AI processes images from a CT scan of the head to find parts of the brain that...
AI processes images from a CT scan of the head to find parts of the brain that are not currently getting enough blood flow (green areas) as opposed to those parts of the brain that are already dead (pink areas).
Source: LifeBridge Health

How AI is already helping physicians save lives

While many of the speculative “AI” use cases within healthcare are either far-fetched or still many years away from touching patients, the stroke service line at LifeBridge Health has been on the forefront of using AI at the beside since late 2016.

Consider the following scenario, which recently occurred in our health system. A patient presented with left sided weakness to one of our community hospitals in the middle of the night on a weekend, exactly the kind of time when access to specialty care has historically been a challenge outside of major tertiary and quarternary stroke centers. He was seen briefly by the ER team before being immediately evaluated through a virtual “telestroke” consult by neurologist Dr. Richard Jung. The patient was judged to be highly suspicious for stroke and a RAPID scan was ordered. LifeBridge Health is still the only center in Maryland doing this, but the radiology departments at other health systems such as Johns Hopkins, MedStar and Maryland are now following in our footsteps and looking to implement similar programs.

The images above are from RAPID, a special kind of software that “processes” images from a CT scan of the head and uses a deep learning algorithm to find parts of the brain that are not currently getting enough blood flow (green areas) as opposed to those parts of the brain that are already dead (pink areas). In the past, this kind of analysis often took technologists and radiologists over an hour to perform. With RAPID AI, the physicians now get answers for patients and their doctors within minutes. In this case, the scan told us that large amounts of this patient’s brain would die from his stroke if nothing was done to restore blood flow.

Photo
Red region shows the area of absent blood flow.
Source: LifeBridge Health

On this particular night, LifeBridge Health was also becoming one of the first health systems in the world to use IschemiaView’s automated CT angiography AI algorithm (RAPID CTA AI). This technology uses AI to create pictures of the blood vessels within the brain to determine whether there are any large clots or blockages obstructing the flow of blood and causing the stroke. In our patient’s case, the RAPID CTA showed that blood flow to one of the largest vessels in his brain was cut off by a large blood clot (the red region in picture below shows the area of absent blood flow). 

Thanks to these two AI algorithms, our teams knew the following three things within minutes of our patient arriving in the ER:

  • The patient’s symptoms of left sided weakness were due to a large right-sided stroke.
  • This was caused by a large blood clot in the right middle cerebral artery (MCA).
  • Most of the patient’s brain was still salvageable (not yet dead), meaning that he could still benefit from an emergent “thrombectomy” procedure to remove the clot.

The patient was emergently transferred to Sinai Hospital of Baltimore. At Sinai, the patient quickly underwent thrombectomy at the hands of internationally-renowned neuroendovascular surgeon Dr. William Ashley. After the procedure, the patient’s symptoms immediately began to resolve and he has since continued to enjoy an excellent recovery. He suffered a large stroke, but because the intervention was performed so quickly he is now currently expected to make a nearly a full recovery.

In the past, prior to RAPID AI, such patients could not have been treated as quickly or as aggressively. Because “time equals brain” in the golden hour of stroke, our ability to act quickly and with greater certainty means that there will be more lives saved and a higher quality of life for those who survive. Since LifeBridge Health implemented the RAPID stroke imaging pathway at LifeBridge Health, they have quadrupled the number of live-saving thrombectomy procedures that we are able to offer patients in the Baltimore area. In a world where so much of the promise of AI seems like science fiction, real stroke patients, their families, are benefiting tremendously from AI today.

Subscribe to our newsletter

Related articles

Dentistry: AI helps localize the mandibular canals

Dentistry: AI helps localize the mandibular canals

Researchers have developed a new model that accurately and automatically shows the exact location of mandibular canals.

AI rivals radiologists at detecting brain hemorrhages

AI rivals radiologists at detecting brain hemorrhages

An algorithm did better than experts radiologists at finding tiny brain hemorrhages in head scans — an advance that one day may help doctors treat patients with strokes.

Deep learning system automatically detects diseases

Deep learning system automatically detects diseases

Patients could soon get faster and more accurate diagnoses with new software that can automatically detect signs of diabetes, heart disease and cancer from medical images.

AI system learns to diagnose intracranial hemorrhage

AI system learns to diagnose intracranial hemorrhage

Researchers have developed a system using artificial intelligence to quickly diagnose and classify brain hemorrhages and to provide the basis of its decisions from relatively small image datasets.

A high-precision radiology system for the coronavirus

A high-precision radiology system for the coronavirus

Researchers are developing a new high-precision radiology system for coronavirus pulmonary involvement.

AI outperform doctors: Experts express concerns

AI outperform doctors: Experts express concerns

Many studies claiming that AI is as good as (or better than) human experts at interpreting medical images are of poor quality and are arguably exaggerated, warn researchers in The BMJ.

AI helps predict heart attacks and stroke

AI helps predict heart attacks and stroke

In a new study, artificial intelligence has been used for the first time to instantly and accurately measure blood flow.

AI predicts effectiveness of immunotherapy

AI predicts effectiveness of immunotherapy

Scientists can determine which lung-cancer patients will benefit from expensive immunotherapy.

Deep learning assists in detecting malignant lung cancers

Deep learning assists in detecting malignant lung cancers

Radiologists assisted by deep learning based software were better able to detect malignant lung cancers on chest X-rays.

Popular articles