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.
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.
Source: LifeBridge Health