David Ouyang, MD

David.Ouyang@kp.org

Ouyang, David

David Ouyang, MD, is a research scientist at the Kaiser Permanente Northern California Division of Research and a non-invasive cardiologist and echocardiographer at Kaiser Permanente Santa Clara Medical Center. Dr. Ouyang’s group works on applications of deep learning, computer vision, and the statistical analysis of large datasets within cardiovascular medicine. His work has been published in Nature, Nature Medicine, NEJM AI, Circulation, JACC, JAMA Cardiology, EHJ, and other venues. He is also a Deputy Editor for New England Journal of Medicine (NEJM) AI.

A physician-scientist and statistician with a focus on cardiology and imaging, Dr. Ouyang majored in statistics at Rice University, obtained his MD at the University of California, San Francisco, and received post-graduate medical education in internal medicine, cardiology, and a postdoctoral fellowship in computer science and biomedical data science at Stanford University. He is the recipient of an NHLBI K99/R00 and two R01 grants focused on applications of computer vision in echocardiography. He is the Principal Investigator (PI) or Co-Investigator on multiple investigator-initiated pragmatic clinical trials of AI in cardiovascular medicine.

Current Positions

  • Research Scientist, Division of Research, Kaiser Permanente Northern California
  • Staff Cardiologist, Department of Cardiology, The Permanente Medical Group, Santa Clara

Section Affiliations

Primary Research Interests

  • Deep learning
  • Computer vision
  • Statistical analyses of large datasets within cardiovascular medicine

 

Studies

AI-Enabled Echocardiographic Biomarkers and Real-World Data for Predicting Cancer Therapy-Related Cardiac Dysfunction

This study will apply previously validated AI-based echocardiographic biomarkers in cancer patients treated with cardiotoxic therapies; compare the timing and incidence of cancer therapy-related cardiac dysfunction (CTRCD) in patients treated with cardiotoxic agents using AI-enhanced definitions to that using electronic medical record data alone; and develop and validate multimodal predictive models for CTRCD integrating EHR and AI-echo data.

Investigator: Feliciano, Elizabeth; OUYANG, David

Funder: Food and Drug Administration (FDA)/DHHS

Opportunistic Screening of Liver and Kidney Disease with Computer Vision in a High Cardiovascular Risk Population

This project will use artificial intelligence to analyze standard heart ultrasounds for signs of kidney and liver disease that cardiologists typically miss. The team will implement and test their AI system across four healthcare systems to determine its accuracy, develop optimal notification strategies, and measure impacts on patient care. By enabling early detection of conditions that have new available treatments, this approach aims to improve timely intervention and patient outcomes without requiring additional testing.

Investigator: Ouyang, David

Funder: American Heart Association

Artificial Intelligence Imaging Biomarkers of Longitudinal Cardiovascular Stress

This study will train and validate artificial intelligence (AI) models on predicting biological age from cardiac imaging and identify its component contributors to excess cardiovascular risk in the healthcare setting and in the community setting.

Investigator: Ouyang, David

Funder: National Heart, Lung, and Blood Institute

Deep Learning Assessment of the Right Ventricle: Function, Etiology, and Prognosis

This research will involve using novel artificial intelligence techniques on noninvasive imaging (echocardiography) to investigate contributors to right ventricular (RV) dysfunction and factors related to the development of RV specific disease phenotypes and outcomes.

Investigator: Ouyang, David

Funder: National Heart, Lung, and Blood Institute

Machine Learning Guided Precision Genetic Testing for Identification of Monogenic Cardiovascular Disorders

This project will validate and determine generalizability of imaging-based deep learning (DL) algorithms for HCM and ATTR-CM using echocardiograms across four health systems caring for diverse patients.

Investigator: Ouyang, David

Funder: National Heart, Lung, and Blood Institute

Artificial Intelligence Imaging Biomarkers of Longitudinal Cardiovascular Stress

ABSTRACT Across every type of prediction model, applied to virtually any population, the single most substantial contributor to incident cardiovascular disease (CVD) is older age. However, our understanding of why cardiovascular risk dramatically rises with advancing age remains limited. Evidence to date suggests that CVD culminates from age- related changes in cardiac structure and function that begin very early in adulthood and continue to develop on a background of lifelong exposure to risk factors – contributing to an ‘age gap’ between biological age and chronological age that grows over time. It logically follows that a person’s increasing burden of cardiovascular risk should manifest as progressive cardiac abnormalities that can be tracked, analyzed, and identified over the lifespan. Until recently, methods for assessing the cardiovascular ‘age gap’ have been limited. Recent advances in artificial intelligence (AI), when applied to biomedical images, indicate that deep learning algorithms can both offer precise measurements beyond human fidelity and also identify subtle traits in imaging that are unrecognized by the human eye. In fact, our prior work applying AI to echocardiography as well as others applying AI to other forms of medical imaging, have shown deep learning can not only reproduce standard measures of cardiac structural and function but is also identify CVD risk features including chronologic age, biological sex, diabetes, hypertension, and smoking. In effect, AI applied to echocardiography now offers the potential to capture an aggregate measure of cardiac aging and, in turn, identify intervenable target for mitigating age-related CVD risk. Thus, we hypothesize that AI methods applied to echocardiography can be used to not only predict biological cardiovascular age but also (i) identify trajectories of accelerated versus delayed cardiovascular aging, (ii) discern key contributors to accelerated cardiovascular aging phenotypes, and (iii) elucidate the excess age- related risk for specific CVD outcomes that may be independent from any co-existing burden of risk factors or subclinical cardiac disease. To test these hypotheses, we will leverage echocardiography images that are acquired as a part of routine clinical care in addition to serial imaging frequently obtained in large cohort studies of aging adults. Because healthcare cohorts are enriched for patients with accelerated aging trajectories, while epidemiologic cohorts are enriched for individuals with delayed aging trajectories, we plan to analyze imaging and outcomes data collected from both types of cohorts. Accordingly, our aims are to train and validate AI models on predicting biological age from cardiac imaging and identify its component contributors to excess cardiovascular risk in both the healthcare setting and in the community setting.

Investigator: Ouyang, David

Funder: National Heart Lung and Blood Institute

Deep Learning Assessment of the Right Ventricle: Function, Etiology, and Prognosis

ABSTRACT Heart failure imposes a tremendous burden of morbidity and mortality, costing the United States in excess of $31 billion annually. An increasingly recognized major determinant of outcomes in heart failure is right ventricular (RV) dysfunction. However, the nature and character of RV contribution to cardiovascular outcomes remains poorly understood, largely due to the imprecision of imaging and interpretation of RV morphology and function. Echocardiography, with its high temporal resolution and low cost of acquisition, serves as frontline cardiovascular imaging and a mainstay in approaches to assessing RV morphology and function. However, echocardiographic imaging of the RV is limited by factors that include technical variation in image acquisition and heterogeneity in image assessment as well as overall interpretation. We postulate that deep learning based phenotyping can offer the ability to not only more precisely characterize RV function but also classify RV imaging phenotypes according to etiologic disease states and, even further, refine prognostic evaluations of future cardiovascular risk. Therefore, in Aim 1, we will use video-based deep learning segmentation models to assess RV function, evaluate its cross-sectional relation with a range of expert-measured parameters, and examine its variation in the context of patient characteristics derived from large hospital-based cohorts. In Aim 2, we will use video-based deep learning models to produce imaging-based classification of RV disease and assess the ability of unsupervised approaches to classify RV dysfunction into various categories of disease etiology. In Aim 3, we will use models developed in part from training in Aims 1 and 2 to predict major cardiovascular outcomes including heart failure in addition to coronary artery disease, stroke, and cardiovascular death in both hospital- based and community-based cohorts. The overarching goal of this proposal is to improve the precision and standardization of RV phenotyping and determine the extent to which deep learning models can augment human assessment of the RV. This research will be accomplished in the setting of a comprehensive career development program designed to provide the candidate with the skills needed to become an independent physician-scientist in cardiovascular medicine and translational imaging science. An advisory committee of established scientists/mentors in the fields of cardiac imaging, deep learning, data science, and translational science will guide the candidate in his transition to scientific independence over the course of the award period.

Investigator: Ouyang, David

Funder: National Heart Lung and Blood Institute

Publications

Clinical risk prediction models for worsening heart failure events and all-cause mortality in adults with mild-to-moderate chronic kidney disease

Authors: Patel S;Go, Alan S;Liu, Jane Y;Parikh, Rishi V;Tan, Thida C;Bhatt, Ankeet S;Lee, Keane K;Ouyang, David;Ambrosy, Andrew P;Ambrosy AP; et al.

ESC Heart Fail. 2026 Feb 03;13(1).

PubMed abstract

Foundation models for electrocardiogram interpretation: clinical implications

Authors: Nolin-Lapalme A;Ouyang, David;Avram R; et al.

Eur Heart J. 2026 Jan 22.

PubMed abstract

Deep Learning-Based Continuous QT Monitoring to Identify High-Risk Prolongation Events After Class III Antiarrhythmic Initiation

Authors: Ansari RA;Ouyang, David;Rogers AJ; et al.

Circulation. 2026 Jan 06;153(1):35-46. Epub 2025-11-08.

PubMed abstract

Factors associated with physician modifications to automated ECG interpretations

Authors: Chiu IM;Sahashi Y;Torbati SS;Chugh SS;Ouyang D

Eur Heart J Digit Health. 2026 Jan;7(1):ztaf119. Epub 2025-11-08.

PubMed abstract

Current State of Artificial Intelligence in Assessing Cardiac Function

Authors: Yuan V;Lee K;Ambrosy AP;Ouyang D;Ieki H

Curr Cardiol Rep. 2025 Nov 27;27(1):158. Epub 2025-11-27.

PubMed abstract

Artificial intelligence prediction of age from echocardiography as a marker for cardiovascular disease

Authors: Rawlani M;Bhatt, Ankeet;Ambrosy, Andrew P;Ouyang, David;Ouyang D; et al.

NPJ Digit Med. 2025 Nov 18;8(1):688. Epub 2025-11-18.

PubMed abstract

Comprehensive echocardiogram evaluation with view primed vision language AI

Authors: Vukadinovic M;Chiu IM;Tang X;Yuan N;Chen TY;Cheng P;Li D;Cheng S;He B;Ouyang D

Nature. 2025 Nov 11.

PubMed abstract

Clinical Characteristics, Early GDMT Initiation, and Likelihood of Heart Failure With Improved Ejection Fraction

Authors: Min KH;Go, Alan S;Parikh, Rishi V;Ambrosy, Andrew P;Tan, Thida C;Lee, Keane;Ouyang, David;Bhatt, Ankeet S;Bhatt AS; et al.

J Card Fail. 2025 Nov 08.

PubMed abstract

Worsening Heart Failure Events in Adults with Mild-to-Moderate Chronic Kidney Disease

Authors: Ye L;Go, Alan S;Liu, Jane Y;Parikh, Rishi V;Tan, Thida C;Bhatt, Ankeet S;Lee, Keane K;Ouyang, David;Ambrosy, Andrew P;Ambrosy AP; et al.

Am Heart J. 2025 Oct 17:107290.

PubMed abstract

AI, Health, and Health Care Today and Tomorrow: The JAMA Summit Report on Artificial Intelligence

Authors: Angus DC;Lieu, Tracy;Liu, Vincent;Ouyang, David;Bibbins-Domingo K; et al.

JAMA. 2025 Oct 13.

PubMed abstract

Artificial Intelligence Automation of Echocardiographic Measurements

Authors: Sahashi Y;Ieki H;Yuan V;Christensen M;Vukadinovic M;Binder-Rodriguez C;Rhee J;Zou JY;He B;Cheng P;Ouyang D

J Am Coll Cardiol. 2025 Sep 30;86(13):964-978. Epub 2025-09-07.

PubMed abstract

Pathway to Risk Stratification in Tricuspid Regurgitation-Reply

Authors: Vrudhula A;Ouyang D

JAMA Cardiol. 2025 Sep 24.

PubMed abstract

Using Deep Learning to Predict Cardiovascular Magnetic Resonance Findings From Echocardiographic Videos

Authors: Sahashi Y;Vukadinovic M;Duffy G;Li D;Cheng S;Berman DS;Ouyang D;Kwan AC

J Am Soc Echocardiogr. 2025 Sep;38(9):807-815. Epub 2025-05-30.

PubMed abstract

PRIME 2.0: Proposed Requirements for Cardiovascular Imaging-Related Multimodal-AI Evaluation: An Updated Checklist

Authors: Kagiyama N;Ouyang, David;Sengupta PP; et al.

JACC Cardiovasc Imaging. 2025 Aug 27.

PubMed abstract

Incident Heart Failure in Adults With Mild to Moderate Chronic Kidney Disease

Authors: Girouard MP;Go, Alan S;Liu, Jane Y;Parikh, Rishi V;Tan, Thida C;Bhatt, Ankeet S;Zheng, Sijie;Ouyang, David;Ambrosy, Andrew P;Ambrosy AP; et al.

JACC Heart Fail. 2025 Aug 18:102616.

PubMed abstract

Vision-language foundation model for echocardiogram interpretation.

Authors: Christensen, Matthew;Vukadinovic, Milos;Yuan, Neal;Ouyang, David

Nat Med. 2024 May;30(5):1481-1488. doi: 10.1038/s41591-024-02959-y. Epub 2024 Apr 30.

PubMed abstract

Blinded, randomized trial of sonographer versus AI cardiac function assessment.

Authors: He, Bryan;Ouyang, David;et al.

Nature. 2023 Apr;616(7957):520-524. doi: 10.1038/s41586-023-05947-3..

PubMed abstract

Video-based AI for beat-to-beat assessment of cardiac function.

Authors: Ouyang, David;He, Bryan;Ghorbani, Amirata;Yuan, Neal;Ebinger, Joseph;Langlotz, Curtis P;Heidenreich, Paul A;Harrington, Robert A;Liang, David H;Ashley, Euan A;Zou, James Y

Nature. 2020 Apr;580(7802):252-256. doi: 10.1038/s41586-020-2145-8. Epub 2020 Mar 25.

PubMed abstract

Related Stories

Researchers build largest-ever AI model to interpret echocardiograms

Researchers build largest-ever AI model to interpret echocardiograms

November 11, 2025

Kaiser Permanente investigator’s validation study sets stage to bring the AI model, called EchoPrime, into clinical care.
National workgroup urges rapid, efficient evaluation of impacts of artificial intelligence on health, health care

National workgroup urges rapid, efficient evaluation of impacts of artificial intelligence on health, health care

October 13, 2025

Division of Research investigators among key organizers and authors of JAMA AI Summit report.
American Heart Association funds Kaiser Permanente to study AI in cardiovascular care

American Heart Association funds Kaiser Permanente to study AI in cardiovascular care

July 29, 2025

Investigators receive $5 million research grant to explore ways to use artificial intelligence to accelerate and improve screening and treatment for cardiovascular disease.
Our Team
Back To Top