NOrthwestern Tempus AI-enaBLed Electrocardiography (NOTABLE) Trial (NOTABLE)

NOrthwestern Tempus AI-enaBLed Electrocardiography (NOTABLE) Trial: A Pragmatic, Real-world Study of an Artificial-intelligence Enabled Electrocardiogram Algorithms to Improve the Diagnosis of Cardiovascular Disease

The goal of this clinical trial is to determine if a machine learning/artificial intelligence (AI)-based electrocardiogram (ECG) algorithm (rECHOmmend and ECG-AF) can identify undiagnosed cardiovascular disease in patients. It will also examine the safety and effectiveness of using this AI-based tool in a clinical setting. The main questions it aims to answer are:

1. Can the AI-based ECG algorithm improve the detection of atrial fibrillation and structural heart disease?
2. How does the use of this algorithm affect clinical decision-making and patient outcomes?

Researchers will compare the outcomes of healthcare providers who receive the AI-based ECG results to those who do not. Participants (healthcare providers) will:

Be randomized into two groups: one that receives AI-based ECG results and one that does not.

In the intervention group, receive an assessment of their patient's risk of atrial fibrillation or structural heart disease with each ordered ECG.

Decide whether to perform further clinical evaluation based on the AI-generated risk assessment as part of routine clinical care.

Study Overview

• Status: Recruiting
• Conditions: Cardiovascular Diseases; Atrial Fibrillation; Arrhythmia; Valvular Disease
• Intervention / Treatment: Device: Risk-Based Assessment for Cardiac Dysfunction

Detailed Description

There is a large burden of undiagnosed, treatable cardiovascular disease (CVD), encompassing various heart conditions such as arrhythmias (e.g., atrial fibrillation) and structural heart diseases (e.g., valvular disease). Early detection and accurate diagnosis can significantly improve patient outcomes by enabling timely, guideline-based interventions or therapies.

The goal of this study is to leverage machine learning approaches to enhance the detection and diagnosis of CVD. By identifying patients at risk of undiagnosed CVD and referring them for further clinical evaluation, the study aims to improve health outcomes.

Study Overview:

The NOTABLE study will compare the rates of new disease diagnoses, therapeutic interventions, and cardiovascular outcomes between two groups of patients managed by clinicians at Northwestern Medicine:

Patients whose clinicians use ECG predictive models. Patients whose clinicians do not use ECG predictive models.

Intervention Details:

This study utilizes Tempus AI algorithms (rECHOmmend and ECG-AF) to analyze 12-lead ECGs. Clinicians randomized to the intervention group will receive a "Risk-Based Assessment for Cardiac Dysfunction" when ordering a 12-lead ECG within EPIC. If a high-risk result is identified, clinicians receive an EHR inbox message suggesting a follow-up diagnostic test, such as echocardiography and/or ambulatory ECG monitoring.

Outcome Tracking:

Weekly summaries will inform clinicians in the intervention group of high-risk results identified by the AI algorithm. Clinicians in the usual care group will not receive any communication from the study investigators regarding AI predictions.

• Study Type: Interventional
• Enrollment (Estimated): 1000
• Phase: Not Applicable

Contacts and Locations

Study Locations

• United States
  • Illinois
    • Chicago, Illinois, United States, 60611
      • Recruiting
      • Northwestern University
      • Contact: Uma Mylavarapu; Email: uma.mylavarapu@northwestern.edu
      • Contact: Sanjiv Shah, MD; Phone Number: 312-498-0894; Email: sanjiv.shah@northwestern.edu

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

1. Atrial fibrillation algorithm

   1. Age 65 or over
   2. ECG obtained as part of routine clinical care

2. Structural heart disease algorithm

   1. Age 40 or over
   2. ECG obtained as part of routine clinical care

Exclusion Criteria:

1. Atrial fibrillation algorithm

   1. No history of AF
   2. No permanent pacemaker (PPM) or implantable cardioverter defibrillator (ICD)
   3. No recent cardiac surgery (within the preceding 30 days)

2. Structural heart disease algorithm

   1. No history of SHD
   2. No echocardiogram within the past 1 year

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Screening
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Intervention; Care teams randomized to the intervention will have access to the AI-enabled ECG-based screening tool.	Device: Risk-Based Assessment for Cardiac Dysfunction; The AI-enabled ECG-based screening tool analyzes 12-lead ECG recordings to identify patients at increased risk for undiagnosed cardiovascular diseases, specifically atrial fibrillation (AF) and structural heart disease (SHD). Clinicians in the intervention group will receive a risk assessment for AF and SHD each time they order an ECG for their patients.; Other Names: rECHOmmend; ECG-AF
No Intervention: Control; Care teams randomized to control will continue routine practice without access to the AI-enabled ECG-based screening tool.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Incidence of New Atrial Fibrillation Diagnosis	Number of participants with a new diagnosis of atrial fibrillation, identified by ICD-10-CM diagnosis code entry in the electronic health record (EHR), among patients ≥65 years old without a prior AF diagnosis who received a 12-lead ECG as part of routine clinical care.	6 months from index ECG
Incidence of New Structural Heart Disease Diagnosis (Composite)	Number of participants with a new diagnosis of one or more of the following, identified by ICD-10-CM diagnosis code and/or echocardiographic report in the EHR: moderate or severe aortic stenosis, moderate or severe aortic regurgitation, moderate or severe mitral stenosis, severe mitral regurgitation, severe tricuspid regurgitation, left ventricular ejection fraction ≤40%, or interventricular septal thickness (IVSd) >15 mm - among patients ≥40 years old without prior SHD diagnosis who received a 12-lead ECG as part of routine clinical care.	6 months from index ECG
Incidence of New Cardiovascular Diagnosis (Overall Composite: AF + SHD)	Number of participants with a new diagnosis of atrial fibrillation and/or any structural heart disease component listed in Primary Outcome Measure 2, identified by ICD-10-CM diagnosis code and/or echocardiographic report in the EHR.	6 months from index ECG

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Incidence of New Atrial Fibrillation-Related Therapy (Composite)	Number of participants initiated on one or more of the following after index ECG, identified by EHR medication order/administration record and procedural (CPT) codes: antiarrhythmic medication, atrioventricular (AV) nodal blocking agent, anticoagulant medication, or AF ablation procedure.	6 months from index ECG
Incidence of New Structural Heart Disease-Related Therapy (Composite)	Number of participants initiated on one or more of the following after index ECG, identified by EHR medication order/administration record and procedural (CPT) codes: medication for left ventricular systolic dysfunction (beta blocker, ACE-I/ARB/ARNI, MRA, or SGLT2 inhibitor); valvular heart disease therapy (valve repair or replacement); or new therapy for hypertrophic cardiomyopathy, cardiac amyloidosis, or hypertensive heart disease.	6 months from index ECG
Incidence of Cardiovascular Death	Number of participants who died from a cardiovascular cause, identified by EHR mortality data and/or documented cause of death.	6 months from index ECG
Incidence of Myocardial Infarction	Number of participants with a new myocardial infarction, identified by ICD-10-CM diagnosis code in the EHR.	6 months from index ECG
Incidence of Hospitalization for a Cardiovascular Cause	Number of participants hospitalized for a cardiovascular cause, including heart failure and stroke, identified by inpatient encounter records and ICD-10-CM diagnosis codes in the EHR.	6 months from index ECG

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Total Cost of Care	Total cost of care per participant managed by Northwestern Medicine clinicians using ECG-based predictive models compared to that of patients managed by Northwestern Medicine clinicians that are not using ECG-based predictive models, in US dollars, calculated from billing and procedural (CPT) codes recorded in the EHR and converted to cost using standard procedural code cost estimates.	Up to 5 years from index ECG
Incidence of Cardiovascular Death, Myocardial Infarction, or Hospitalization for a Cardiovascular Cause (Long-Term)	Number of participants experiencing cardiovascular death, myocardial infarction, or hospitalization for a cardiovascular cause (including heart failure and stroke), identified by EHR mortality data, ICD-10-CM diagnosis codes, and inpatient encounter records.	Up to 5 years from index ECG

Collaborators and Investigators

• Sponsor: Northwestern University
• Collaborators: Tempus AI
• Investigators: Principal Investigator: Sanjiv Shah, MD, Northwestern University

Study record dates

Study Major Dates

• Study Start (Actual): September 16, 2024
• Primary Completion (Estimated): September 1, 2027
• Study Completion (Estimated): September 1, 2028

Study Registration Dates

• First Submitted: July 16, 2024
• First Submitted That Met QC Criteria: July 16, 2024
• First Posted (Actual): July 22, 2024

Study Record Updates

• Last Update Posted (Actual): August 20, 2026
• Last Update Submitted That Met QC Criteria: August 19, 2026
• Last Verified: August 1, 2026

More Information

Terms related to this study

• Keywords: early detection; atrial fibrillation; artificial intelligence; structural heart disease; cardiac diagnostics
• Additional Relevant MeSH Terms: Pathologic Processes; Heart Diseases; Pathological Conditions, Signs and Symptoms; Cardiovascular Diseases; Atrial Fibrillation; Arrhythmias, Cardiac; Physiological Effects of Drugs; Molecular Mechanisms of Pharmacological Action; Protective Agents; Antioxidants; TEMPO
• Other Study ID Numbers: STU00220862

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: Yes
• product manufactured in and exported from the U.S.: No