Diagnostic test incorporates artificial intelligence and could shorten the time clinical laboratories need to determine patients’ risk for antimicrobial resistance
Sepsis continues to be a major killer in hospitals worldwide. Defeating it requires early diagnosis, including antimicrobial susceptibility testing (AST), and timely administration of antibiotics. Now, in a pilot study, scientists at Seoul National University in South Korea have developed a new clinical laboratory test that uses artificial intelligence (AI) to pinpoint the condition sooner, enabling faster treatment of the deadly bacterial infection.
Sepsis, also known as septicemia or blood poisoning, is a serious medical condition that occurs when the body overreacts to an infection or injury. This often takes place in hospitals through blood-line infections and exposure to deadly bacteria. The dangerous reaction causes extensive inflammation throughout the body. If not treated early, sepsis can lead to organ failure, tissue damage, and even death.
Research teams around the world are creating new technologies and approaches to slash time to answer from when blood specimen is collected to a report of whether the patient is or is not positive for sepsis. The Seoul National University scientists’ new approach is yet another sign for microbiologists and clinical laboratory managers of the priority test developers are giving to solving the problem of diagnosing sepsis faster than using blood culture methodology, which requires several days of incubation.
“Sepsis strikes over 40 million people worldwide each year, with a mortality rate ranging from 20% to 50%,” said Sunghoon Kwon, PhD (above), professor of electrical and computer engineering at Seoul National University and senior author of the study, in an interview with The Times in the UK. “This high mortality rate leads to over 10 million deaths annually. Thus, accurate and prompt antibiotic prescription is essential for treatment,” he added. Clinical laboratories play a critical role in the testing and diagnosis of sepsis. (Photo copyright: Seoul National University.)
Reducing Time to Diagnosis
Seoul National University’s approach begins with drawing a sample of the patient’s blood. The researchers then attach special peptide molecules to magnetic nanoparticles and add those nanoparticles to the blood sample. The particles bind to the harmful pathogens in the blood.
The harmful bacteria are then collected using magnets. Their DNA is extracted, amplified, and analyzed to establish the type of microbes that are present in the sample.
The pathogens are exposed to antibiotics and an AI algorithm evaluates their growth patterns to forecast what treatments would be most beneficial to the patient. This last step is known as antimicrobial susceptibility testing or AST.
“The principle is simple,” said Sunghoon Kwon, PhD, professor of electrical and computer engineering at Seoul National University and senior author of the study, in a Nature podcast. “We have a magnetic nanoparticle. The surface of the magnetic nanoparticle we coat in a peptide that can capture the bacteria.”
Kwon is the CEO of Quantamatrix, the developer of the test.
The complete process can be performed on one machine and results are available in about 12 hours, which reduces typical AST time by 30 to 40 hours when compared to traditional processes.
“Sepsis progresses very quickly, with the survival rate dropping with each passing hour,” Kwon told The Times UK. “Every minute is crucial.”
Preventing Antimicrobial Resistance
The team assessed the performance of their test on 190 hospital patients who had a suspected sepsis infection. The test achieved a 100% match in the identification of a bacterial species. The test also achieved an efficiency of 96.2% for capturing Escherichia coli (E. coli) and 91.5% for capturing Staphylococcus aureus.
“Treatment assessment and patient outcome for sepsis depend predominantly on the timely administration of appropriate antibiotics,” the authors wrote in Nature.
“However,” they added, “the clinical protocols used to stratify and select patient-specific optimal therapy are extremely slow,” due to existing blood culture procedures that may take two or three days to complete.
“The microbial load in patient blood is extremely low, ranging between 1 and 100 colony-forming units (CFU) ml−1 and is vastly outnumbered by blood cells,” the study authors explained. “Due to this disparity, prior steps—including blood culture (BC) to amplify the number of pathogens followed by pure culture to subculture purified colonies of isolates—have been essential for subsequent pathogen species identification (ID) and AST.”
Further research, studies and regulatory approval are needed before this technique becomes available, but the South Korean scientists believe it could be ready for use within two to three years. They also state their test can help prevent antimicrobial resistance (AMR) and bolster the strength of existing antibiotics.
Previous Studies
The Seoul National University study is just the latest effort by scientists to develop faster methods for clinical laboratory testing and diagnosing of sepsis.
In September, Dark Daily reported on a similar test that uses digital imaging and AI to determine sepsis risk for emergency room patients.
According to the Centers for Disease Control and Prevention (CDC), at least 1.7 million adults develop sepsis annually in the US, and that at least 350,000 die as a result of the condition. CDC also lists sepsis as one of the main reasons people are readmitted to hospitals.
Microbiologists and clinical laboratory managers should be aware that scientists are prioritizing the creation of new testing methods for faster detection of sepsis. Various research teams around the world are devising technologies and approaches to reduce the time needed to diagnose sepsis to improve patient outcomes and save lives.
With FDA clearance already approved, hospital infection control teams and their clinical laboratories may have another diagnostic tool for diagnosing blood infections
Controlling sepsis in hospitals continues to be a major concern in nations around the world, including in the United States. Now, a new 10-minute clinical laboratory blood test that uses artificial intelligence (AI) and digital images to spot biomarkers of the potentially fatal condition may soon be available for use in hospitals. The test, which was approved to be marketed in the US in 2022 by the federal Food and Drug Administration (FDA), may be “one of the most important breakthroughs in modern medical history,” according to US researchers, Good News Network (GNN) reported.
“Early detection of sepsis is an invaluable capability for healthcare professionals. Quickly identifying sepsis is critical to saving lives, but until now, we’ve lacked a reliable tool to either recognize the condition or explore alternate diagnoses,” said O’Neal in an LSU press release.
“IntelliSep is truly a game changer,” said Hollis O’Neal, MD (above), Associate Professor of Medicine at Louisiana State University Health Sciences Center in Baton Rouge. “The test provides hospital staff with information needed to identify and treat septic patients efficiently and reduce the financial and health burdens of overtreatment for hospitals and patients.” Clinical laboratories may have a new blood test for sepsis by the end of the year. (Photo copyright: Louisiana State University.)
How IntelliSep Works
The IntelliSep test analyzes blood samples extracted from emergency room patients who present with sepsis symptoms by squeezing white blood cells through a tiny tube to determine how the cells react and if they change shape. White blood cells in patients with sepsis are softer and spongier and their shape compresses and elongates, increasing the likelihood of developing sepsis.
Images are taken of the cells using an ultra-high-speed camera that can capture up to 500,000 frames per second. The images are the analyzed by an AI-powered computer which calculates the total number of elongated white blood cells to determine if sepsis is present.
IntelliSep then separates patients into three bands of risk for developing sepsis:
Band 1 (low)
Band 2 (medium)
Band 3 (high)
Results of the test are available to emergency room personnel in less than 10 minutes.
“Sepsis is notorious as the ‘silent killer’ because it is so easily missed early on, when a patient’s symptoms can often be mistaken for other less serious illnesses,” Michael Atar, PhD, DDS, Associate Professor, Pediatric Dentistry at New York University told Good News Network. “Rapid diagnosis and treatment is crucial to a good outcome, but there has never been a single, reliable diagnostic test available to doctors, costing precious time and people’s lives.”
Atar is a lead medical technology investor and an advisor to Cytovale.
‘Holy Grail’ of Sepsis Diagnosis
To complete the IntelliSep study, researchers enrolled 1,002 ER patients who presented with signs of sepsis. IntelliSep correctly identified patients who did not have sepsis with an accuracy rate of 97.5%. The technology showed an accuracy rate of 55% for positive sepsis results. Researchers also used IntelliSep to quickly diagnose and assess the severity of a sepsis infection.
There were no sepsis deaths reported in patients with low-risk scores. This indicates the test could help physicians rule out sepsis and seek other diagnoses for those patients.
“Cytovale’s IntelliSep device is, by any objective measure, the ‘holy grail’ that the medical community has been so desperate to find,” Atar told Good News Network. “The technology behind it is genuinely groundbreaking and it has the real-world, tried-and-tested potential to save millions of lives, year on year, across the planet.”
The technology is currently being used in a few hospitals in Louisiana and the inventors hope to have it available in at least 10 other hospitals by the end of the year.
Our Lady of the Lake Regional Medical Center, a not-for-profit Catholic healthcare ministry located in Baton Rouge, was one of the first hospitals to implement IntelliSep.
“Cytovale’s innovative technology will help drastically decrease the number of sepsis-related deaths in hospital settings, and we are honored that, since day one, we have been a part of the research that led to this technology,” said Chuck Spicer, President of Our Lady of the Lake Health in a news release.
Saint Francis Medical Center in Monroe, La., announced on September 3 that it has started using the IntelliSep test in its emergency rooms and staff are impressed by the impact on hospital efficiency.
“If it turns out negative then you don’t have to treat as many patients as you did before, which runs up costs, hospital bills and causes people to be in the hospital for longer periods of time,” said pulmonary disease physician Thomas Gullatt, MD, President, St. Francis Health, told KNOE News.
Patient Expectations for Treatment
Sepsis, also known as septicemia or blood poisoning, is a serious medical condition that occurs when the body improperly reacts to an infection or injury. The dangerous reaction causes extensive inflammation throughout the body and, if not treated early, can lead to organ failure, tissue damage, and even death.
The Centers for Disease Control and Prevention (CDC) reports at least 1.7 million adults develop sepsis annually in the US and at least 350,000 die as a result of the condition. It also states sepsis is one of the main reasons people are readmitted to hospitals.
Clinical laboratories should be aware of developments in the use of this new diagnostic assay and how it is aiding the diagnosis, antibiotic selection, and monitoring of patients with this deadly infection. Patients often learn about new technologies and come to their hospital or provider expecting to be treated with these innovations.
