May 16, 2019
HCA Healthcare using algorithm driven technology to detect sepsis early and help save 8,000 lives
Developed by HCA Healthcare clinical experts, data scientists and programmers, SPOT technology combines data from 31 million annual patient care episodes with artificial intelligence techniques
Nashville, TN – HCA Healthcare (NYSE: HCA), a leading healthcare provider with 185 hospitals and approximately 2,000 sites of care in 21 states and the United Kingdom, today announced it has developed an algorithm driven, real-time system to more quickly identify patients with sepsis and help save lives. HCA Healthcare’s Sepsis Prediction and Optimization of Therapy, or SPOT, technology so far has been used with 2.5 million patients and, in conjunction with the use of evidence-based clinical interventions, has helped save an estimated 8,000 lives in the last five years.
Sepsis is an overwhelming infection that can lead to total body failure, and approximately 270,000 Americans die from it each year, making it more deadly than breast cancer, prostate cancer, and AIDS combined, according to Sepsis Alliance. Additionally, it is the No. 1 cause of death in non-cardiac intensive care units in all hospitals and the 11th leading cause of death overall in the U.S. Because the symptoms of sepsis are similar to those of many other illnesses, diagnosing it can be very challenging; however, studies have shown with early recognition followed by aggressive treatment, patient survival can increase significantly because sepsis mortality increases by 4 to 7 percent every hour it goes undetected.
“With sepsis, minutes matter, and just as we’ve improved safety in our homes with smoke detectors that ‘sniff out’ possible fire, HCA Healthcare’s SPOT technology now helps detect sepsis earlier, accelerating treatment, improving the care provided to our patients and thereby saving lives,” said Dr. Jonathan Perlin, HCA Healthcare’s chief medical officer and president, clinical services group.
HCA Healthcare’s SPOT, which uses the popular dog name because it sniffs out sepsis in a way humans cannot, is an algorithm and alert system for the early detection of sepsis. Created by HCA Healthcare clinical and IT experts using data from millions of hospitalizations, SPOT continuously monitors vital signs, lab results, nursing reports and other data that can inform treatment, and recognizes critical data points in patients’ electronic health records. HCA Healthcare’s SPOT links algorithmic sepsis detection with clinical workflow and quickly alerts care teams to important, often subtle changes in a patient’s condition so they can take appropriate action.
“If you or your loved one were in the hospital, what would you want from the perfect clinician? You would want them focused on you, and only you, 24 hours a day. You want them analyzing every new piece of lab data when it is created, and you want them to understand the implications of that data and the relationships between the different pieces of data,” said Dr. Perlin. “SPOT is designed to monitor available data every moment of every day, and when combinations of lab data that are consistent with sepsis are detected, the system responds by alerting clinicians so they can more quickly intervene with potentially life-saving treatment for you or your loved one.”
Because HCA Healthcare’s SPOT algorithm was informed by data from 31 million annual patient care episodes, it is highly sensitive and precise. It detects signs of potential sepsis humans cannot see, while excluding instances when humans inaccurately suspect sepsis.
“Studies about sepsis show that the sooner we can act, and act effectively, the more likely the patient is to survive. SPOT is a technology and workflow that helps us catch sepsis early and more likely prevent catastrophe,” said Dr. Michael Nottidge, critical care medical director at HCA Healthcare’s TriStar Centennial Medical Center. “SPOT does not make decisions, but it monitors in the background and brings vital, accurate and up-to-date information to the people who do make decisions.”
Sabrina Burkdoll, a registered nurse with HCA Healthcare’s Menorah Medical Center in Overland Park, Kansas, experienced the benefits of SPOT firsthand during a recent bout with pneumonia. After two days at home on antibiotics, Burkdoll was getting worse, not better, and came to the Menorah ER with shortness of breath and a fever. ER staff diagnosed her with sepsis and began treating her and monitoring her, while starting the process of admitting her; however, before she was moved to an inpatient room, SPOT detected that the sepsis had quickly progressed to septic shock, a dangerous condition that can lead to organ failure and death. SPOT alerted the care team who confirmed this and took quick action. Burkdoll would stay in the hospital for three days, but the timely SPOT alert helped Menorah caregivers effectively treat her condition and prevent a transfer to the ICU.
“As a nurse, I understand sepsis, but as a patient I didn’t fully realize what was happening to me and how dire the situation had become,” said Burkdoll. “I am so grateful for the quick response, because without it, I’m not sure I would have survived. Speaking from personal experience, SPOT is a life-saving tool, and I know our patients are in better hands because we have it.”
SPOT is the first of many initiatives across HCA Healthcare to leverage data at-scale and in real-time to drive both discovery and improvement as a natural outgrowth of patient care. HCA Healthcare’s clinical and data science teams expect to continue to improve the algorithm, combining real-world experiences and outcomes with techniques of machine learning and artificial intelligence to enhance clinical effectiveness. Building upon the SPOT technology employed in the inpatient setting, HCA Healthcare is developing “SPOT-ER,” which HCA plans to begin deploying in emergency rooms this year. HCA Healthcare also has plans to use machine learning to more quickly detect other critical or life-threatening conditions such as shock in trauma patients, post-operative complications, and early signs of deterioration in all patients. The opportunity to improve care through clinical informatics and machine learning is substantial, and HCA Healthcare is leveraging its scale to do so.
HCA Healthcare is a learning health system that uses the significant data it collects from approximately 31 million annual patient care episodes to inform and improve the care it provides to patients. HCA Healthcare’s national clinical data warehouse, which receives information from the electronic health record, is the heart of HCA’s data ecosystem, providing the ability to aggregate and analyze data streams in real time and feed tools like SPOT that, in turn, provide actionable information to caregivers.
This information architecture also supports HCA Healthcare’s efforts to drive continuous learning and improvement, and was the basis for the renowned REDUCE MRSA trial, a three-arm, comparative effectiveness study involving 43 cluster-randomized hospitals and nearly 75,000 patients. In just 18 months, the study demonstrated a 44 percent all-cause reduction of potentially life-threatening bloodstream infections among intensive care unit patients by employing a “universal decolonization” strategy. The learning model also underpins a recent study, known as the ABATE Infection (Active BAThing to Eliminate infection) Trial, conducted exclusively at HCA Healthcare hospitals. The study found an antiseptic wash achieved a 31 percent reduction in bloodstream infections and nearly a 40 percent reduction in antibiotic-resistant bacteria among non-ICU patients with central line catheters and lumbar drains. The Centers for Disease Control was engaged in both REDUCE MRSA and ABATE, and universal decolonization in the ICU is now recognized worldwide as a best practice.