The findings, published in Nature Communications, show monitoring

vital signs using AI-powered wearables can help patients and hospital staff

While hospitals nationwide want to keep patients from regressing and requiring unplanned Intensive Care Unit (ICU) transfers, researchers from Northwell Health’s Feinstein Institutes for Medical Research published today in Nature Communications a new study about artificial intelligence (AI)-powered wearable devices. The study showed the AI algorithm can predict patient deterioration up to 17 hours in advance of adverse clinical outcomes, providing the opportunity to intervene earlier and improve patient outcomes.

This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20251103673132/en/

Dr. Theodoros Zanos led the study. (Credit: Feinstein Institutes).

The new study, titled “Development and validation of a clinical wearable deep learning based continuous in hospital deterioration prediction model,” was led by Theodoros P. Zanos, PhD, head of the Northwell’s Division of Heath AI, and associate professor in the Feinstein Institutes’ Institute of Bioelectronic Medicine and the Institute of Health System Science.

“Currently, hospital staff rely on intermittent vital sign checks of a patient, like their heart rate or temperature, to identify worsening conditions,” said Dr. Zanos. “Combining clinical wearables with the predictive AI algorithm we have developed, we can help clinicians identify these deteriorations a lot earlier and more accurately than standard of care early warning scores, improving patient outcomes.”

Clinical wearables, including the VitalPatch^® biosensor from Vital Connect, Inc. were placed on the chests of 888 adult non-ICU Northwell inpatients, capturing heart rate, respiratory rate, temperature and movement. The AI model continuously analyzed data from the clinical wearables and demographics and flagged at-risk patients an average of 17 hours before their condition worsened. AI predicted 50 percent of rapid response team activations, which entails an emergency clinical team mobilized to assist the patient at time of deterioration. It anticipated more than 83 percent of unplanned ICU transfers – patients who were considered stable whose conditions worsened – and identified all cases that would have involved breathing tubes, cardiac arrest, or death within 24 hours. Importantly, the AI algorithm is agnostic to the clinical wearable used, as long as the measurements are accurate.

Dr. Zanos and his team, including senior biomedical engineer and first author of the paper, Michael Scheid, PhD, developed the AI model, known as a recurrent neural network (RNN) model, which leverages continuous monitoring (CM) data from the wearable biosensors.

“Dr. Zanos and his team continue to pioneer new AI tools for use in hospitals and clinics,” said Kevin J. Tracey, MD, president and CEO of the Feinstein Institutes and Karches Family Distinguished Chair in Medical Research. “This research leverages data, technology and clinical expertise to improve safety and efficiency in patient care.”

The Feinstein Institutes for Medical Research is the global scientific home of bioelectronic medicine, which combines molecular medicine, neuroscience and biomedical engineering. At the Feinstein Institutes, medical researchers use modern technology to develop new device-based therapies to treat disease and injury.

Building on years of research in molecular disease mechanisms and the link between the nervous and immune systems, Feinstein Institutes’ researchers discovered neural targets that can be activated or inhibited with neuromodulation devices, like vagus nerve implants, to control the body’s immune response and inflammation. If inflammation is successfully controlled, diseases – such as arthritis, pulmonary hypertension, heart failure, inflammatory bowel diseases, diabetes, cancer and autoimmune diseases – can be treated more effectively.

Beyond inflammation, using novel brain-computer interfaces, Feinstein Institutes’ researchers developed techniques to bypass injuries of the nervous system so that people living with paralysis can regain sensation and use their limbs. By producing bioelectronic medicine knowledge, disease and injury could one day be treated with our own nerves without costly and potentially harmful pharmaceuticals.

This research is the result of a $3 million NIH grant that was awarded to Dr. Zanos in 2023. Previously, in 2020, he and his lab developed a digital tool that predicts a hospitalized patient’s overnight stability and determines whether they could be left undisturbed overnight to sleep, recover and discharge faster. This vital sign monitoring tool, called “Let Sleeping Patients Lie” led him to become a finalist for Fast Company’s 2021 World Changing Ideas Award.

About the Feinstein Institutes

The Feinstein Institutes for Medical Research is the home of the research institutes of Northwell Health, the largest health care provider and private employer in New York State. Encompassing 50+ research labs, 3,000 clinical research studies and 5,000 researchers and staff, the Feinstein Institutes raises the standard of medical innovation through its six institutes of behavioral science, bioelectronic medicine, cancer, health system science, molecular medicine, and translational research. We are the global scientific leader in bioelectronic medicine – an innovative field of science that has the potential to revolutionize medicine. The Feinstein Institutes publishes two open-access, international peer-reviewed journals Molecular Medicine and Bioelectronic Medicine. Through the Elmezzi Graduate School of Molecular Medicine, we offer an accelerated PhD program. For more information about how we produce knowledge to cure disease, visit http://feinstein.northwell.edu and follow us on LinkedIn.

View source version on businesswire.com: https://www.businesswire.com/news/home/20251103673132/en/