Multimodality imaging helps cardiologists manage heart failure patients—with an assist from AI

 

There has been a wide movement toward integrated, multimodality imaging programs that follow evidence-based guidelines to pick the right test for specific clinical questions. This trend has been a hot topic of discussion at cardiac imaging subspecialty conferences where sessions include a lot more information on the roles of other modalities. 

Heart failure is one of the most common diagnoses in cardiology, and echocardiography, cardiac MRI, cardiac CT and nuclear imaging all play different roles depending on the clinical questions being asked.

Purvi Parwani, MD, director of echocardiography for Loma Linda University Medical Center, spoke on heart failure imaging guidelines and the rising use of mixed multimodality imaging during a session at the American Society of Echocardiography (ASE) 2023 conference in June. She spoke with Cardiovascular Business about the ongoing trend.

"In the United States, heart failure readmissions play an important role in the healthcare economics, and we lose a lot of dollars when these patients come back. So it is really important that when it comes to the diagnostic part of why that patient has heart failure that we find the the underlying cause. Now ... we are realizing that instead of having a blanket heart failure diagnosis, we can actually phenotype those patients very well using multimodality imaging," Parwani explained.

While echo is the front-line imaging modality to identify heart failure in a patient, advanced imaging such as cardiac MRI or CT is increasingly being used to identify the specific etiology of the heart failure. Parwani said this allows targeted, personalized treatments for each patient.

"Echo is the first diagnostic test because it is the easiest. We can take this machine anywhere in the hospital. As a physician, I can scan my patients and make a diagnosis very quickly in the emergency room," Parwani said.

MRI, CT and nuclear imaging can be ordered if needed, but they involve more infrastructure that may limit their immediate use or access. 

"At the same time, I think we need to realize there are inherent limitations with every modality. I think in the future we are going to learn how to incorporate multimodality imaging much more effectively in cardiology. And every hospital administration has to learn how to make that process efficient," she said.

She said this process usually will maintain an echo-first approach, but if questions remain unanswered, there needs to be a process to get the patients the right advanced imaging exams. 

With advanced noninvasive imaging, why do we still need angiography?

Parwani said many hospitals and doctors still have invasive angiography ingrained in their minds as the next logical test after an inconclusive echo, especially to assess if there is coronary ischemia. MRI and CT can show the anatomy of the coronaries very clearly to quickly rule-in or rule-out the role of plaque and ischemia. However, CT is used in less than 2% of cardiac imaging, even though it is readily available and can help avoid, or nearly eliminate, the need for diagnostic angiograms. Parwani said this also helps avoid exposing the patients to additional risks of an invasive procedure.

Cardiac MRI usage is also very low, she added. This is despite the fact that it offers both excellent anatomical and physiological imaging in addition to helping identify if there is a rare or mixed cardiomyopathy playing a role. 

Phenotyping with advanced imaging can reduce transplant rejections

For heart failure patients that go on to heart transplants, Parwani said there is somewhat large margin of error, up to 20%, where there are mismatches in pathology between the donor hearts and the patients. 

"The patient goes in for a heart transplant and the explanted heart gets a biopsy and then they realize the pathology they thought the patient had, they did not have. And this can really be reduced if we use the imaging to phenotype the patients using advanced imaging," Parwani explained.

New roles for echo in HCM and amyloid

In the past couple years, new drugs have been introduced to treat hypertrophic cardiomyopathy (HCM) using mavacamten and cardiac amyloidosis using tafamidis. This has caused an explosion of interest in diagnosing these patients for diseases that were previously difficult to treat or untreatable. However, while echo can identify these diseases, phenotyping them with echo alone can sometimes be difficult. Echo also may not be able to show small improvements in serial exams. This has given rise to artificial intelligence (AI) research to help make more confident diagnoses without the need for more expensive advanced imaging tests. 

"I think in the next few years, with all the technology advances in echocardiography, in particular AI, we will be able to use echo for monitoring these patients to see how they are doing," she said.

Parwani said AI will be increasingly used to automatically assess left and right ventricular strain more accurately than it can be done manually. The AI will also correlate the measurements with prognosis. Overall, she said AI in the near future will make echo measurements much more reproducible and help alleviate workflow issues for sonographers.   

Find more cardiac amyloidosis news and video.

Find more HCM news and video.

Dave Fornell is a digital editor with Cardiovascular Business and Radiology Business magazines. He has been covering healthcare for more than 16 years.

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

Around the web

Ron Blankstein, MD, professor of radiology, Harvard Medical School, explains the use of artificial intelligence to detect heart disease in non-cardiac CT exams.

Eleven medical societies have signed on to a consensus statement aimed at standardizing imaging for suspected cardiovascular infections.

Kate Hanneman, MD, explains why many vendors and hospitals want to lower radiology's impact on the environment. "Taking steps to reduce the carbon footprint in healthcare isn’t just an opportunity," she said. "It’s also a responsibility."