Multidisciplinary Screening for Heart Failure

(MAPLE-CHF Trial)

Recruiting at 3 trial locations

Overseen By Jennifer Petterson

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Cardiology Research UBC

Disqualifiers: Heart failure, Renal replacement, others

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

Compensation: Varies

Number of Visits: 28

1360 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

The trial aims to find better ways to detect heart failure early by using new tools like an AI echocardiogram (a type of heart imaging test using artificial intelligence) and a special blood test. It compares these new methods against usual care to determine if they can identify heart failure risks sooner. Participants divide into two groups: one follows standard care, and the other receives additional tests if certain blood markers are high. Individuals who may be a good fit for this trial include those over 40 with conditions such as diabetes or chronic obstructive pulmonary disease (COPD). As an unphased trial, this study offers a unique opportunity to contribute to groundbreaking research that could improve early detection of heart failure.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It is best to discuss this with the trial coordinators or your doctor.

What prior data suggests that this screening method is safe for identifying heart failure risk?

Research has shown that NT-proBNP tests are often used to diagnose heart failure. Patients have tolerated them well in the past, and they help doctors understand heart conditions better without causing harm.

Studies have found that artificial intelligence (AI) in heart ultrasound tests, known as echocardiograms, can help detect heart problems early. The AI echocardiogram is non-invasive, involving no surgery or needles. It functions like a regular ultrasound and has been safely used in many patients to assess heart health.

Electrocardiograms (ECGs) are commonly used to monitor the heart's electrical activity. They are safe and painless, serving as a standard tool for checking heart health for a long time.

Overall, these tests have been used safely in many situations, with no reports of serious side effects, making them a safe option for participants in this study. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about the Multidisciplinary Screening for Heart Failure trial because it explores advanced diagnostic tools like the AI echocardiogram and NT-proBNP testing to potentially improve early detection of heart failure. Unlike traditional methods, which often rely solely on symptoms and basic tests like an electrocardiogram (ECG), this approach integrates artificial intelligence to analyze heart images, offering a more precise and comprehensive assessment. The use of NT-proBNP as a biomarker helps identify high-risk patients sooner, allowing for targeted interventions. By potentially catching heart failure earlier, this trial aims to enhance patient outcomes and reduce the burden of heart disease.

What evidence suggests that this trial's methods could be effective for early heart failure screening?

In this trial, NT-proBNP results will guide participants in the investigational arm. Research has shown that NT-proBNP reliably indicates heart failure. Levels above 125 pg/mL may suggest heart failure, aiding early diagnosis. Participants with elevated NT-proBNP levels will have a study visit that includes an AI echocardiogram and an electrocardiogram (ECG), both of which enhance heart failure detection. Studies support these tools for predicting heart failure, aiming to identify heart issues earlier and potentially improve patient outcomes. ^{1 4 6 7 8}

Who Is on the Research Team?

Nathaniel M Hawkins, MD

Principal Investigator

Associate Professor of Medicine, UBC Division of Cardiology

Anique Ducharme, MD

Principal Investigator

Professor of Medicine, Univeriste de Montreal, Montreal Heart Institute

Serge LePage, MD

Principal Investigator

Centre Hospitalier Universite de Sherbrooke-Hopital Fleurimont

Are You a Good Fit for This Trial?

This trial is for adults over 40 with risk factors like coronary artery disease, diabetes, atrial fibrillation, stroke history, regular diuretic use, COPD, peripheral artery disease or chronic kidney disease. It's not for those who can't consent, already have heart failure diagnosis or are on renal replacement therapy.

Inclusion Criteria

I have COPD confirmed by tests, a doctor, or I'm on COPD treatment.

I have been using water pills regularly for over a month in the past year.

I have two or more risk factors for heart failure.

Exclusion Criteria

I am on dialysis.

I am able to understand and agree to the study's procedures and risks.

I have been diagnosed with heart failure before.

Timeline for a Trial Participant

Pre-screening

Pre-screening using extracted primary care electronic health records with a case finding algorithm

2 weeks

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Intervention

Participants in the intervention arm undergo NT-proBNP testing, and if elevated, receive an AI echocardiogram and ECG

6 months

Study visit within 28 days of NT-proBNP result for elevated cases

Routine Care

Participants in the routine care arm are monitored for heart failure events

6 months

Follow-up

Participants are monitored for safety and effectiveness after treatment

6 months

What Are the Treatments Tested in This Trial?

Interventions

• AI echocardiogram
• Electrocardiogram
• NT-proBNP

Trial Overview

The study tests if a special algorithm to find heart failure signs in electronic health records plus additional screening (NT-proBNP blood test and AI echocardiogram) can detect heart failure earlier compared to usual care methods.

How Is the Trial Designed?

Group I: Investigational arm guided by NT-proBNP result Active Control 4 Interventions

NT-proBNP drawn and if level elevated (\>125 pg/ml) a study visit with artificial intelligence (AI) echocardiogram, electrocardiogram (ECG), and heart failure (HF) focused examination conducted

Group II: Routine care arm Active Control 1 Intervention

Participants will be remotely monitored for number of heart failure events

AI echocardiogram is already approved in Canada for the following indications:

Approved in Canada as AI Echocardiogram for:

• Heart Failure Diagnosis
• Cardiac Function Assessment

Who Is Running the Clinical Trial?

Cardiology Research UBC

Lead Sponsor

Trials

16

Recruited

7,100+

Centre for Cardiovascular Innovation

Collaborator

Trials

1

Recruited

1,400+

NHS Greater Glasgow & Clyde

Collaborator

Trials

1

Recruited

1,400+

Montreal Heart Institute

Collaborator

Trials

125

Recruited

85,400+

AstraZeneca

Industry Sponsor

Trials

4,491

Recruited

290,540,000+

Sir Pascal Soriot

AstraZeneca

Chief Executive Officer since 2012

Veterinary Medicine from École nationale vétérinaire d'Alfort, MBA from HEC Paris

Dr. Cristian Massacesi

AstraZeneca

Chief Medical Officer since 2021

MD from Marche Polytechnic University, Oncology training at Royal Marsden Hospital, Kaplan Comprehensive Cancer Center, and European Institute of Oncology

Pascal Soriot

AstraZeneca

Chief Executive Officer since 2012

Veterinary Medicine from École nationale vétérinaire d'Alfort, MBA from HEC Paris

Cristian Massacesi

AstraZeneca

Chief Medical Officer since 2021

MD from Marche Polytechnic University, Medical Oncology training at Royal Marsden Hospital, Kaplan Comprehensive Cancer Center, and European Institute of Oncology

Canadian Heart Function Alliance

Collaborator

Trials

2

Recruited

1,400+

HeartLife Foundation

Collaborator

Trials

1

Recruited

1,400+

Published Research Related to This Trial

Artificial intelligence-enabled electrocardiography (AIeECG) shows high diagnostic accuracy for detecting left ventricular systolic dysfunction (LVSD), with a median area under the curve (AUC) of 0.90, sensitivity of 83.3%, and specificity of 87% across various populations.

AIeECG can be particularly beneficial in non-cardiology settings and when used alongside natriuretic peptide testing, but further prospective randomized trials are needed to assess its impact on treatment outcomes and cost-effectiveness.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificial intelligence enabled ECG screening for left ventricular systolic dysfunction: a systematic review. Bjerkén, LV., Rønborg, SN., Jensen, MT., et al.[2023]

The study compared three NT-proBNP immunoassays for diagnosing heart failure using 160 patient samples, finding that all assays had acceptable analytical performance and good agreement.

Among the assays, the Elecsys proBNP II demonstrated higher specificity and a better positive likelihood ratio for diagnosing heart failure, suggesting it may be the most effective option for clinicians.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Evaluation of Analytical Performances and Comparison of 3 NT-proBNP Assays for Diagnosing Heart Failure. Cho, J., Lee, JH., Lee, SG.[2023]

In a study of 108,330 heart failure patients, NT-proBNP levels were found to reliably predict clinical outcomes, supporting its use as a surrogate marker in heart failure trials.

The analysis showed that early NT-proBNP measurements can effectively forecast hazard ratios for clinical events, allowing for shorter and smaller heart failure trials without compromising reliability.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

NT-proBNP Qualifies as a Surrogate for Clinical End Points in Heart Failure. Schmitt, W., Rühs, H., Burghaus, R., et al.[2021]

In a study of 245 heart failure patients, those with atrial fibrillation (AF) had significantly higher levels of N-terminal pro brain natriuretic peptide (NT-proBNP) compared to those with sinus rhythm, indicating a potential biomarker for worse outcomes.

NT-proBNP was found to be an independent predictor of death in patients with AF, suggesting that monitoring NT-proBNP levels could be crucial for assessing prognosis in these patients.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Effect of atrial fibrillation on plasma NT-proBNP in chronic heart failure. Corell, P., Gustafsson, F., Kistorp, C., et al.[2007]

In a study of 254 patients undergoing cardiac catheterization, plasma brain natriuretic peptide was found to be the most effective marker for identifying left ventricular impairment, significantly predicting increased left ventricular end diastolic pressure and decreased ejection fraction.

While brain natriuretic peptide showed better diagnostic accuracy compared to atrial natriuretic factor and N-terminal pro-atrial natriuretic factor, the overall effectiveness of these natriuretic peptides in diagnosing left ventricular dysfunction in patients with coronary heart disease was still considered modest.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Plasma cardiac natriuretic peptide determination as a screening test for the detection of patients with mild left ventricular impairment. Omland, T., Aakvaag, A., Vik-Mo, H.[2019]

A study involving 44,959 patients demonstrated that an AI model applied to ECG data can effectively identify asymptomatic left ventricular dysfunction (ALVD), achieving high accuracy (85.7%) and sensitivity (86.3%).

Patients who screened positive for ALVD using the AI model were found to be four times more likely to develop future ventricular dysfunction, highlighting the potential of AI-enhanced ECG as a proactive screening tool for early intervention.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. Attia, ZI., Kapa, S., Lopez-Jimenez, F., et al.[2022]

In a study of 271 patients with acute heart failure, NT-proBNP-guided therapy, which involved intensifying treatment based on NT-proBNP levels, did not significantly improve outcomes compared to standard care.

However, a decrease in NT-proBNP levels from predischarge to discharge was found to be an independent predictor of better outcomes, indicating that monitoring NT-proBNP could still be valuable in assessing patient prognosis.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

N-terminal pro-B-type natriuretic peptide-guided therapy in patients hospitalized for acute heart failure. Carubelli, V., Lombardi, C., Lazzarini, V., et al.[2017]

Echocardiography combined with B-type natriuretic peptides (BNPs) significantly enhances the assessment of cardiac function and can improve the diagnosis and management of cardiovascular diseases.

Using amino-terminal pro-B-type natriuretic peptide (NT-proBNP) alongside echocardiography helps identify asymptomatic left ventricular dysfunction and stratifies risk in heart failure patients, guiding timely interventions for those at greatest risk.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

B-type natriuretic peptides and echocardiographic measures of cardiac structure and function. Troughton, RW., Richards, AM.[2016]

Cardiac natriuretic peptides, BNP and NT-proBNP, are effective for screening left ventricular systolic dysfunction in patients with heart failure symptoms, particularly in those under 75 years old, where they show high sensitivity and negative predictive values.

These peptides also serve as important prognostic markers for mortality and cardiovascular hospitalization, and can be useful in monitoring heart failure patients over time.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

[Natriuretic peptides as cardiac markers in clinical practice]. Veien, KT., Jensen, JK., Hildebrandt, P., et al.[2015]

The AI-enabled electrocardiogram (ECG) system can accurately predict levels of B-type natriuretic peptide (BNP) and N-terminal pro-brain natriuretic peptide (pBNP) using deep learning models, with high accuracy in distinguishing between mild and severe abnormalities.

ECG-pBNP was found to be a better predictor of all-cause mortality compared to ECG-BNP, suggesting it may be more effective for monitoring cardiovascular disease risk in patients.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificial Intelligence-Enabled Electrocardiography Detects B-Type Natriuretic Peptide and N-Terminal Pro-Brain Natriuretic Peptide. Liu, PY., Lin, C., Lin, CS., et al.[2023]

A study involving 221,846 ECGs from four institutions aimed to develop AI models for detecting left ventricular systolic dysfunction (LVSD) with an ejection fraction (EF) <40%, showing promising internal accuracy but variable external validation results.

The performance of AI models varied significantly between institutions, emphasizing the need for external validation and careful consideration of patient characteristics and ECG abnormalities when using AI for LVSD detection.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Importance of external validation and subgroup analysis of artificial intelligence in the detection of low ejection fraction from electrocardiograms. Yagi, R., Goto, S., Katsumata, Y., et al.[2023]

In a blinded, randomized trial involving 3,769 echocardiographic studies, AI assessment of left ventricular ejection fraction (LVEF) was found to be non-inferior to sonographer assessments, with a significantly lower rate of substantial changes in LVEF (16.8% for AI vs. 27.2% for sonographers).

The AI-guided workflow not only matched the accuracy of sonographer assessments but also saved time for both sonographers and cardiologists, indicating that AI can effectively streamline the echocardiography interpretation process.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Blinded, randomized trial of sonographer versus AI cardiac function assessment. He, B., Kwan, AC., Cho, JH., et al.[2023]

Citations

1.

ahajournals.org

ahajournals.org/doi/10.1161/JAHA.124.039511

Artificial Intelligence in Diagnosis of Heart Failure

In this review, we explore the challenges in current diagnosis of HF, basic AI concepts and common AI algorithms, and latest AI research in HF diagnosis.

2.

pmc.ncbi.nlm.nih.gov

pmc.ncbi.nlm.nih.gov/articles/PMC12542969/

AI-assisted heart failure management: A review of clinical ...

The results suggest that AI and deep learning can improve ECG analysis efficiency and accuracy and support expert-human interpretation, reducing the number of ...

3.

nature.com

nature.com/articles/s41586-025-09227-0

Detecting structural heart disease from electrocardiograms ...

Here we introduce a deep learning model, EchoNext, trained on more than 1 million heart rhythm and imaging records across a large and diverse health system.

4.

pmc.ncbi.nlm.nih.gov

pmc.ncbi.nlm.nih.gov/articles/PMC7617907/

The Emerging Role of Artificial Intelligence in Heart Failure

AI systems can be trained to analyse readily available data, such as ECGs and heart sounds, and assess likelihood of heart failure. AI can also ...

5.

sciencedirect.com

sciencedirect.com/science/article/abs/pii/S0914508725002229

Artificial intelligence in HFpEF: Diagnosis, prognosis, and ...

Chiou et al. AI-assisted echocardiographic prescreening of heart failure with preserved ejection fraction on the basis of intrabeat dynamics ...

6.

pmc.ncbi.nlm.nih.gov

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

Artificial Intelligence in Echocardiography: The Time is Now

RV function can be affected by congenital heart disease, left-sided heart failure, valvular heart disease, pulmonary hypertension and coronary artery disease [ ...

7.

medicine.yale.edu

medicine.yale.edu/news-article/new-ai-tool-identifies-risk-of-future-heart-failure/

New AI Tool Identifies Risk of Future Heart Failure

Researchers developed an artificial intelligence (AI) tool that can identify individuals at high risk of developing heart failure using electrocardiogram (ECG) ...

8.

clinicaltrials.gov

clinicaltrials.gov/study/NCT03936413

NCT03936413 | Artificial Intelligence in Echocardiography

Also called a data safety and monitoring board, or DSMB. ... Echocardiography is a common and essential tool in the diagnosis of cardiovascular disease.