Geisinger, IBM Develop Predictive Technology for Spotting Sepsis Risk

Sept. 12, 2019
Geisinger will now aim to develop more personalized clinical care plans for at-risk sepsis patients

The Danville, Pa.-based Geisinger Health and a data science team at IBM have come together to create a predictive model for detecting sepsis risk using data from the integrated health system’s electronic health record (EHR).

Geisinger’s team of scientists, led by Shravan Kethireddy, M.D., initiated a project to build a predictive model for sepsis mortality based on data from an actual, critical hospital setting. Partnering with the IBM Data Science and AI Elite teams, they assembled a six-person swat team to develop two projects: a model to predict sepsis mortality and a tool to keep the team on top of the latest sepsis research.

The team used IBM Watson Studio open source tools to build a predictive model that would ingest clinical data from thousands of de-identified sepsis patients spanning a decade. Then they used all the data to build another model to predict patient mortality during the hospitalization period or during the 90 days following their hospital stay. 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, according to officials from the two organizations.

“For clinicians, making a sepsis diagnosis can be very difficult, as the symptoms overlap with many other common illnesses. If we can identify patients more quickly and more accurately, we can administer the right treatments early and increase the chances of a positive outcome,” said Donna Wolk, Ph.D., division director, molecular and microbial diagnostics and development at Geisinger.

Indeed, the body's response to an infection can cause sepsis, a potentially life-threatening condition that affects about 1.7 million American adults. Sepsis is a complex syndrome that is difficult to identify early, as symptoms such as fever and low blood pressure overlap with other common illnesses. The infection is linked to more than 250,000 deaths annually, researchers stated.

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.

“Our experience using machine learning and data science has been very positive, and we see huge potential to continue its use in the medical field,” said Vida Abedi, Ph.D., Geisinger staff scientist, Department of Molecular and Functional Genomics.  “We are well on our way to breaking new ground in clinical care for sepsis and achieving more positive outcomes for our patients.”

Equipped with the new model, Geisinger will aim to develop more personalized clinical care plans for at-risk sepsis patients. Geisinger hopes to increase patient chances of recovery by paying attention to the key factors linked to sepsis deaths, officials stated.

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.

“It’s very important for me as a clinician and a research scientist to save patient lives using all the knowledge of the data and the clinical background”, said Hosam Farag, M.D., a bioinformatic scientist in Geisinger’s Diagnostic Medicine Institute. “Machine learning can close the care gaps and optimize the treatment. That makes me passionate about how to save patient lives.” 

Sponsored Recommendations

Findings on the Healthcare Industry’s Lag to Adopt Technologies to Improve Data Management and Patient Care

Join us for this April 30th webinar to learn about 2024's State of the Market Report: New Challenges in Health Data Management.

Findings on the Healthcare Industry’s Lag to Adopt Technologies to Improve Data Management and Patient Care

2024's State of the Market Report: New Challenges in Health Data Management

Improving care with AI-powered solutions

Don't miss our April 23rd webinar delving into the transformative impact of AI-powered solutions on healthcare. Join industry leaders Reid Conant and Dr. Patrick McGill as they...

Shield your health system against cyber threats

You won't want to miss out on this imperative April 4th webinar about how you can protect your healthcare organization. Join us to learn how to fortify your health system against...