Aortic Stenosis, Left Ventricular Diastolic Dysfunction, Mitral Regurgitation, Valvular Heart Disease Patients
Conditions
Keywords
Point-of-care ultrasound, POCUS, Artificial Intelligence, AI-guided imaging, Echocardiography, Screening, Early detection, Heart Failure, Older Adults, Geriatrics, Primary Care, Cluster randomized Trial, Implementation Science
Brief summary
Heart valve disease and weakened heart muscle (left ventricular systolic dysfunction) are common in older adults and often go undetected until serious complications such as heart failure develop. Detection currently depends on a clinician hearing a murmur and then ordering an echocardiogram, which is easily missed or delayed. This study tests whether a brief, artificial intelligence (AI)-guided handheld heart ultrasound - point-of-care ultrasound, or POCUS - performed by trained clinic staff during a routine visit identifies these conditions earlier than usual care. Primary care and geriatrics providers, rather than individual patients, are assigned by chance to one of two groups. Patients seen by providers in the AI-ultrasound group are offered a POCUS scan and a one-time blood test at their regular visit, and are referred for a confirmatory echocardiogram if the scan is abnormal. Patients seen by providers in the usual care group receive standard clinic care. Researchers will compare how often previously undiagnosed structural heart disease is newly identified in each group.
Detailed description
Structural heart disease (SHD) - principally degenerative valvular heart disease (VHD) and left ventricular systolic dysfunction (LVSD) - affects an estimated 21.7% of adults aged 65 and older and carries substantial morbidity and mortality, yet detection relies on passive case finding through auscultation and subsequent echocardiography referral. AI-guided point-of-care ultrasound (AI-POCUS) offers a means of systematic screening at the point of routine ambulatory care by operators without formal sonography training. IMPROVE is a hybrid type 1 effectiveness-implementation, stratified, cluster-randomized trial. The unit of randomization is the provider cluster: each participating primary care or geriatrics physician or advanced practice provider, with their patient panel, constitutes one cluster. Thirty-two clusters are randomized 1:1 to AI-POCUS screening or usual care, stratified by hospital system (UT Southwestern Medical Center and Parkland Health & Hospital System), with approximately 1,088 patients aged 65-85 enrolled over 24 months. In intervention clusters, trained clinic staff perform protocolized AI-guided POCUS using the Kosmos Torso-One device, together with a 2 mL NT-proBNP blood draw. Images are reviewed by a blinded echocardiographic core laboratory; participants with at least moderate VHD or LVEF 50% or less are referred for confirmatory transthoracic echocardiography, with all subsequent management at the treating provider's discretion. Usual care clusters receive standard care and are monitored for echocardiography referral within 90 days of the index visit. All echocardiograms performed within 90 days in either arm are interpreted in the core lab in a blinded fashion. The primary outcome (Aim 1) is a new diagnosis of at least moderate VHD or LVSD confirmed by complete echocardiography within 90 days of screening. Secondary outcomes include downstream care processes and major adverse cardiovascular events over 2 years. Aim 2 evaluates implementation determinants and outcomes - adoption, acceptability, appropriateness, and feasibility - using CFIR and Proctor's taxonomy, through structured workflow observations and semi-structured interviews. The primary analysis is intention-to-treat using a generalized linear mixed model with provider-level random effects.
Interventions
DEVICEKosmos Torso-One AI-guided Point-of-Care Ultrasound (EchoNous, Inc.)
A single AI-guided handheld POCUS examination performed by trained clinic staff (medical or certified nursing assistants) during a routine primary care or geriatrics visit. Acquisition is standardized, including parasternal long- and short-axis and apical 3- and 4-chamber views, with 2D imaging, color Doppler, M-mode of the mitral valve, and continuous-wave Doppler of the aortic and mitral valves. Images are transmitted to a central echocardiographic core laboratory, which screens for adequacy; adequate studies are analyzed by pre-specified AI algorithms based on 2017 ASE guidelines, blinded to arm assignment. A positive screen is defined as moderate or greater valvular heart disease or left ventricular ejection fraction of 50% or less. Positive results are communicated to the participant's primary care provider with a recommendation to consider confirmatory TTE; ordering remains at provider discretion, and the study team facilitates completion within 90 days of index visit.
Sponsors
University of Texas Southwestern Medical Center
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
SCREENING
Masking
SINGLE (Outcomes Assessor)
Masking description
Participants, treating providers, and investigators are aware of cluster assignment. All AI-POCUS images and all transthoracic echocardiograms performed within 90 days of the index visit in either arm are interpreted by an independent echocardiographic core laboratory blinded to arm assignment and to participant clinical information.
Intervention model description
Stratified cluster-randomized trial. The unit of randomization is the provider cluster: each participating primary care or geriatrics physician or advanced practice provider, together with their patient panel, constitutes one cluster. Thirty-two clusters are randomized 1:1 to AI-POCUS screening or usual care, stratified by hospital system, with 16 clusters per system (8 per arm). All eligible patients seen by a given provider are assigned to that provider's arm.
Eligibility
Sex/Gender
ALL
Age
65 Years to 85 Years
Healthy volunteers
No
Inclusion criteria
Provider (cluster) participants: * Physician or advanced practice provider (physician assistant or nurse practitioner) practicing in primary care or geriatrics at a participating institution who independently assesses patients * Patient panel comprising \>50% adults aged 65 years or older * Sees patients in ambulatory clinic at least 1 day per week on average * Agrees to participate, to undergo randomization, and to permit inclusion of all eligible patients from the panel * Provides written informed consent Patient participants: * Adults aged 65 to 85 years, inclusive * Attending a scheduled outpatient visit at a participating geriatrics or primary care clinic * Willing and able to provide written informed consent and, if the AI-POCUS screen is positive, to return for a confirmatory echocardiogram
Exclusion criteria
Provider (cluster) participants: * Serving in a locum tenens or other temporary capacity * Unwilling or unable to nominate an AI-POCUS champion from the clinic Patient participants: * Echocardiogram performed within the past 5 years * At least moderate aortic or mitral valve disease, or left ventricular ejection fraction 50% or less, documented on any prior echocardiogram * History of surgical or transcatheter intervention for aortic or mitral valve disease * Self-reported structural heart disease * Significant frailty burden or comorbidities limiting life expectancy to 1 year or less * Unable to provide informed consent
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| New diagnosis of structural heart disease (≥ moderate valvular heart disease or left ventricular systolic dysfunction) | 90 days from index clinic visit | New diagnosis of ≥ moderate aortic or mitral valvular heart disease or left ventricular systolic dysfunction (ejection fraction ≤50%), confirmed by standard transthoracic echocardiography performed within 90 days of the index clinic visit. Assessed using the disease detection rate (true positives/total number of patients in the study). |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Recall Rate | 90 days from index clinic visit | Proportion of AI-POCUS screening studies requiring further workup, defined as total number of positive screens (true + false positives) divided by total number of patients in the study. |
| Referrals to cardiology or cardiac surgery | 2 years from index clinic visit | Proportion of participants with a new referral to cardiology or cardiac surgery, ascertained through electronic health record review. |
| Major adverse cardiac events (MACE) | 2 years from index clinic visit | Composite of all-cause mortality, stroke, and cardiovascular hospitalization. Deaths ascertained through EHR review and annual National Death Index query. Stroke and cardiovascular hospitalization ascertained through participant self-report at follow-up, EHR review, and primary discharge diagnoses (ICD-10-CM), with additional confirmation from regional hospital claims data. |
Countries
United States
Contacts
CONTACTDharam J Kumbhani, MD, SM, MRCP, FACC, FAHA, FSCA
CONTACTRitika Dhruve, MBBS, MPH
Outcome results
None listed