Skip to content

Detection of Heart Conditions Using Artificial Intelligence

Real-World Evaluation of the Performance of Eko's Heart Murmur Detection Algorithm When Used by Front-line Healthcare Providers on Geriatric Patients

Status
Completed
Phases
Unknown
Study type
Observational
Source
ClinicalTrials.gov
Registry ID
NCT04933890
Enrollment
68
Registered
2021-06-22
Start date
2021-06-01
Completion date
2021-12-31
Last updated
2022-12-09

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Heart Failure, Left Ventricular Dysfunction

Brief summary

The purpose of this study is to evaluate how Eko AI performs in the real world, front-line setting where the availability of sophisticated, expensive diagnostic tools is limited, and where there is a premium on detecting VHD early in its course.

Detailed description

Echocardiography is the state of the art for diagnosing VHD. However, without an effective pre-screening tool, many echocardiograms (echos) are being ordered unnecessarily. A recent study found that greater than 66% of all echos performed in the United States do not alter clinical management, while an additional 4% may be deemed inappropriate altogether. Because of this, echos now make up a disproportionately large segment of healthcare expenditure. Each year, 1 in 5 Medicare enrollees receives an echo at a total cost of $1.2 billion, or 11% of total Medicare spending on imaging services. This is compounded by the fact that an estimated 35 million Americans live in medically underserved areas, where patients must travel an average of 56 miles to see a specialist and receive an echo. This does not encourage compliance, and only adds to cost, lost working hours, and inconvenience. There is therefore a growing, unmet need for better VHD screening tools. Tools that will consistently, reliably, quickly, and cheaply identify VHD when it is early and asymptomatic, when patients can be managed early and appropriately, and when they are at the lowest risk from an intervention. Such a tool will have a positive impact on the cost of care, patient and provider experience, and healthcare outcomes. The FDA-cleared Eko CORE and Eko DUO electronic stethoscopes offer clinicians a familiar and inexpensive tool that is widely accepted by patients and providers, while at the same time offer sensors and artificial intelligence technology that can improve screening and detection of medical conditions such as VHD. Both the CORE and the DUO feature sound amplification during auscultation - the CORE also offers active noise cancellation - which improves the ability of the clinician to detect nuanced changes in heart sounds.

Interventions

Auscultation of heart sounds using electronic stethoscope

Sponsors

Eko Devices, Inc.
Lead SponsorINDUSTRY

Study design

Observational model
COHORT
Time perspective
CROSS_SECTIONAL

Eligibility

Sex/Gender
ALL
Age
18 Years to No maximum

Inclusion criteria

* English-speaking adults who are 18 years and older * Able and willing to provide informed consent * Complete a clinical echocardiogram within 7 days before or after study procedures

Exclusion criteria

* Unwilling or unable to provide informed consent * Patients who are hospitalized

Design outcomes

Primary

MeasureTime frameDescription
Single-lead ECG based algorithm developmentWithin two minutes of device useEvaluate performance of single-lead ECG based algorithm to identify individuals with reduced ejection fraction.
Single-lead ECG based algorithm PerformanceWithin two minutes of device useTo demonstrate that Eko's murmur detection algorithm outperforms front-line healthcare providers in detecting heart murmurs in real-world use. Collecting data in a point-of-care setting will demonstrate how accurately the algorithm detects murmurs in comparison to an unassisted clinical examination. Algorithm output and clinical determination will be confirmed by echocardiographic ground truth, with the results being blinded until the end of the study

Countries

United States

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026