Researchers Use AI to Predict which COVID-19 Patients will Need a Ventilator to Breathe

Researchers at Case Western Reserve University have developed an online tool to help medical staff quickly determine which COVID-19 patients will need help breathing with a ventilator.

The tool, developed through analysis of CT scans from nearly 900 COVID-19 patients diagnosed in 2020, was able to predict ventilator need with 84% accuracy.

"That could be important for physicians as they plan how to care for a patient - and, of course, for the patient and their family to know," said Anant Madabhushi, the Donnell Institute Professor of Biomedical Engineering at Case Western Reserve and head of the Center for Computational Imaging and Personalized Diagnostics (CCIPD). "It could also be important for hospitals as they determine how many ventilators they’ll need."

Next, Madabhushi said he hopes to use those results to try out the computational tool in real time at University Hospitals and Louis Stokes Cleveland VA Medical Center with COVID-19 patients.

If successful, he said medical staff at the two hospitals could upload a digitized image of the chest scan to a cloud-based application, where the AI at Case Western Reserve would analyze it and predict whether that patient would likely need a ventilator.

Dire need for ventilators

Among the more common symptoms of severe COVID-19 cases is the need for patients to be placed on ventilators to ensure they will be able to continue to take in enough oxygen as they breathe.

Yet, almost from the start of the pandemic, the number of ventilators needed to support such patients far outpaced available supplies - to the point that hospitals began "splitting" ventilators - a practice in which a ventilator assists more than one patient.

While 2021's climbing vaccination rates dramatically reduced COVID-19 hospitalization rates - and, in turn, the need for ventilators - the recent emergence of the Delta variant has again led to shortages in some areas of the United States and in other countries.

"These can be gut-wrenching decisions for hospitals - deciding who is going to get the most help against an aggressive disease," Madabhushi said.

To date, physicians have lacked a consistent and reliable way to identify which newly admitted COVID-19 patients are likely to need ventilators - information that could prove invaluable to hospitals managing limited supplies.

Researchers in Madabhushi’s lab began their efforts to provide such a tool by evaluating the initial scans taken in 2020 from nearly 900 patients from the U.S. and from Wuhan, China - among the first known cases of the disease caused by the novel coronavirus.

Madabhushi said those CT scans revealed - with the help of deep-learning computers, or Artificial Intelligence (AI) - distinctive features for patients who later ended up in the intensive care unit (ICU) and needed help breathing.

The research behind the tool appeared this month in the IEEE Journal of Biomedical and Health Informatics.

Amogh Hiremath, a graduate student in Madabhushi’s lab and lead author on the paper, said patterns on the CT scans couldn’t be seen by the naked eye, but were revealed only by the computers.

"This tool would allow for medical workers to administer medications or supportive interventions sooner to slow down disease progression," Hiremath said. "And it would allow for early identification of those at increased risk of developing severe acute respiratory distress syndrome - or death. These are the patients who are ideal ventilator candidates."

Further research into 'immune architecture'

Madabhushi's lab also recently published research comparing autopsy tissues scans taken from patients who died from the H1N1 virus (Swine Flu) and from COVID-19. While the results are preliminary, they do appear to reveal information about what Madabhushi called the “immune architecture” of the human body in response to the viruses.

"This is important because the computer has given us information that enriches our understanding of the mechanisms in the body against viruses," he said. "That can play a role in how we develop vaccines, for example."

Germán Corredor Prada, a research associate in Madabhushi's lab who was the primary author on the paper, said computer vision and AI techniques allowed the scientists to study how certain immune cells organize in the lung tissue of some patients.

"This allowed us to find information that may not be obvious by simple visual inspection of the samples," Corredor said. "These COVID-19-related patterns seem to be different from those of other diseases such as H1N1, a comparable viral disease."

Eventually, when combined with other clinical work and further tests in larger sets of patients, this discovery could serve to improve the world’s understanding of these diseases and maybe others, he said.

Madabhushi established the CCIPD at Case Western Reserve in 2012. The lab now includes more than 60 researchers. Some were involved in this most recent COVID-19 work, including graduate students Hiremath, Pranjal Vaidya; research associates Corredor and Paula Toro; and research faculty Cheng Lu and Mehdi Alilou.

Hiremath A, Bera K, Yuan L, Vaidya P, Alilou M, Furin J, Armitage K, Gilkeson R, Ji M, Fu P, Gupta A, Lu C, Madabushi A.
Integrated Clinical and CT based Artificial Intelligence nomogram for predicting severity and need for ventilator support in COVID-19 patients: A multi-site study.
IEEE J Biomed Health Inform. 2021 Aug 13;PP. doi: 10.1109/JBHI.2021.3103389

Most Popular Now

Orion Health Supports Professional Recor…

Orion Health is supporting the Professional Record Standards Body's partnership scheme by applying to become a 'quality partner'. The company, which is one of the UK’s leading providers of shared care...

FDA Authorizes Software that Can Help Id…

Today, the U.S. Food and Drug Administration authorized marketing of software to assist medical professionals who examine body tissues (pathologists) in the detection of areas that are suspicious for cancer...

Northumbria Healthcare Picks CliniSys to…

Pathologists at one of England's most innovative trusts have chosen the CliniSys laboratory information system (LIMS) as part of a digital strategy to support its drive to continually improve patient...

Study Finds Telemedicine Appointments Re…

Telemedicine appointments combined with in-person visits significantly reduced the risk of further illness for children with medically complex cases, according to results of a new study by researchers with The...

Contact-Tracing Apps could Improve Vacci…

Mathematical modeling of disease spread suggests that herd immunity could be achieved with fewer vaccine doses by using Bluetooth-based contact-tracing apps to identify people who have more exposure to others...

A Computer Algorithm Called 'Eva' May Ha…

A prescriptive computer program developed by the USC Marshall School of Business and Wharton School of Business of the University of Pennsylvania for Greece to identify asymptomatic, infected travelers...

FDA Clears First Major Imaging Device Ad…

Today, the U.S. Food and Drug Administration cleared the first new major technological improvement for Computed Tomography (CT) imaging in nearly a decade. "Computed tomography is an important medical imaging tool...

Using Internet in Retirement Boosts Cogn…

Using the internet during your retirement years can boost your cognitive function, a new study has found. Researchers from Lancaster University Management School, the Norwegian University Science and Technology and...

AI Tool Improves Accuracy of Breast Canc…

A computer program trained to see patterns among thousands of breast ultrasound images can aid physicians in accurately diagnosing breast cancer, a new study shows. When tested separately on 44,755 already...

Study Shows Trust is still at Heart of N…

A new study has shown that issues surrounding trust are still at the heart of people's reluctance to download and use the NHS App, particularly among Black, Asian and minority...

Time until Dementia Symptoms Appear can …

Researchers at Washington University School of Medicine in St. Louis have developed an approach to estimating when a person who is likely to develop Alzheimer’s disease, but has no cognitive...