AI, new cardiac imaging technology can assess for CAD

By Erik L. Ridley, staff writer

August 20, 2018 -- The combination of artificial intelligence (AI) and a new noninvasive cardiac imaging technique can perform comparably to current imaging tests used to detect coronary artery disease (CAD) -- without requiring cardiac stress, contrast agents, or radiation exposure, according to research published recently in PLOS One.

Researchers led by Dr. Thomas Stuckey of Cone Health in Greensboro, NC, and senior author William Sanders Jr. of technology developer Analytics 4 Life (A4L) developed a machine-learning algorithm to analyze cardiac phase space tomography (CPST) -- a novel imaging method that uses a handheld instrument to capture the heart's resting phase signals. In testing, the algorithm was more than 90% sensitive for diagnosing significant CAD.

Currently, screening tests for CAD are expensive, typically require physical or pharmacologic stress, and commonly involve radiation exposure. In patients with chest pain, functional testing and CT angiography (CTA) serve as gatekeeping tests for risk stratification and to identify individuals who would benefit from angiography, according to the researchers.

"Little has changed with regard to the accuracy of these technologies in the last decade, and better tools for screening CAD are needed," they wrote.

In their study, the researchers sought to assess the diagnostic performance of CPST for assessing CAD in patients referred for coronary angiography due to chest pain. With CPST, 10 million data points are acquired from the patient's resting phase heart signals, which are transferred along with ancillary patient-specific information to the cloud for evaluation by a machine learning-based analytic engine. These results are subsequently displayed as a phase space tomography model on a web portal for review by physicians, according to the researchers. A4L is developing CPST and funded the study (PLOS One, August 8, 2018).

The researchers developed and tested the machine-learning algorithm using phase signals from 606 subjects who presented with chest pain at 12 U.S. centers. Phase signals were acquired at rest prior to angiography. Of the 606 participants, 159 (31%) had obstructive coronary lesions.

To train the algorithm to analyze the unique features associated with flow-limiting CAD, mathematical and tomographic features were extracted from the phase data and paired with the angiography results -- the gold standard for the study. The algorithm was trained using data from 512 subjects and then prospectively tested on the remaining 94 participants.

Performance of machine learning + CPST to predict CAD
Sensitivity 92%
Specificity 62%
Positive predictive value 46%
Negative predictive value 96%

The researchers noted that the algorithm was optimized to maximize sensitivity. The algorithm's specificity level is similar to that of other functional tests, according to the researchers.

"[CPST analysis] exhibits comparable diagnostic performance to existing functional and anatomical modalities without the requirement of cardiac stress (exercise or pharmacological) and without exposure of the patient to radioactivity," the authors wrote. "This technology may provide a new and efficient technique for assessing the presence of obstructive coronary lesions in patients presenting with chest pain suspected to be of cardiac etiology."

Cardiac MRI offers prognosis for hard-to-find infarctions
Cardiac MRI can play a critical role in helping to determine which patients suspected of having stable coronary artery disease could have an unrecognized...
CCTA reduces unnecessary invasive coronary procedures
Using coronary CT angiography (CCTA) instead of SPECT myocardial perfusion imaging to diagnose coronary artery disease can significantly reduce the number...
SNMMI: AI enables stress-first SPECT MPI protocol
PHILADELPHIA - Artificial intelligence (AI) analysis of stress SPECT myocardial perfusion imaging (MPI) can be highly sensitive for all types of coronary...
ACC: PET/CT calcium scans could foretell cardiac events
By using PET/CT to measure the level of calcium in the coronary arteries during stress tests, clinicians can better predict which patients are at high...
ACC: PET tops SPECT for severe coronary artery disease
PET is significantly more proficient than SPECT in detecting severe obstructive coronary artery disease, enabling more appropriate use of revascularization...

Copyright © 2018

Last Updated np 8/17/2018 3:06:03 PM

13 comments so far ...
8/20/2018 3:21:25 AM
Phil Shaffer
This is just totally unbelievable. 

This article stands as a testimonial to the fact that you can never, ever, believe the press reports and headlines about research.
This article is disgraceful, and should never have been published. I have judged junior high science fairs in which the participants had a more sophisticated understanding of the scientific method than these authors do.
Let's discard the AI claims, and just look at the methods. Scientific papers are supposed to allow enough information for an interested researcher to repeat and verify the work. However, nowhere in the paper or references do these authors tell us exactly what "phase tomography" IS. The methods say:
"The cPSTA System is a medical device system that uses tomography to analyze phase signals and assess the presence of significant coronary artery disease in the major coronary arteries "  As if, by using "tomography" it is instantly clear how it is done and what is actually being measured. 
So what is it? Electrical, echocardiography, acoustic, something else entirely? What is it. No word on this. The one reference (#6) to information about the device leads to a page that says the information is not available to the public.
They do mention many times that there is no exposure to "radioactivity". And, as we all know that is very very bad, so it has that going for it.

They ask the readers to believe that they have a black box that produces some signal that, when processed,  predicts the outcome of coronary angiography, without any information whatever about how it is done, no information about the physiologic basis of their black box. 

At first I thought this was a hoax, like the fake papers which have been submitted to some of the pay-to-publish fake journals and subsequently published, just to prove they would publish any collection of words sent to them. But, at least the lead author is a real person in some obscure medical practice. 

So my second thought is that this is the leading edge of medical idiocracy that will eventually engulf us all.  That is my current working hypothesis.
I guess there is a reason it is in PLOS one. 

8/20/2018 6:51:21 AM
At least this has a video:

8/20/2018 7:19:57 AM
What the heck is cPSTA?

I don't know what's dumber. This "phase space tomography" business or rejecting the whole notion of AI because of this one nonsense mumbo jumbo.

8/20/2018 7:23:23 AM
What the heck is cPSTA?

I don't know what's dumber. This "phase space tomography" business or rejecting the entire notion of AI because of this one nonsense mumbo jumbo.

I can't believe AM posted this. This looks like a clickbate for someone wanting seed funding.

8/20/2018 7:36:10 AM
What the heck is cPSTA?

I don't know what's dumber. This "phase space tomography" business or Phil rejecting the entire notion of AI because of this one nonsense mumbo jumbo.

I can't believe AM posted this. This looks like a clickbate for someone wanting seed funding. They use the term "AI" to get more eyes.