AI-Assisted Echocardiogram for Heart Ultrasound Software

(AI INSIGHT Trial)

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Kaiser Permanente

Disqualifiers: Congenital heart disease, Ventricular assist, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

Duration: 6 months

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial explores how artificial intelligence (AI) can help doctors read heart ultrasound images more efficiently and consistently. It compares three methods of interpreting these images: AI-Assisted Echocardiogram Interpretation, a sonographer (a trained technician), and a cardiologist alone. The goal is to determine if AI can match the accuracy of current methods while saving time. The trial seeks adults who have undergone a standard heart ultrasound at a KPNC Medical Center. As an unphased trial, it offers patients the chance to contribute to innovative research that could enhance future heart ultrasound diagnostics.

Do I need to stop my current medications for the trial?

The trial information does not specify whether you need to stop taking your current medications. It's best to consult with the trial coordinators for specific guidance.

What prior data suggests that this AI-assisted echocardiogram interpretation is safe?

Research has shown that using AI to help interpret heart ultrasounds is generally safe and well-tolerated. In past studies, AI quickly and accurately analyzed heart images. For instance, one study found that AI's interpretations matched the accuracy of those by trained technicians. Another study demonstrated that AI could interpret these images in just minutes without losing accuracy.

These studies did not identify any safety issues for patients. Since the AI tool is neither a drug nor a medical procedure, it lacks the side effects that medications might have. It provides an initial analysis, which a heart doctor then reviews to ensure the final interpretation is accurate and reliable.

In short, current evidence suggests that AI-assisted heart ultrasound interpretation is safe. The AI helps doctors work more efficiently without affecting the quality of care. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about this trial because it explores the potential of AI in interpreting echocardiograms, a crucial tool for diagnosing heart conditions. Unlike traditional methods where sonographers or cardiologists provide preliminary interpretations, this AI-assisted approach offers a new layer of efficiency by delivering quick and potentially more consistent initial readings. The AI's ability to analyze patterns and anomalies rapidly could enhance diagnostic accuracy and save valuable time, which is especially important in urgent cardiac care. This trial aims to find out if AI can match or even exceed human performance in preliminary interpretations, potentially revolutionizing how we conduct heart ultrasounds.

What evidence suggests that AI-assisted echocardiogram interpretation is effective for improving cardiologist efficiency and accuracy?

Research has shown that AI-assisted interpretation of heart ultrasounds can match the accuracy of traditional methods used by cardiologists and technicians. In this trial, participants will be assigned to different arms to compare these methods. One arm will use AI-Assisted Interpretation, where the AI tool provides a preliminary interpretation that a blinded cardiologist finalizes. One study found that the AI tool can interpret these scans in minutes, potentially speeding up the process and reducing the time doctors need to review results. Another study demonstrated that AI increases efficiency without sacrificing accuracy. These findings suggest that AI can maintain the quality of heart ultrasound readings while making the process faster and more consistent. The AI tool's ability to provide detailed reports supports its potential to enhance the reliability of heart health assessments. ^{2 6 7 8 9}

Who Is on the Research Team?

David Ouyang

Principal Investigator

Kaiser Permanente

Keane K Lee

Principal Investigator

Kaiser Permanente

Are You a Good Fit for This Trial?

This trial is for adult patients with historical echocardiogram images. Specific eligibility criteria are not provided, but typically participants would have no contraindications to an echocardiogram and be able to give informed consent.

Inclusion Criteria

Comprehensive transthoracic echocardiogram study performed at KPNC Medical Center

I am 18 years old or older.

Exclusion Criteria

Known Ventricular assist device

Known Congenital heart disease

Limited transthoracic echocardiogram study

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants undergo AI-assisted, sonographer-assisted, or cardiologist-only TTE interpretation workflows

6 months

Follow-up

Participants are monitored for accuracy, efficiency, and interpretation consistency after treatment

6 months

What Are the Treatments Tested in This Trial?

Interventions

• AI-Assisted Echocardiogram Interpretation

Trial Overview The study compares three ways of interpreting heart ultrasound tests: by cardiologists alone, with sonographer assistance, or with AI assistance. It aims to see if AI can match the accuracy of standard methods while improving efficiency and consistency in reading these tests.

How Is the Trial Designed?

Group I: AI-Assisted Interpretation Active Control 1 Intervention

In AI-prelim arm, AI provides the preliminary interpretation which is finalized by a blinded cardiologist.

Group II: Sonographer-Assisted Interpretation Active Control 1 Intervention

In Sonographer-prelim arm, sonographer provides the preliminary interpretation which is finalized by a blinded cardiologist.

Group III: Cardiologist-Only Interpretation Active Control 1 Intervention

In cardiologist-prelim arm, cardiology provides the preliminary interpretation which is finalized by a blinded separate cardiologist.

Who Is Running the Clinical Trial?

Kaiser Permanente

Lead Sponsor

Trials

563

Recruited

27,400,000+

Citations

1. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC11799715/

AI in Echocardiography: State-of-the-art Automated ... Echo AI Report―AI generates comprehensive echocardiographic reports based on automated measurements and analyses. AI Diagnosis―AI assists in ...

2. medicine.yale.edu medicine.yale.edu/news-article/ai-tool-interprets-echocardiograms-in-minutes/

AI Tool Interprets Echocardiograms in Minutes, New Yale ... A new study in JAMA led by Yale School of Medicine researchers finds that an artificial intelligence (AI)-enabled tool can interpret ...

3. medrxiv.org medrxiv.org/content/10.1101/2025.08.20.25334115v1.full

Artificial Intelligence-based Automated Echocardiographic ... Conclusions This real-world randomized trial demonstrated that AI-based echocardiographic analysis can enhance workflow efficiency, reduce ...

4. nature.com nature.com/articles/s44325-025-00063-9

AI assisted focused cardiac ultrasound in preventive ... An accelerated heart aging trajectory was observed in ~15% of patients and was associated with a significant elevation in the primary endpoint ...

5. clinicaltrials.gov clinicaltrials.gov/study/NCT03936413

NCT03936413 | Artificial Intelligence in Echocardiography Using ultrasound, this technique allows for non-invasive assessment of cardiac function, including systolic function, diastolic function, heart chamber ...

6. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC11266969/

Artificial Intelligence in Echocardiography: The Time is Now AI has firmly made its stamp on echocardiography, showing great promise in training, image acquisition, interpretation and analysis, diagnostics, ...

7. clinicaltrials.gov clinicaltrials.gov/study/NCT07229300?rank=3

AI ECHO INSIGHT RCT for Automated Echo Reporting The goal of this blinded randomized controlled trial is to assess whether AI-assisted TTE interpretation can improve cardiologist efficiency ...

8. nature.com nature.com/articles/s41586-023-05947-3

Blinded, randomized trial of sonographer versus AI cardiac ... For patients undergoing echocardiographic quantification of cardiac function, initial assessment of LVEF by AI was non-inferior to assessment by sonographers.

9. jamanetwork.com jamanetwork.com/journals/jama/article-abstract/2835630

Complete AI-Enabled Echocardiography Interpretation ... This study evaluates the accuracy of an artificial intelligence (AI) system on a comprehensive set of 39 echocardiographic labels and ...