FDA clears Tempus AI's third cardiovascular device for pulmonary hypertension detection

Tempus AI Inc. (NASDAQ: TEM) announced it has received 510(k) clearance from the U.S. Food and Drug Administration for Tempus ECG-PH, an artificial intelligence-enabled software device that analyzes standard 12-lead electrocardiograms for signs associated with pulmonary hypertension.

The clearance marks the third FDA-cleared device in Tempus' cardiovascular portfolio, expanding the company's suite of AI products aimed at identifying patients at risk for complex cardiac conditions.

Tempus ECG-PH analyzes resting, non-ambulatory 12-lead ECG recordings and detects signs associated with elevated mean pulmonary artery pressure — above 20 mmHg — an indicator of pulmonary hypertension. It is intended for use on clinical diagnostic ECG recordings collected at a health care facility from patients 40 years of age or older who present with cardiovascular symptoms such as dyspnea, fatigue, chest pain or edema, and who do not have a known history of the condition.

The software analyzes ECG data only and provides a binary output for interpretation. Tempus said the device is not intended as a stand-alone diagnostic tool for pulmonary hypertension, should not be used for serial patient monitoring, and should not be used on ECGs with paced rhythms. Results should be interpreted alongside other diagnostic information, including the patient's original ECG recordings, symptoms, additional testing and clinical history, according to the company.

"Pulmonary hypertension has historically been underdiagnosed because early symptoms are non-specific and gold-standard diagnostics are invasive," Brandon Fornwalt, MD, PhD, senior vice president of cardiology at Tempus, said in a statement. "This third FDA-cleared cardiovascular device reflects our broader goal of using AI to help identify patients across the spectrum of cardiovascular disease. We're building tools that can help clinicians surface risk earlier."

Pulmonary hypertension is characterized by stiffening and narrowing of the blood vessels in the lungs, which puts strain on the right side of the heart. It affects roughly 1% of the population and up to 10% of adults over 65, according to Tempus, yet can be difficult to diagnose. Confirming a diagnosis typically requires right heart catheterization, an invasive procedure, along with echocardiography.

Tempus, a technology company focused on advancing precision medicine through the application of artificial intelligence in health care, said it maintains one of the world's largest libraries of multimodal data along with an operating system designed to make that data accessible and useful. The company provides AI-enabled precision medicine solutions to physicians to support personalized patient care, while also facilitating the discovery, development and delivery of therapeutics. Tempus has said its goal is for each patient to benefit from the treatment of others who came before, by giving physicians tools that learn as the company gathers more data.

AI-ECG screening tools expand across cardiology

Tempus ECG-PH's clearance adds to a growing field of AI tools designed to extract diagnostic signal from the electrocardiogram, a test that is inexpensive, noninvasive and already part of routine care for millions of patients. Other AI-enabled ECG platforms have recently earned regulatory clearance for detecting conditions ranging from atrial fibrillation risk to structural heart disease, often well before those conditions would otherwise be caught through symptoms or imaging.

The broader shift reflects changing expectations around cardiovascular screening: rather than relying primarily on invasive testing or imaging after a patient becomes symptomatic, AI models are increasingly being used to mine data from a test many patients already have on file for subtle patterns tied to underlying disease. Proponents argue the approach could meaningfully expand early detection, particularly in primary care and community settings where advanced cardiac testing may not be readily available.

As more of these software tools move through the FDA's clearance pipeline, health systems and payers will likely continue to weigh how AI-flagged results should be incorporated into existing referral pathways, and how performance holds up across diverse patient populations before broader clinical adoption.