect anyone after an injury or minor infection. But people with weakened immune systems are most at risk - along with the very young or old.