What is the ROI for adopting AI in cardiac imaging?
The biggest overarching trend in healthcare today is the implementation of artificial intelligence (AI) algorithms into clinical and back-end IT workflows. This is especially true for radiology and cardiac imaging, which makes up about 75% of all U.S. Food and Drug Administration (FDA)-cleared clinical algorithms. While interest in AI is high, purchasing and implementing the technology is still slow because many centers question its high costs and lack of reimbursement.
To find out more about the business ROI for AI in cardiac imaging, Cardiovascular Business spoke with Marcelo DiCarli, MD, chief of the division of nuclear medicine and molecular imaging and executive director for the cardiovascular imaging program at Brigham and Women's Hospital, and Rob Beanlands, MD, director of the National Cardiac PET Centre at the University of Ottawa Heart Institute in Canada. DiCarli is also the chair of the American College of Cardiology (ACC) Cardiovascular Imaging Leadership Council.
"AI is touching pretty much all aspects of cardiac imaging," explained DiCarli. "And not just in research and publications, but in a very direct way with application to patient care."
One example he gave was Brigham and Women's Hospital recently rolling out an AI-driven approach to cardiac MRI. The AI model picks the views and enables the acquisition with just one click. It also provides all measurements and quantification automatically.
"What that has done for us is impact many important areas. Number one, it shortened the examinations. It is good for patients because they don't need to spend as much time in the magnet, but it is also better for throughput because we can accommodate more patients on any given day. Number two, it has increased the quality of what we do, because it is less dependent on the expertise of the technologists who are pressing the buttons and making decisions. And then on the post-processing it has simplified our lives. What used to be a very time-consuming process is now just a click away. For me, that is very impactful," DiCarli explained.
He also said AI is impacting cardiac CT. This includes new AI vendors offering FDA-cleared algorithms to assess soft plaque in the coronaries and automation of contouring and measurements. HeartFlow 's FFR-CT technology has changed how patients are being assessed quickly for coronary disease.
AI is also seeing adoption to improve nuclear imaging without the need to make large capital investments in new scanners, he said.
"One of the Achilles heels of SPECT imaging has been attenuation artifacts, and now we have a deep-learning based approached to attenuation correction that does not require extra equipment," DiCarli said.
In PET, AI can independently assess coronary calcium using the non-gated, attenuation correction CT scan on the SPECT-CT systems.
"You have potential AI applications for test selection," Beanlands explained. "You can use it for the actual image acquisition processing. Then you have the image processing, including removing things like attenuation artifact to potentially increase the accuracy of the disease detection. And then you have the potential to better prognosticate using the information you have, using the AI to complement human assisted intelligence."
The business ROI argument for implementing AI
Currently there is little to no reimbursement for using AI, which has made many hospitals think twice about investing. But DiCarli said the realities of lower reimbursements, shortages of physicians and rising numbers of patients makes AI look very attractive to him and other imagers.
"When it comes down to business, it is about throughput on the scanner. As reimbursement comes down, being able to replace the shrinkage of reimbursements with being able to accommodate more patients becomes very relevant. And for physician time, it also becomes very relevant. Doing our work more more efficiently, accurately and potentially even better becomes very, very meaningful," DiCarli explained.
"Many people have feared AI would replace imagers, but I think it will enable us to actually do more and be better at what we do. I can only think of positive things coming out of AI over the next five years," he said.
AI can educate the patient for better shared decision making
Beanlands and DiCarli are working on a project to use open AI to take the imaging report and other patient data to create an automated report in plain layman's terms for the patient so they can better understand their condition. They are not there quite yet, but Beanlands firmly believes AI-enabled patient report summaries will be used regularly in just a few years.
"AI is a tool that can complement the physicians and help make the best decisions for patients," Beanlands said.
DiCarli said AI can help explain to patients complex things like what low-flow perfusion means for their disease condition, their symptoms and to lay out what their treatment options are in simple, non-medical terms.
"Part of the success of treatment is to engage the patient in shared decision making. But it is hard for patients to engage in shared decision making if they do not understand the disease, but also what the results of the test mean. I think that is the future. The technology will help us translate this to the patients more effectively. And sometimes the clinicians just do not have the time," DiCarli said.
"We as doctors have not done a very good job. We talk medical speak and we often lose the patient in the conversation. So we need ways to bring a clear message to the patients so they understand, and then they can make informed decisions," Beanlands added.
Watrch the related video and article with DiCarli and Beanlands — What's new in cardiac imaging? 2 experts discuss the latest trends.
Dave Fornell has covered healthcare for more than 17 years, with a focus in cardiology and radiology. Fornell is a 5-time winner of a Jesse H. Neal Award, the most prestigious editorial honors in the field of specialized journalism. The wins included best technical content, best use of social media and best COVID-19 coverage. Fornell was also a three-time Neal finalist for best range of work by a single author. He produces more than 100 editorial videos each year, most of them interviews with key opinion leaders in medicine. He also writes technical articles, covers key trends, conducts video hospital site visits, and is very involved with social media. E-mail: dfornell@innovatehealthcare.com