Skip to Content
800-533-8762
  • Careers
  • Newsroom
  • Health Care Professionals
  • About Us
  • Contact Us
UPMC
  • Find a Doctor
  • Services
    • Frequently Searched Services
    • Frequently Searched Services
      Allergy & Immunology Behavioral & Mental Health Cancer Ear, Nose & Throat Endocrinology Gastroenterology Heart & Vascular Imaging Neurosciences Orthopaedics
      Physical Rehabilitation Plastic & Reconstructive Surgery Primary Care Senior Services Sports Medicine Telemedicine Transplant Surgery Walk-In Care Weight Management Women’s Health
      See all Services
    • Services by Region
    • Find a UPMC health care facility close to you quickly by browsing by region.
      UPMC in Western Pa. Western Pa. and New York
      UPMC in Central Pa. Central Pa.
      UPMC in North Central Pa. North Central Pa.
      UPMC in Western Md. Maryland & West Virginia
    • See All Services
  • Locations
    • Locations by Type
    • Locations by Type
      UPMC hospitals
      Hospitals
      Physical Therapy
      Physical Therapy
      Urgent care
      Walk-In Care
      UPMC Outpatient Centers
      Outpatient Centers
      UPMC Imaging Services
      Imaging
      Community Health Centers
      Community Health Centers
      See All Locations
    • Locations by Region
    • Locations by Region
      UPMC in Southwest Pa. Southwest Pa.
      UPMC in North Central Pa. North Central Pa.
      UPMC in Northwest Pa and Ny. Northwest Pa. & Western N.Y.
      UPMC in West Central Pa. West Central Pa.
      UPMC in Central Pa. Central Pa.
      UPMC in Western Md. Maryland & West Virginia
    • See All Locations
  • Patients & Visitors
    • Patient & Visitor Resources
    • Patient & Visitor Resources
      Patients and Visitors Resources Pay a Bill Classes & Events Medical Records Health Library Patient Information
      Patient Portals Privacy Information Shared Decision Making Traveling Patients Visitor Information
      Man uses mobile phone
      Pay a Bill
      Nurse reviews medical chart
      Request Medical Records
  • Patient Portals
  • Find Covid-19 updates
  • Schedule an appointment
  • Request medical records
  • Pay a bill
  • Learn about financial assistance
  • Find classes & events
  • Send a patient an eCard
  • Make a donation
  • Volunteer
  • Read HealthBeat blog
  • Explore UPMC Careers
Skip to Content
UPMC
  • Patient Portals
  • For Patients & Visitors
    • Find a Doctor
    • Locations
    • Patient & Visitor Resources
    • Pay a Bill
    • Services
    • More
      • Medical Records
      • Financial Assistance
      • Classes & Events
      • HealthBeat Blog
      • Health Library
  • About UPMC
    • Why UPMC
    • Facts & Stats
    • Supply Chain Management
    • Community Commitment
    • More
      • Financials
      • Support UPMC
      • UPMC Apps
      • UPMC Enterprises
      • UPMC International
  • For Health Care Professionals
    • Physician Information
    • Resources
    • Education & Training
    • Departments
    • Credentialing
  • Careers
  • Contact Us
  • Newsroom
  • UPMC >
  • Media Relations >
  • News Releases >
  • 042522Machine Learning Model
Media Relations
News Releases
Central Pa. News
North Central Pa. News
Contact Us
Experts
Community-Focused News
Media Kits
Media RSS
Media Relations
News Releases
Central Pa. News
North Central Pa. News
Contact Us
Experts
Community-Focused News
Media Kits
Media RSS

Chat Keywords List

  • cancel or exit: Stops your conversation
  • start over: Restarts your current scenario
  • help: Shows what this bot can do
  • terms: Shows terms of use and privacy statement
  • feedback: Give us feedback
Continue
Chat with UPMC
RESTART
MENU
CLOSE

Machine Learning Model Can Steer Traumatic Brain Injury Patients to Life-Saving Care

For Journalists

Anastasia (Ana) Gorelova
Senior Manager, Science Writing
412-647-9966
gorelovaa@upmc.edu

Sheila Davis
Manager
412-313-6070
davissn2@upmc.edu

Want to Make an Appointment or Need Patient Information?
Contact UPMC at

1-800-533-8762.

Go to Find a Doctor to search for a UPMC doctor.

2021 PITT HS horiz

4/26/2022

PITTSBURGH - A prognostic model developed by University of Pittsburgh School of Medicine data scientists and UPMC neurotrauma surgeons is the first to use automated brain scans and machine learning to inform outcomes in patients with severe traumatic brain injuries (TBI). 

  

In a study reported today in the journal Radiology, the team showed that their advanced machine-learning algorithm can analyze brain scans and relevant clinical data from TBI patients to quickly and accurately predict survival and recovery at six-months after the injury.

   

“Every day, in hospitals across the United States, care is withdrawn from patients who would have otherwise returned to independent living,” said co-senior author David Okonkwo, M.D., Ph.D., professor of neurological surgery at Pitt and UPMC. “The majority of people who survive a critical period in an acute care setting make a meaningful recovery—which further underscores the need to identify patients who are more likely to recover.” OKONKWO_DAVIDpress

  

It often takes two weeks for TBI patients to emerge from their coma and begin their recoveries—yet severe TBI patients are often taken off life support within the first 72 hours after hospital admission. The new predictive algorithm, validated across two independent patient cohorts, could be used to screen patients shortly after admission and can improve clinicians’ ability to deliver the best care at the right time.

  

TBI is one of the most pressing public health issues in the U.S.—every year, nearly 3 million people seek TBI care across the nation, and TBI remains a leading cause of death in people under the age of 45. 

 

Recognizing the need for better ways to assist clinicians, the team of data scientists at Pitt set out to leverage their expertise in advanced artificial intelligence to develop a sophisticated tool to understand the nature of each unique patient’s TBI. 

  

“There is a great need for better quantitative tools to help intensive care neurologists and neurosurgeons make more informed decisions for patients in critical condition,” said corresponding author Shandong Wu, Ph.D., associate professor of radiology, bioengineering and biomedical informatics at Pitt. “This collaboration with Dr. Okonkwo’s team gave us an opportunity to use our expertise in machine learning and medical imaging to develop models that use both brain imaging and other clinically available data to address an unmet need.”

   

Led by the co-first authors Matthew Pease, M.D., and Dooman Arefan, Ph.D., the group developed a custom artificial intelligence model that processed multiple brain scans from each patient and combined it with an estimate of coma severity and information about the patient’s vital signs, blood tests and heart function. Importantly, because brain imaging techniques evolve over time and image quality can vary dramatically from patient to patient, the researchers accounted for data irregularity by training their model on different image-taking protocols. WU_SHANDONGpress

  

The model proved itself by accurately predicting patients’ risk of death and unfavorable outcomes at six months following the traumatic incident. To validate the model, Pitt researchers tested it with two patient cohorts: one of over 500 severe TBI patients previously treated at UPMC and the other an external cohort of 220 patients from 18 institutions across the country, through the TRACK-TBI consortium. The external cohort was critical to test the model’s prediction ability.

  

“We hope this research shows that AI can provide a tool to improve clinical decision-making early when a TBI patient is admitted to the emergency room, towards yielding a better outcome for the patients,” said Wu and Okonkwo.

  

Additional authors of this paper include Ava Puccio, Ph.D., Kerri Hochberger, Enyinna Nwachuku, M.D., Souvik Roy, and Stephanie Casillo, all of UPMC; Jason Barber and Nancy Temkin, Ph.D., of the University of Washington; and Esther Yuh, M.D., of the University of California, San Francisco and group-author investigators from the TRACK-TBI Consortium.

 

This research was supported by National Institutes of Health National Cancer Institute (grant R01CA218405), National Institute of Neurological Disorders and Stroke (grant U01 NS1365885 and U01 NS086090), Department of Defense (grants W911QY-14-C-0070, W81XWH-18- 2-0042, W81XWH-15-9-0001 and W81XWH-14-2-0176), Radiological Society of North America

Research Scholar grant RSCH1530, Amazon Machine Learning Research Award and the Congress of Neurological Surgeons Data Science Fellowship grant. 


PHOTO DETAILS: (click images for high-res versions)

Top right photo:

 

CREDIT: UPMC

CAPTION: David Okonkwo, M.D., Ph.D.

 

Bottom right photo:

CREDIT: UPMC

CAPTION: Shandong Wu, Ph.D.

 

 

UPMC
200 Lothrop Street Pittsburgh, PA 15213

412-647-8762 800-533-8762

Patients And Visitors
  • Find a Doctor
  • Locations
  • Pay a Bill
  • Patient & Visitor Resources
  • Disabilities Resource Center
  • Services
  • Medical Records
  • No Surprises Act
  • Price Transparency
  • Financial Assistance
  • Classes & Events
  • Health Library
Health Care Professionals
  • Physician Information
  • Resources
  • Education & Training
  • Departments
  • Credentialing
Newsroom
  • Newsroom Home
  • Inside Life Changing Medicine Blog
  • News Releases
About
  • Why UPMC
  • Facts & Stats
  • Supply Chain Management
  • Community Commitment
  • Financials
  • Supporting UPMC
  • HealthBeat Blog
  • UPMC Apps
  • UPMC Enterprises
  • UPMC Health Plan
  • UPMC International
  • Nondiscrimination Policy
Life changing is...
Follow UPMC
  • Contact Us
  • Website/Email Terms of Use
  • Medical Advice Disclaimer
  • Privacy Information
  • Active Privacy Alerts
  • Sitemap
© 2025 UPMC I Affiliated with the University of Pittsburgh Schools of the Health Sciences Supplemental content provided by Healthwise, Incorporated. To learn more, visit healthwise.org
Find Care
Providers
Video Visit
Portal Login