New research shows superiority of Ultromics’ AI in predicting cardiac-related death
As the use of artificial intelligence (AI) in healthcare continues to grow, researchers are evaluating whether AI technology can now outperform human experts. A new study from the World Alliance Societies of Echocardiography (WASE), a major international research initiative led by the American Society of Echocardiography (ASE), says artificial intelligence (AI) is superior to human experts when it comes to predicting cardiac-related death.
According to the study, researchers “aimed to test the performance of an artificial intelligence machine learning-derived algorithm for the prediction of outcomes in patients admitted for acute COVID-19 and its incremental value to that of expert echocardiographer analysis.”1
Researchers looked at 870 patients admitted for acute COVID-19 from January to September 2020. Patients were admitted to 13 hospitals in 9 countries. According the study, the patients all underwent transthoracic echocardiography (TTE), the leading procedure for assessing COVID-19 patients as it can evaluate the full spectrum of involvement, and it can be performed safely at the bedside or in the ICU.
Echocardiographic left ventricular ejection fraction (LVEF) and left ventricular longitudinal strain (LVLS) were obtained manually by multiple expert readers and by the automated cloud-based AI platform from Ultromics. Researchers then compared the ability of the manual and AI analyses to predict all-cause mortality. The study concluded that “AI-based analysis of LVEF and LVLS had similar feasibility as manual analysis, minimized variability, and consequently increased the statistical power to predict mortality.”
Dr. Federico M. Asch, lead study author and Director of the Cardiovascular and Echo Core Labs at MedStar Health Research Institute, said: “The AI derived results outperformed traditional manual analysis in the generation of Left Ventricular Ejection Fraction and Global Longitudinal Strain, as the AI proved to be a significant predictor of outcomes, which traditional reads by expert echocardiographers could not achieve.”
The new study builds on previous work by WASE which showed that AI–based analysis could accurately detect outcomes from echocardiographic images, including combining myocardial strain biomarkers to improve predictive accuracy. Strain is recommended in recent guidelines as clinical best practice.
Ultromics’ AI analysis had lower variability than human analysis for both LVEF (P = .003) and LVLS (P = .005).
AI-derived LV analyses were predictors of mortality in univariable and multivariable regression analysis where manual LV analyses were not LVEF (odds ratio, 0.974 [95% CI, 0.956-0.991; P = .003] LVLS (odds ratio, 1.060 [95% CI, 1.019-1.105; P = .004].
Direct comparison of the predictive value of AI versus manual measurements of LVEF and LVLS showed that AI was significantly better (P = .005 and P = .003, respectively).
AI-derived LVEF and LVLS had more significant and stronger correlations to other objective biomarkers of acute disease than manual reads.
In addition, inter-operator agreement for LVEF and GLS was 23% and 44% (respectively) lower for manual measurements than that achieved by the AI.
According to Ultromics, this latest study demonstrates the prognostic value of AI for routine primary care and improved accuracy for prediction of cardiovascular disease. Ultromics says it will continue to explore how AI can contribute to the development of echocardiography and preventative care.
“Developing precision strategies for cardiovascular disease is more critical than ever,” said Ross Upton, PhD and CEO and Founder of Ultromics in the company’s announcement of the study. “We built our AI platform to improve the accuracy of heart failure detection and prevent worsening cardiac outcomes.”
“The technology was built using deep learning, from 10 years' worth of echocardiographic images tied to outcomes, to provide precision analysis independent of expert clinicians”
Read the full publication here.
Dr. Federico M. Asch, lead study author and Director of the Cardiovascular and Echo Core Labs at MedStar Health Research Institute, will be on a webinar November 3, 2022 to discuss these ground-breaking results. Sign-up here to register.
To learn more about Ultromics, visit: ultromics.com
Ultromics is the leader in artificial intelligence for echocardiography enabling earlier detection and risk stratification of heart failure for better outcomes, lower costs, and improved patient care. All providers, regardless of their care setting, can now make precise, accurate, and timely diagnoses of heart failure with Ultromics’ AI technology. The cloud-based platform, EchoGo, offers a simple, secure and seamless way to augment your existing technology and workflow with fully automated, advanced echo analysis including critical advanced measures recommended by guidelines.. The technology is FDA-cleared and trusted by world-renowned organizations such as Mayo Clinic and the NHS England. Learn more: https://www.ultromics.com
1. Asch FM, Descamps T, Sarwar R, et al. Human versus Artificial Intelligence-Based Echocardiographic Analysis as a Predictor of Outcomes: An Analysis from the World Alliance Societies of Echocardiography COVID Study [published online ahead of print, 2022 Jul 19]. J Am Soc Echocardiogr. 2022;S0894-7317(22)00351-0. doi:10.1016/j.echo.2022.07.004