Though medical laboratory testing is key to confirming sepsis, predictive analytics systems can identify early indications and alert caregivers, potentially saving lives
Medical laboratory testing has long been the key element in hospitals’ fight to reduce deaths caused by sepsis, a complication caused by the human body’s response to infection which can injure organs and turn fatal. But clinical laboratory testing takes time, particularly if infectious agents must be cultured in the microbiology lab. And sepsis acts so quickly, by the time the condition is diagnosed it is often too late to prevent the patient’s death.
To speed detection and diagnosis, several large healthcare providers are adding predictive analytics, artificial intelligence (AI) and machine learning technologies to their efforts to reduce sepsis-related mortality.
One example is HCA Healthcare (NYSE:HCA), the for-profit corporation with 185 hospitals, 119 freestanding surgery centers, and approximately 2,000 sites of care in 21 US states and in the United Kingdom.
SPOT receives clinical data in real time directly from monitoring equipment at the patient’s bedside and uses predictive analytics to examine the data, including medical laboratory test results. If the data indicate that sepsis is present, SPOT alerts physicians and other caregivers.
With SPOT, HCA’s physicians have been detecting sepsis in its earliest stages and saving lives. This lends support to the growing belief that AI and machine learning can improve speed to diagnosis and diagnostic accuracy, which Dark Daily has covered in multiple e-briefings.
HCA began developing the software in 2016. It was initially deployed in 2018 at TriStar Centennial Medical Center, HCA’s flagship hospital in Nashville,The Tennessean reported. It is now installed in most of the hospitals owned or operated by HCA.
Michael Nottidge, MD, is ICC Division Medical Director for Critical Care at HCA Healthcare Physician Services Group, and a critical care physician at TriStar Centennial. Nottidge told The Tennessean that unlike a heart attack or stroke, “sepsis begins quietly, then builds into a dangerous crescendo.”
Since its implementation, “[SPOT] has alerted clinicians to a septic patient nearly every day, often hours sooner than they would have been detected otherwise,” Nottidge told The Tennessean.
HCA’s SPOT system uses machine learning to ingest “millions of data points on which patients do and do not develop sepsis,” according to an HCA blog post. “Those computers monitor clinical data every second of a patient’s hospitalization. When a pattern of data consistent with sepsis risk occurs, it will signal with an alert to trained technicians who call a ‘code sepsis.’”
More Accurate than Clinicians
The federal Centers for Disease Control and Prevention (CDC) estimates that more than 250,000 Americans die from sepsis each year. The Sepsis Alliance describes the life-threatening complication as the “leading cause of death in US hospitals.”
Like most health systems, HCA has been battling sepsis for many years using guidelines and educational tools provided by the Surviving Sepsis Campaign (SSC), a joint initiative of the Society of Critical Care Medicine (SCCM) and the European Society of Intensive Care Medicine (ESICM), Modern Healthcare reported.
Early detection and treatment are key to reducing sepsis mortalities. However, a study in the journal Clinical Medicine reported that, despite recent advances in identifying at-risk patients, “there is still no molecular signature able to diagnose sepsis.”
And according to a study published in Critical Care Medicine, the survival rate is about 80% when treatment is administered in the first hour, but each hour of delay in treatment decreases the average survival rate by 7.6%.
In an interview with Becker’s Hospital Review, HCA’s Chief Medical Officer and President of Clinical Services, Jonathan Perlin, MD, PhD, touted SPOT’s reliability, having “very few false positives. In fact, it is more than 50% more accurate at excluding patients who don’t have sepsis than even the best clinician.”
Perlin also told The Tennessean that SPOT can detect sepsis “about eight to 10 hours before clinicians ever could.”
Other Healthcare Providers Using AI-Enabled Early-Warning Tools
In November 2018, the emergency department at Duke University Hospital in Durham, N.C., began a pilot program to test an AI-enabled system dubbed Sepsis Watch, reported Health Data Management. The software, developed by the Duke Institute for Health Innovation, “was trained via deep learning to identify cases based on dozens of variables, including vital signs, medical laboratory test results, and medical histories,” reported IEEE Spectrum. “In operation, it pulls information from patients’ medical records every five minutes to evaluate their conditions, offering intensive real-time analysis that human doctors can’t provide.”
Earlier this year, Sentara Norfolk General Hospital in Norfolk, Va., installed an AI-enabled sepsis-alert system developed by Jvion, a maker of predictive analytics software. “The new AI tool grabs about 4,500 pieces of data about a patient that live in the electronic record—body temperature, heart rate, blood tests, past medical history, gender, where they live and so on—and runs it all through an algorithm that assesses risk for developing sepsis,” reported The Virginian Pilot.
Geisinger Health System, which operates 13 hospitals in Pennsylvania and New Jersey, is working on its own system to identify sepsis risk. It announced in a September news release that it had teamed with IBM to develop a predictive model using a decade’s worth of data from thousands of Geisinger patients.
“The model helped researchers identify clinical biomarkers associated with higher rates of mortality from sepsis by predicting death or survival of patients in the test data,” Geisinger stated in the news release. “The project revealed descriptive and clinical features such as age, prior cancer diagnosis, decreased blood pressure, number of hospital transfers, and time spent on vasopressor medicines, and even the type of pathogen, all key factors linked to sepsis deaths.”
So, can artificial intelligence and predictive analytics added to medical laboratory test results help prevent sepsis-related deaths in all hospitals? Perhaps so. Systems like SPOT, Sepsis Watch, and others certainly are logging impressive results.
It may not be long before similar technologies are aiding pathologists, microbiologists, and clinical laboratories achieve improved diagnostic and test accuracy as well.