Tempus ECG-AI (ECG-AF and ECG-Low EF)

Tempus ECG-AI is a suite of FDA-cleared, AI-powered electrocardiogram analysis solutions developed by Tempus to support clinicians in identifying patients who may be at increased risk for certain cardiovascular conditions. Designed for use within existing clinical workflows, the platform integrates with standard ECG platforms and electronic health record (EHR) systems to deliver advanced algorithmic insights at the point of care. The solutions are intended for use in healthcare facilities and are aimed at cardiologists and other clinicians seeking to identify underdiagnosed and undertreated cardiac patients.

The Tempus ECG-AI platform currently includes two FDA-cleared devices — Tempus ECG-AF and Tempus ECG-Low EF — each trained on large-scale de-identified patient datasets and designed to provide clinically actionable outputs that must be interpreted alongside other diagnostic information, patient history, and clinical judgment.

Clinical Workflow: How Tempus ECG-AI Works

• Step 1 – Patient Filtering: Tempus leverages EHR integrations and patient clinical data to filter patients who may be eligible for Tempus ECG-AI device use based on the relevant indications for use (IFU) criteria.
• Step 2 – Patient Diagnosis: Tempus ECG-AI cardiology algorithms analyze physiological inputs using machine learning models to detect signs associated with certain cardiovascular conditions, supporting further referral or diagnostic follow-up.
• Step 3 – Patient Follow-up: The platform uses AI to identify and contextualize patients within their care journey, surface precision pathways at the point of care, and track patients for further referral or diagnostic follow-up consistent with clinical care guidelines.

Tempus ECG-AF: Intended Use and Design

• Intended to analyze recordings from resting 12-lead ECG devices and detect signs associated with a patient experiencing atrial fibrillation and/or atrial flutter (AF) within the next 12 months.
• For use on ECG recordings collected at a healthcare facility from patients 65 years of age or older who do not have a known history of AF, do not have a pacemaker or implantable cardioverter defibrillator, and did not undergo cardiac surgery within the preceding 30 days.
• Results must be interpreted in conjunction with other diagnostic information, including the patient's original ECG recordings, other tests, symptoms, and clinical history.
• Tempus ECG-AF does not describe a person's overall risk of experiencing AF and should not serve as the sole basis for diagnosis or treatment of AF; results are not intended to rule out AF or the need for follow-up.
• The algorithm was trained on de-identified data from more than 1,500,000 ECGs and more than 500,000 patients.
• For patients receiving a positive result, AF would be observed in approximately 1-in-5 patients within the next 12 months.

Tempus ECG-Low EF: Intended Use and Design

• Intended to analyze resting, non-ambulatory 12-lead ECG recordings and detect signs associated with having a low left ventricular ejection fraction (LVEF ≤40%).
• For use on clinical diagnostic ECG recordings collected at a healthcare facility from patients 40 years of age or older who are at risk of heart failure, including but not limited to patients with atrial fibrillation, aortic stenosis, cardiomyopathy, myocardial infarction, diabetes, hypertension, mitral regurgitation, and ischemic heart disease.
• Provides a binary output for interpretation; it is not a stand-alone diagnostic tool, should not be used for patient monitoring, and should not be used on ECGs with paced rhythms.
• A positive result may suggest the need for further clinical evaluation to establish a diagnosis of low LVEF; patients with a negative result should continue to be evaluated according to current medical practice standards.
• The algorithm was trained on de-identified data from more than 930,000 ECGs and more than 170,000 patients.
• For patients receiving a positive result, LVEF ≤40% would be observed in approximately 2-in-5 patients when tested by echocardiogram.

CPT Coding and Reimbursement

• Effective January 1, 2025, CPT codes +0764T and 0765T are listed under the Hospital Outpatient Prospective Payment and Ambulatory Surgical Center Payment Systems (OPPS) as Category III codes to describe assistive algorithmic electrocardiogram assessments for cardiac dysfunction.
• A CMS decision has enabled Medicare reimbursement for assessments of cardiac dysfunction using the Tempus ECG-AF algorithm.

Active Research Studies and Pipeline

• ALERT Study: A multi-center, prospective, cluster-randomized controlled trial evaluating automated notifications as an intervention to support identification and evaluation of patients possibly indicated for transcatheter or surgical procedures to treat aortic stenosis or mitral regurgitation.
• MOMENTOUS Study: A multi-site study of an investigational AI algorithm that analyzes 12-lead ECG results to find patients at increased risk of undetected pulmonary hypertension (PH), tracking clinical outcomes of patients identified for further evaluation.
• NOTABLE Study: Conducted in collaboration with Northwestern Medicine, this study examines rates of new disease diagnosis, therapeutic interventions, and cardiovascular outcomes in patients whose clinicians use ECG predictive models versus those who do not.
• ECG AID Study: Recently completed enrollment; investigates the prospective performance of algorithms for atrial fibrillation and structural heart disease.

Research as a Service

• Automated methods to identify patients indicated for clinical trials.
• Support for publications and conference abstracts.
• Opportunities for healthcare institutions to join studies or partner with Tempus on cardiovascular research.

Tempus ECG-AI solutions are designed to integrate seamlessly with existing ECG platforms and EHR systems, enabling deployment within standard clinical workflows. Both Tempus ECG-AF and Tempus ECG-Low EF have received U.S. FDA 510(k) clearance, and the platform is backed by an active research program advancing algorithm development, validation, and scaled clinical adoption across a broad range of cardiovascular conditions.