Tailored AI Guidelines for Heart Failure Care

Is this trial a fit for you?

A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.

What this trial studies

This cluster-randomized interventional trial tests an AI-driven clinical decision support tool that reviews a patient’s EHR data and provides brief, clinician-facing messages about GDMT opportunities and safety considerations before visits. The tool is advisory and does not place orders, leaving all treatment decisions to the clinician and patient. The study is conducted in Mass General Brigham outpatient cardiology clinics with providers randomized to use the CDS and aims to see if GDMT optimization improves in routine practice. Outcomes focus on uptake of GDMT adjustments and safety flagging. The approach builds on prior retrospective concordance between AI recommendations and expert judgment and seeks to reduce practice gaps in GDMT use.

Why it matters

Who can join: the full rules

Inclusion Criteria:

* Age ≥18 years
* Scheduled outpatient visit with a participating cardiology provider in an MGB outpatient cardiology clinic
* At least one prior cardiology clinic visit in the MGB system within the past 2 years
* Diagnosis of heart failure by ICD code within the past 2 years
* Heart failure diagnosis supported by at least one of the following:
* Current or recent use of a loop diuretic
* Left ventricular ejection fraction ≤40% on the most recent echocardiogram
* Explicit documentation of heart failure diagnosis or heart failure signs/symptoms in a prior cardiology note

Exclusion Criteria:

* Systolic blood pressure \<90 mmHg on the most recent recorded measurement
* Heart rate \<50 beats per minute on the most recent recorded measurement
* eGFR \<20 mL/min/1.73 m² on the most recent laboratory assessment
* Known cardiac amyloidosis or hypertrophic cardiomyopathy
* History of heart transplant or presence of a left ventricular assist device
* Severe aortic stenosis, severe aortic insufficiency, or severe mitral stenosis on the most recent echocardiogram
* Encounter occurs in an adult congenital heart disease clinic

Where it's running

• Mass General Brigham
  Boston, Massachusetts, United States Recruiting

Study contacts

• Study coordinator: Jonathan W Cunningham, MD, MPH
• Email: jcunningham3@bwh.harvard.edu
• Phone: 617-732-8534

Similar studies

Other studies for the same condition or treatment. Recruiting studies are listed first.

• Using Apple Watch data to predict heart failure outcomes

  This study is testing if data from Apple Watches can help predict heart failure problems and the chances of needing to go back to the hospital for patients with heart failure.

  Recruiting University Medical Center Goettingen · Goettigen, Lower Saxony · NCT06819618

• Comparing Aortix Device to Diuretics for Acute Heart Failure

  This study is testing whether the Aortix device can help people with acute heart failure who aren't responding to diuretics feel better compared to standard treatment.

  Recruiting at 33 sites Procyrion · Phoenix, Arizona and 49 other locations · NCT05677100

• Myocardial Energetics Across Cardiovascular Disease Spectrum Using 31P-MRS

  Researchers are testing whether phosphorus-31 magnetic resonance spectroscopy (31P-MRS) can map heart energy metabolism across healthy people and patients with various heart conditions.

  Recruiting Chinese Academy of Medical Sciences, Fuwai Hospital · Beijing · NCT07912086

• Tailored digital support to cut sedentary time in long-term cardiac rehab

  In adults in a long-term cardiac rehabilitation program, this study tests whether a personalized behavioural program with digital tools can reduce daily sitting time.

  Recruiting University of Lisbon · Lisbon, Lisbon District · NCT07910812

• NT-proBNP–guided heart failure screening for people 65+ in rural China

  This study tests whether using NT-proBNP blood tests to guide heart failure screening in adults 65 and older in rural China can find unrecognized heart problems more effectively than symptom-based screening.

  Recruiting Jiangsu Taizhou People's Hospital · Nanjing · NCT07885488

• Voice-based detection of heart failure deterioration using Noah Labs Vox

  This study tests whether a voice-analysis app can flag worsening heart failure in adults by comparing its alerts to standard weight-based monitoring.

  Recruiting Noah Labs · Boston, Massachusetts · NCT07870395

How to take part

1. Review the eligibility criteria above with your treating physician.
2. Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
3. Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.