Heart Failure
Conditions
Keywords
Heart failure, Remote monitoring, Machine learning
Brief summary
Background: Heart Failure (HF) is a condition in which the heart can no longer adequately pump blood around the body. The number of patients diagnosed with HF is increasing, consuming 4% of the NHS budget, and deadlier than most cancers. Most patients suffer from HF with reduced Ejection Fraction (HFrEF), where adequate treatment can improve quality of life and survival. Less than 50% of patients receive gold standard NHS guided medication and less than 20% receive appropriate monitoring (via echocardiography surveillance). This study looks at the use of a 'smart stethoscope' (Eko DUO), a stethoscope that uses information collected from the heart in the form of electrical (ECG) and sounds (phonocardiogram, PCG) waveforms, to predict the pumping function of the heart via artificial intelligence (AI-ECG). Aims: By using the smart stethoscope, this study evaluates whether the use of an easy-to-use home self-monitoring programme can: * Provide a solution for the current poor compliance of NHS echocardiogram surveillance programmes for people with newly diagnosed HF * Provide real-time assessment of heart function in response to medication changes * Improve the health economic and health outcomes of HF in the NHS Methods: 80 participants with newly diagnosed HFrEF, due to pre-existing heart disease and non-heart related causes, will be identified by the clinical team at Imperial College NHS Trust and obtain consent for the research team to approach them. All consented participants will receive a smart stethoscope and instructions for twice-weekly, 15-second self-examination for 3-months. Participants will also be invited for an additional echocardiogram at 6 weeks post-diagnosis, in addition to the routine, standard of care NHS echocardiogram surveillance for HF.
Interventions
DIAGNOSTIC_TESTEko DUO
Acquisition of a single-lead ECG via patients self-examine themselves twice a week for 12 months.
Sponsors
Imperial College London
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Inclusion criteria
* Age 18 years or above * Able to give informed consent * Newly diagnosed with HFrEF (i.e., LVEF below 40%) assessed by a consultant cardiologist within the past two weeks.
Exclusion criteria
* Any chest wound, skin pathology or other feature that would prohibit routine Eko DUO examination. * Participants who have been diagnosed with HF previously
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Descriptive analysis of trends and association of raw AI-ECG signals changes that correlate with HF progression. | Up to 18 months | 1. AI-ECG signal changes with LV impairment. 2. AI-ECG signal changes with medication optimization. 3. AI-ECG signal changes with healthcare episodes. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Sensitivity and specificity of AI-ECG to predict HF progression | Up to 18 months | 1. AI-ECG prediction of HF trajectory deterioration or improvement. 2. AI-ECG prediction of clinical congestive HF |
Countries
United Kingdom
Contacts
Primary ContactAbdullah Alrumayh
Backup ContactNicholas Peters
Outcome results
None listed