Watson Health to Leverage AI-Based CDS Application for Head Trauma, Stroke Identification | Healthcare Informatics Magazine | Health IT | Information Technology Skip to content Skip to navigation

Watson Health to Leverage AI-Based CDS Application for Head Trauma, Stroke Identification

March 20, 2017
by Rajiv Leventhal
| Reprints

IBM Watson Health is collaborating with an artificial intelligence (AI) healthcare startup with the goal to bring a clinical decision support application to imaging experts that will help doctors identify instances of intracranial bleeding as a result of head trauma and stroke.

The Andover, Mass.-based MedyMatch is a company that utilizes cognitive analytics and artificial intelligence with the aim to deliver real-time decision support tools to improve clinical outcomes in acute medical scenarios. Watson Health is now looking to bring MedyMatch’s A.I.-based clinical decision support application to imaging experts working in hospital emergency rooms and other acute care settings to help doctors identify instances of intracranial bleeding as a result of head trauma and stroke.

Initially, IBM Watson Health’s imaging group will distribute the MedyMatch brain bleed detection application globally through its vendor-neutral sales channels. And moving forward, IBM Watson Health and MedyMatch will aim to develop interoperability between MedyMatch’s application and IBM Watson Health imaging’s offerings, according to an announcement on the collaboration.

According to the American Heart Association and American Stroke Association (AHA/ASA), stroke is the fourth leading cause of death and one of the top causes of preventable disability in the U.S Affecting 4 percent of the U.S. adults, it is forecasted that by 2030, there will be approximately 3.4 million stroke victims annually in the U.S., costing the healthcare system $240 billion on an annual basis.

As such, MedyMatch aims to bring cognitive tools into the daily workflow of an emergency department to help physicians assess patients suspected of head trauma or stroke, and rule out the presence of a bleed in the brain. The MedyMatch algorithm uses deep learning, machine vision, patient data, and clinical insights to automatically highlight for a physician regions of interest that could indicate the potential presence of cerebral bleeds, and does so without interrupting how a physician works. 

MedyMatch is currently conducting a clinical trial for its intracranial bleed assessment application and is working towards a PMA Class III approval by the U.S. FDA.

“The implementation of A.I.-based computer aided detection and clinical decision support tools to medicine in general, and to the emergency department, in particular, has the potential to increase the speed, accuracy, and efficiency of patient management – with the potential to ultimately reduce diagnostic errors and improving clinical outcomes,” Michael Lev, M.D., director of emergency radiology at Massachusetts General Hospital and professor of radiology at Harvard Medical School, said in a statement.  “MedyMatch is ideally positioned to leverage this technology, and their willingness to collaborate with industry partners reflects their awareness of, and sensitivity to, the complexities of patient assessment in the acute care setting.  The Company’s first algorithms - CT detection of intracranial bleeds - represents the confluence of physician know-how and artificial intelligence clinical support.”

Gene Saragnese, chairman and CEO of MedyMatch, noted, ““Engaging closely with IBM allows for a near-zero footprint implementation at a customer location delivering ‘A.I. to the bedside’ where I believe the future of healthcare lies.”

Get the latest information on Health IT and attend other valuable sessions at this two-day Summit providing healthcare leaders with educational content, insightful debate and dialogue on the future of healthcare and technology.

Learn More



Arizona ACO Pilots Blockchain Platform to Improve Clinical Outcomes, Reduce Costs

Arizona Care Network, a Phoenix-based accountable care organization (ACO), plans to pilot a blockchain technology platform developed by Solve.Care with the aim of improving clinical outcomes, relieving healthcare’s administrative burdens, and reducing waste within the system.

Protenus February Breach Report: Number of Incidents Remain Steady

The number of healthcare data breach incidents continues to remain steady, and in February’s Breach Barometer report from Protenus, it was revealed that last month, a ransomware attack was responsible for the largest single incident.

Prior Authorization Burdens Hindering Patient Care, AMA Survey Finds

Approximately 64 percent of physicians in a recent American Medical Association (AMA) survey said they wait at least one business day before getting a response from a health plan regarding a prior authorization (PA) decision.

Intermountain Healthcare to Build Global DNA Registry with AncestryDNA, 23andMe Data

Intermountain Healthcare is building a new global DNA registry based on medical histories from people around the world, using existing genetic test results and electronic health histories.

NH-ISAC Accelerates Cyber Threat Sharing for Healthcare Industry

The National Health Information Sharing and Analysis Center (NH-ISAC) is partnering with Anomali, a provider of threat management solutions, to enable seamless, secure threat sharing within the healthcare community.

Enterprise Telemedicine Strategies Gaining Steam, Survey Finds

Healthcare providers are increasingly leveraging a centrally-managed (enterprise) approach to telemedicine, according to the results of the REACH Health 2018 U.S. Telemedicine Industry Benchmark survey.