New AI Platform Diagnoses Brain Disease in Seconds

George W. Citroner

August 15, 2018

An artificial intelligence (AI) platform accurately identifies acute neurologic events, such as stroke, from CT scans in as little as 1.2 seconds, new research suggests.

If the findings are confirmed, this technology would radically speed the triage process by immediately alerting physicians to critical findings that may otherwise have remained in a queue from minutes to hours.

"This was our original study that launched our medical AI research consortium in the Mount Sinai Health System," senior investigator Eric Oermann, MD, Department of Neurosurgery at the Icahn School of Medicine at Mount Sinai, New York City, told Medscape Medical News.

"I was motivated by my specific experiences with taking care of patients with acute neurologic illnesses where any possible way of reducing the time it took for me to reach them could have potentially improved their outcomes," said Oermann.

The study was published online August 13 in Nature Medicine.

"Deep Learning"

Researchers used a dataset of 37,236 studies and an additional 96,303 radiology reports that were accumulated as part of the ICAHNC project, a computer vision initiative within the Department of Radiology and part of the Icahn School of Medicine AI Consortium (AISINAI).

The patients included in the test cohort had an average age of 59.7 years, and 51% were female. The studies were evenly distributed between acquisition settings, with 36% coming from the emergency department, 33% coming from an inpatient unit, and 31% coming from an outpatient setting.

The three most common symptoms at intake were headache, altered mental status, and ataxia/dizziness.

Images and the accompanying reports were standardized and processed by using a crowdsourcing platform and a natural language processing pipeline, a computer program that processes and analyzes large amounts of data using natural language.

The AI was then trained to interpret this information by using "deep learning," a machine learning method that uses data representations instead of task-specific algorithms.

"This study was the perfect combination of my personal experiences as a neurosurgeon and my technical training as a mathematician and deep-learning researcher, and it's the first of many projects that we expect to emerge from AISINAI in the near future," Oermann said.

"Time Is Brain"

Both the natural language processing model and radiologists were assessed to find out how quickly they could recognize and provide notification of a critical finding.

A randomized controlled trial of interpretation speed in a simulated clinical environment showed that the AI platform could interpret CT scans 150 times faster than could a human radiologist.

Commenting on the findings for Medscape Medical News, Dion Graybeal, MD, medical director of inpatient neurology, Baylor University Medical Center, Dallas, Texas, said that "speeding the recognition of these patients can speed the time to treatment and reverse disability and even save lives when additional acute interventions are then applied."

Graybeal, who was not associated with the study, noted that in acute ischemic stroke, almost 2 million neurons are lost with every minute of ongoing ischemia.

"In acute neurological injury, it's important to remember that 'time is brain'," he said.

However, this study was an idealized simulation and, according to the study authors, will require validation in a formal multicenter clinical trial. 

"We see this study, as well as the recent study in Nature Digital Medicine by MR Arbabshirani et al, as being the first two studies to rigorously demonstrate the benefit of AI in the clinic," said Oermann. He adds that techniques similar to this one are already being explored by several companies.

"The key for many of these systems is finding ways to integrate them into clinical operations, as well as demonstrating benefit. We feel like our study specifically addresses that last problem," he said.

Graybeal added that he thinks AI will significantly improve care as the technology becomes more advanced "by changing the current workflow and bringing to the top of the reading queue those exams which have acute neurologic findings to speed the time to image interpretation."

Faster, Safer, Better Care

Oermann sees AI platforms as being a key means of augmenting medical care and extending the reach of individual physicians.

"In areas that are time sensitive, such as acute neurological disorders, I think there is a particular benefit, since speed is critical and computational systems often excel at delivering rapid results," he said.

Oermann added that AI tools, applied smartly to the right medical problems, can augment the ability of physicians to take care of patients faster, safer, and better.

Graybeal agreed, noting that "as a tool and to complement what the physician is doing, these processes can assist and even expand the presence and reach that a single physician can make."

However, he cautioned that "they are not now and may never be at a level in the future to actually supplant the medical professional."

The investigators have disclosed no relevant financial relationships.

Nat Med. Published online August 13, 2018. Abstract

For more Medscape Neurology news, join us on Facebook and Twitter


Comments on Medscape are moderated and should be professional in tone and on topic. You must declare any conflicts of interest related to your comments and responses. Please see our Commenting Guide for further information. We reserve the right to remove posts at our sole discretion.
Post as: