Echocardiogram assessments were compared between artificial intelligence and sonographers, in which the Cedars-Sinai researchers found that AI was superior in diagnosing and assessing cardiac function. This result was published today in Nature, a peer-reviewed journal.
The investigators leading a first-of-its-kind, randomized, blinded clinical trial of Artificial Intelligence (AI) applications in cardiology at Cedars-Sinai’s Smidt Heart Institute and the Division of Artificial Intelligence in Medicine have presented the findings.
The study’s senior author, cardiologist David Ouyang, MD, served as the clinical trial’s principal investigator. Ouyang commented that the results were remarkable and promising.
David Ouyang says:
“The results have immediate implications for patients undergoing cardiac function imaging as well as broader implications for the field of cardiac imaging,”
“This trial offers rigorous evidence that utilizing AI in this novel way can improve the quality and effectiveness of echocardiogram imaging for many patients.”
Deployment of this technology across the clinical system at Cedars-Sinai and other health systems nationally is anticipated to bring great benefit. Investigators are certain of this result.
Sumeet Chugh, MD, holds the esteemed Pauline and Harold Price Chair in Cardiac Electrophysiology Research and is also the Director of the Division of Artificial Intelligence in Medicine.
Sumeet Chugh says:
“This successful clinical trial sets a superb precedent for how novel clinical AI algorithms can be discovered and tested within health systems, increasing the likelihood of seamless deployment for improved patient care,”
The Smidt Heart Institute and Stanford University researchers recently created one of the earliest AI technologies that use left ventricular ejection fraction to measure cardiac function. This technology, published in Nature, is used to diagnose the heart and its performance.
After assessing 3,495 transthoracic echocardiogram studies and building on earlier findings, a new study compared the accuracy of AI to that of a sonographer, an ultrasound technician. Results suggested that AI was more accurate in evaluation.
Discover The Key Findings Of Among The Findings
Cardiologists agreed with the AI’s initial assessments in most cases and only made corrections to 16.8% of them.
Of the assessments first made by sonographers, 27.2% needed to be corrected by cardiologists.
The physicians could not differentiate which assessments were made by AI and which were made by sonographers, as both groups produced similar results.
AI assistance saved both cardiologists’ and sonographers’ time; it improved efficiency and allowed more time for other activities.
Ouyang went on to say:
“We asked our cardiologists to guess if the preliminary interpretation was performed by AI or by a sonographer, and it turns out that they couldn’t tell the difference,”
“This speaks to the strong performance of the AI algorithm as well as the seamless integration into clinical software. We believe these are all good signs for future AI trial research in the field.”
Clinicians hope to save time and do away with tedious parts of the cardiac imaging process by employing AI models. However, results should still be evaluated by a cardiologist for accuracy. Ouyang explains that this is the goal; the AI model would be used to minimize those laborious tasks but after all,
The studies conducted in the clinical trial and their subsequent research publication provided insights that could eventually be used to gain regulatory approvals.
Dr. Susan Cheng, MD, MPH, plays a large role in the Institute for Research on Healthy Aging within Smidt Heart Institute’s Cardiology Department – her position as Director and co-senior author of a study affirms that fact.
Dr. Susan Cheng says:
“This work raises the bar for artificial intelligence technologies being considered for regulatory approval, as the Food and Drug Administration has previously approved artificial intelligence tools without data from prospective clinical trials,”
“We believe this level of evidence offers clinicians extra assurance as health systems work to adopt artificial intelligence more broadly as part of efforts to increase efficiency and quality overall.”
The potential benefits of AI in cardiovascular health assessment are substantial, and we will likely see more and more AI tools being integrated into clinical practice in the years ahead. By combining AI’s power with medical professionals’ expertise, we can improve our ability to prevent, diagnose, and treat heart disease, ultimately leading to better patient outcomes and a healthier society.