Bedside monitors in cardiac intensive care units measure everything from patients’ blood pressure and blood oxygen levels to their heart rate and rhythm.

Digital and waveform measurements provide valuable information to doctors and nurses monitoring patients for immediate signs of distress. But once this information appears on a screen, it is gone forever.

What if data could be captured and processed in real time?

04/10/22 – PORTLAND, ME. – Rai Winslow, Northeast Professor of Bioengineering and Director of Life Sciences and Medicine, poses for a portrait Tuesday, Oct. 4, 2022. Winslow’s HEART research project aims to take complex data sets on patients in hospitals and translate them into measures that will predict the likelihood that this patient will need to be readmitted after returning home. Photo by Alyssa Stone/Northeastern University

Could big data help predict which patients might be susceptible to infections that can lead to life-threatening sepsis?

Could it identify patients who are at increased risk of readmission?

Raymond “Rai” Winslowa national leader in computational medicine based at Northeastern’s Roux Institute in Portland, Maine, thinks so.

He is a principal investigator on a research project with MaineHealth that aims to take complex patient datasets from the state’s largest cardiothoracic intensive care unit and translate them into metrics that could better predict adverse outcomes. , in time for doctors to avoid them whenever possible.

The project is known as HEART for Healthcare Enabled by AI in Real-Time and is largely funded by Northeastern University’s Impact engine program.

“The goal of HEART is to use machine learning models to collect data from patients as they recover in ICU CT, and every moment a new metric comes into play to predict their risk of develop a complication”, explains Winslow, Director of Research in Life Sciences and Medicine at Le Roux.

Twenty percent of heart surgery patients develop complications, and of those patients, 20% don’t survive, he says.

Doctors can use the level of risk assigned to patients by computational medicine to determine which patients need more intense treatment and which are doing well, he says.

“The idea being that if you can make that prediction in advance before the complication actually happens, you can step in and help.”

Winslow says he started working on the HEART project about a year ago, after coming to the Roux Institute at Johns Hopkins University School of Medicine, where he was the founding director of the Institute for Computational Medicine. .

Dr. Douglas Sawyer, director of studies at MaineHealth and Maine Medical Center, approached him with the project, and “it moved quickly,” Winslow says.

He says he expects to enroll patients recovering from heart surgery in MaineHealth’s 12-bed intensive care unit in clinical trials in 18 months.

But first, researchers need to develop a model of the cardiovascular disease process using large patient datasets and animal models of disease.

The next step is to take streaming data from individual patients, send it to the cloud for anonymization, and analyze what the data bodes for patient recovery.

“We are using machine learning methods applied to population data to learn an algorithm that could reliably select patients with sepsis who go on to develop septic shock,” for example, Winslow says.

If the estimate of development of the often-fatal syndrome is 90%, doctors are likely to take a different approach than if the risk for a particular patient is 20%, he says.

The final step is finding a way to deliver the information to medical staff in an digestible and timely format, Winslow says.

“We don’t tell (doctors) what to do, what procedures to perform,” he says. “We are simply informing them that this patient is heading for a complication. “Use your knowledge, common sense, intuition and experience to treat this patient as you see fit.”

Winslow predicts that Project HEART will help reduce readmissions by helping patients recover more fully in hospital.

And that affects a hospital’s bottom line, since the Centers for Medicare and Medicaid Services change reimbursement rates based on hospital readmission rates, Winslow says.

Other medical and academic centers, including University College Dublin, Ireland, Tufts Medical Center in Boston and Northeastern University in Toronto, have expressed interest in joining the HEART research project, Winslow says.

The prospect of medical heavyweights joining HEAR comes as no surprise to Gene TunikAssociate Dean for Research and Innovation at Northeastern’s Bouve College of Health Sciences, who called Winslow’s appointment to Roux a “game changer.”

“It’s a huge feather in our cap. He is a great figure in computational medicine. It’s just fantastic that he’s at Northeastern.

Tunik leads a post-ICU phase of the HEART project, which involves using the computational medicine model to predict how well MaineHealth cardiothoracic surgery patients are progressing through the recovery process.

“The trajectory of their care does not stop at intensive care. In the later stages, rehabilitation services become very important,” says Tunik, who is also director of AI Plus Health at Northeastern’s Experiential AI Institute.

Winslow says he sees the predictive service eventually being made available to all hospitals, large and small, with computed data in the cloud, he says, “it means a community hospital doesn’t have to invest in a huge infrastructure”.

Winslow, who was born in Portland and grew up a few miles away, says he’s impressed with how quickly MaineHealth has responded to new intellectual and practical challenges in patient care.

“I was at Johns Hopkins for 30 years and was very happy there. I left and came to Le Roux for several reasons. The first is that I thought Maine’s healthcare system was something special.

“It has very high quality clinician-researchers and clinicians. It can attract faculty nationwide. They are hungry. They are eager to improve their institution and make it a well-known university research center.

“They really want to see this technology in the clinic, helping their patients,” Winslow says. And it’s not just doctors. “The nurses and technicians I’ve spoken to are all excited about it. Everyone is.”

He sees HEART’s predictive model eventually expanding to “almost all types of care decisions in critical care”.

“Think of what a doctor does when he comes in the morning and makes his rounds and sees his patient. They want to know, “What is my patient’s condition?” If it’s bad, ‘What can I do, how can I improve them?’ If it’s good, “Great, how can I make them even better?”

For media inquiriesplease contact [email protected].