AI-Guided Ultrasound for Heart Disease

(IMPROVE Trial)

Not yet recruiting at 2 trial locations
DJ
RD
Overseen ByRitika Dhruve, MBBS, MPH
Age: 65+
Sex: Any
Trial Phase: Academic
Sponsor: University of Texas Southwestern Medical Center
No Placebo GroupAll trial participants will receive the active study treatment (no placebo)

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial aims to determine if an AI-guided handheld ultrasound, specifically the Kosmos Torso-One AI-guided Point-of-Care Ultrasound, can detect heart problems earlier than usual methods during routine doctor visits. It focuses on identifying heart valve disease and a weak heart muscle, which are often difficult to detect before causing serious issues. Patients visiting doctors using this AI tool may receive a quick ultrasound and a blood test. If the ultrasound indicates a problem, they will undergo a detailed heart exam. This trial is suitable for adults aged 65 to 85 who are visiting a participating clinic and have not had a heart ultrasound in the past five years. As an unphased trial, it offers a unique opportunity to contribute to innovative research that could improve early detection of heart issues.

What prior data suggests that this AI-guided ultrasound is safe for detecting heart conditions?

In a previous study, researchers used the Kosmos Torso-One AI-guided ultrasound device to scan over 1,200 patients. The results showed that individuals without specialized training could use the device effectively and safely. It correctly identified heart issues 89 to 94 percent of the time, demonstrating high reliability. Additionally, the FDA has approved the Kosmos platform, indicating that it meets strict safety standards for medical devices. This approval confirms the device's safety and tolerability for use on people.12345

Why are researchers excited about this trial?

Researchers are excited about AI-guided ultrasound for heart disease because it offers a new, potentially more efficient way to detect heart issues early. Unlike traditional methods that rely on manual echocardiography referrals based on symptoms or physical findings, the Kosmos Torso-One device uses artificial intelligence to guide clinic staff in performing point-of-care ultrasounds. This approach could lead to earlier detection of conditions like moderate valvular heart disease or reduced ejection fraction, allowing for quicker intervention. By integrating AI into routine check-ups, this method promises to streamline the diagnostic process and expand access to advanced care without needing specialized sonographers.

What evidence suggests that AI-guided ultrasound is effective for detecting heart disease?

Research has shown that AI-guided ultrasounds effectively detect heart problems. In 95% of cases, the Kosmos Torso-One device provided quick answers to important heart health questions. Studies have found that when non-experts used this AI-powered device, it achieved accuracy rates of 89% to 94%. This tool excels at identifying issues such as heart pumping efficiency and valve problems. In this trial, participants in the AI-POCUS Screening arm will receive AI-guided point-of-care ultrasound using the Kosmos Torso-One device. These findings suggest that AI-guided ultrasound might help detect heart disease earlier than usual methods, potentially preventing serious complications.12678

Are You a Good Fit for This Trial?

This trial is for adults aged 65 and older who visit primary care or geriatric clinics. It aims to find heart valve problems or heart dysfunction early, before symptoms appear. People with known severe heart disease may not be eligible.

Inclusion Criteria

Presenting for a new or established visit at a primary care or geriatrics clinic at UT Southwestern Medical Center or Parkland Hospital
Seen by a provider cluster enrolled in the study
I have never been diagnosed with aortic or mitral valve heart disease.
See 3 more

Exclusion Criteria

I am unable or unwilling to give my consent for the study.
I am younger than 65 or older than 85 years old.
I have been diagnosed with aortic or mitral valve heart disease.
See 2 more

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Intervention

Trained clinic staff perform AI-guided point-of-care ultrasound using the Kosmos Torso-One device on eligible patients during routine primary care or geriatrics visits. Patients with ≥ moderate valvular heart disease or EF ≤50% are referred for confirmatory echocardiography within 90 days.

90 days
1 visit (in-person)

Usual Care

Eligible patients receive standard provider-driven care. Echocardiography referral occurs per routine clinical indications such as auscultated murmur or patient-reported symptoms.

90 days

Follow-up

Participants are monitored for major adverse cardiovascular events and other outcomes over 2 years.

2 years

What Are the Treatments Tested in This Trial?

Interventions

  • Kosmos Torso-One AI-guided Point-of-Care Ultrasound

Trial Overview

The study compares usual care to a new screening method using an AI-guided handheld ultrasound device during routine clinic visits, to see if it helps detect serious heart valve and muscle problems earlier.

How Is the Trial Designed?

2

Treatment groups

Experimental Treatment

Active Control

Group I: AI-POCUS ScreeningExperimental Treatment1 Intervention
Group II: Usual CareActive Control1 Intervention

Find a Clinic Near You

Who Is Running the Clinical Trial?

University of Texas Southwestern Medical Center

Lead Sponsor

Trials
1,102
Recruited
1,077,000+

Citations

AI-Powered Ultrasound Device Enhances Cardiac Monitoring ...

The findings demonstrate that non-ultrasound experts can effectively use Kosmos, achieving diagnostic accuracy between 89 to 94 percent among ...

Importance of Point-of-Care Ultrasound for Early Detection ...

Trained clinic staff perform AI-guided point-of-care ultrasound using the Kosmos Torso-One device on eligible patients during routine primary ...

Clinical Benchmarking for the Kosmos Platform

In 95% of cases, immediate answers to critical clinical questions were achieved. The ability to acquire superior quality images of the heart, lungs and abdomen

Nurse-led home-based detection of cardiac dysfunction ... - PMC

The primary outcome was the sensitivity of AI-POCUS in detecting a left ventricular ejection fraction (LVEF) <50% or left atrial volume index (LAVI) >34 mL/m2, ...

Importance of Point-of-Care Ultrasound for Early Detection of ...

Trained clinic staff perform AI-guided point-of-care ultrasound using the Kosmos Torso-One device on eligible patients during routine primary ...

Diagnostic accuracy of point-of-care ultrasound with artificial ...

Our objective was to determine the accuracy of FoCUS AI-assisted left ventricular ejection fraction (LVEF) assessment and compare its accuracy between novice ...

AI-Assisted Handheld Echocardiography by Nonexpert ...

Overall, AI-assisted handheld echocardiography supports reliable, triage-oriented cardiac imaging by nonexperts across diverse environments.

EchoNous, Inc. Announces FDA Approval for Its New ...

KOSMOS' image quality and AI-confirmation will give us greater accuracy and confidence at the bedside, reducing the need for additional testing ...