Publications

An innovative approach to early diagnosis of heart failure (HF) and COPD, leveraging the power of Premier League football ⚽ to reach communities that may not otherwise respond to community health care screening strategies. By integrating AI-enabled point-of-care diagnostics into a 1-stop community hub, this project is making early detection more accessible than ever. Sankaranarayanan,…

Published in JACC: Cardiovascular Imaging, the authors validated a fully automated AI echocardiographic workflow for grading Mitral Regurgitation (MR) severity. The study demonstrated that the machine learning approach was feasible, fast, highly accurate, and predicts 1-year mortality. Its implementation in clinical practice could improve patient care while improving quality and efficiency in echo labs. Sadeghpour,…

This study highlights the use of a convolutional neural network (CNN) [Us2.ai] to measure key thoracic aortic parameters—LVOT, SoV, STJ, and pAA—in Aortic Stenosis (AS) patients. The CNN demonstrated comparability to cardiologist measurements on transthoracic echocardiography (TTE) and computed tomographic angiography (CTA). With its ability to deliver rapid and highly reproducible measurements, CNN technology holds…

Digital tools, including AI-based tools, holds great potential to reshape the design and execution of cardiovascular clinical trials. In this review published in the European Heart Journal, the authors summarizes the landscape of digital tools at each stage of clinical trial planning and execution, and outlines roadblocks and opportunities for successful implementation in cardiovascular clinical…

Healthcare AI technologies have seen tremendous adoption in the medical imaging field. AI-echo’s performance has been shown to match or exceed human experts in many studies, but do we know if patients are ready to accept AI technology? In 100 patients with suspected heart failure who presented for cardiac imaging at National Heart Centre Singapore,…

Despite successes in the treatment of heart failure resulting in effective therapies across the entire LVEF spectrum, heart failure remains a huge global public health problem. The authors discuss how digital health tools could improve patient outcomes.

Echo is essential in cardiovascular medicine for screening, diagnosis, and monitoring. AI has the potential to reduce variability and analysis time. While 3D echo is becoming more accurate, 2D imaging still dominates clinical care. This study evaluates agreement in measures of LV volume and function between human readers, Us2.ai and the 3D Heart Model.

This Nature Scientific Reports study affirms the role of Us2.ai in empowering novices to obtain accurate ultrasound information to diagnose heart failure. AI offered a more sensitive and objective alternative than NT-proBNP to initiate guideline directed medical therapy in primary care clinics.

New research led by the University of Dundee, demonstrated the feasibility of AI to automatically identify and classify patients with heart failure from archived echocardiographic images with Us2.ai software.

A study conducted at Christ Hospital Health Network and presented at ACC.24 showed good to excellent agreement between AI and experts assessments of LV volumes and ejection fraction in contrast echocardiograms.

Evaluating the performance of automated deep learning algorithms for measurement of echo estimators of invasively measured PCWP.

Us2.ai echocardiographic analysis led to a 70% reduction in measurement and report creation time compared to manual methods, as published in the Journal of Echocardiography.

Published in Nature Hypertension Research, this study used Us2.ai to support healthcare workers in South Africa obtain LVH measurements despite limited training, hand-held sonography devices, difficult imaging conditions, and limited personal resources for analysis.

The CUMIN study, published in European Heart Journal Digital Health, showcases the technical feasibility of AI-POCUS with an EchoNous Kosmos in the hands of novice nurses and opens new possibilities for redefining how we approach cardiac care, particularly in regions with limited resources. The fusion of AI, POCUS and nursing expertise holds the promise of…

The first fully automated AI software with validated global longitudinal strain in patients with and without atrial fibrillation; plus regional strain validated in real-world datasets; plus accurate identification of patients with heart failure, as well as those with regional wall-motion abnormalities, published in the European Heart Journal’s Digital Health.

Remarkable recent advances have revolutionized the field of heart failure. Survival has improved among individuals with heart failure and a reduced ejection fraction, as published in Nature Medicine.

AI to identify cases and classify types of heart failure (HFpEF or HFrEF) from routine EHR surveillance, published in the Journal of Cardiac Failure.

Aortic stenosis published in JASE. First study of its kind demonstrating the capacity of AI Echo to accurately quantify AoS severity with zero human input beyond image acquisition. See the results and the video.

AI echo mortality prediction published in eBioMedicine. Echo can facilitate risk stratification, comparable in performance to established risk scores and correlated with patient’s quality of life measures. Read the publication.

AI-enabled, home-based cardiac care by nurses – abstract presented at the ESC Heart Failure Congress 2023. AI point-of-care ultrasound can improve access, enabling novice nurses to perform cardiac screening in patients’ homes. Download the results.

AI-based MR severity grading presentation at EACVI 2023. Grading MR severity is essential due to high mortality. We’ve built an automated, machine learning based, multiparametric approach. Download the results.

AI echo for cardiac amyloidosis. ATTR-CM is an ultimately fatal cause of heart failure. Manual analysis is slow and highly variable. We showed that automated AI echo can identify predictors of mortality. View the poster.

Strain is a sensitive measure of cardiac function, but clinical application remains limited due to expertise requirements and high variability. We showed AI Echo can automate generation and interpretation of strain. See the results.

A formal white paper on how to democratize echocardiography with augmented intelligence. Download the white paper.

AI echo reports with AI Point-of-Care ultrasound enable novices to perform heart failure screening

AI interpretation of echocardiograms – a formal validation of echo analysis software published in Nature Communications. Download the study.

Echo Strain AI – validation of AI auto strain AI-assisted echocardiography presented at the AHA Scientific Sessions

AI echo reports – automated echo diagnosis support for interpretation of systolic and diastolic function published in The Lancet Digital Health

AI echo disease detection at scale – University of Dundee poster on the detection and diagnosis of patients with heart failure from electronic health records

JASE publication on AI Point-of-care Ultrasound with Continuous-Wave Doppler Capability to evaluate aortic stenosis

Machine learning for diastology and heart failure with preserved ejection fraction – editorial published in JASE

Deep learning in echocardiography – an automated AI echo workflow validation presented at EuroEcho

Cardiovascular disease is the leading cause of death in women. Reducing the global burden by 2030