FDA Clears ECG-AI Algorithm for Early Detection of Pulmonary Hypertension

Anumana has received U.S. Food and Drug Administration (FDA) 510(k) clearance for its pulmonary hypertension (PH) algorithm, an artificial intelligence (AI)-enabled software-as-a-medical-device (SaMD) that detects early signs of PH. The algorithm previously earned FDA Breakthrough Device Designation and is the first PH algorithm cleared for use with standard 12-lead electrocardiograms (ECGs), thus making it broadly accessible across care settings.

A serious and progressive condition affecting the lungs and right side of the heart, PH is a progressive, life-threatening pulmonary vascular disease estimated to affect up to 1% of the global population.¹ It is often difficult to diagnose² due to non-specific early symptoms, such as dyspnea, with delays frequently exceeding two years.³ These delays are associated with increased morbidity and mortality, highlighting the need for earlier detection.⁴ Anumana’s algorithm enhances the standard 12-lead ECG by detecting subtle abnormalities that may not be visible to the human eye, helping clinicians identify when follow-up testing, such as echocardiography, is warranted using existing clinical workflows.

“Pulmonary hypertension is often difficult to recognize until it has progressed significantly, leaving patients and physicians at a disadvantage,” said Paul Friedman, M.D., chair of the Department of Cardiovascular Medicine at Mayo Clinic and an Anumana advisory board member. “FDA clearance of Anumana’s PH algorithm provides clinicians with a practical solution to identify PH earlier and determine appropriate next steps in care, expanding the clinical utility of routine ECGs.”

The PH algorithm helps clinicians identify subtle patterns associated with early PH in standard 12-lead ECGs. It integrates with EHR systems, including ECG management platforms, and runs entirely within the health system environment without transferring patient data.

“The FDA clearance of our Pulmonary Hypertension algorithm is the result of clinical development and regulatory work, and it marks a step toward expanding access to AI-enabled insights at the point of care,” Anumana President/Chief Operating Officer Simos Kedikoglou stated. “As the first PH algorithm cleared for use with standard 12-lead ECGs, it is broadly accessible across care settings, integrates directly into existing clinical workflows, and supports clinical decision-making in real time, with the potential to help identify patients earlier in their disease course. This milestone reflects Anumana’s broader vision to expand the role of ECGs in identifying cardiovascular risk earlier and at scale.”

Anumana’s ECG-AI PH algorithm was developed using more than 250,000 de-identified patient records from the Mayo Clinic.⁵ In an independent, multi-center study of 21,066 patients at five U.S. health systems, ECG-AI detected PH with 73% sensitivity and 74.4% specificity in adult patients presenting with dyspnea. In a separate real-world analysis study of patients with an ECG available between symptom onset and PH diagnosis, ECG-AI identified more than 85% of patients with pulmonary arterial hypertension (PAH) and 78% with chronic thromboembolic pulmonary hypertension (CTEPH).⁶ These data suggest a potential opportunity to support earlier detection of these two treatable PH subgroups.

Anumana is an AI-driven health technology company transforming cardiovascular care. Co-founded by nference and Mayo Clinic, Anumana develops SaMD solutions that apply multimodal AI to support early detection, clinical decision-making, and intraoperative guidance across the continuum of care. The company’s portfolio includes ECG-based algorithms, generative imaging applications, and real-time procedural support tools designed to improve outcomes in both diagnostic and intraoperative settings. The company’s FDA-cleared ECG-AI LEF and ECG-AI PH algorithms are currently available in the United States and eligible for reimbursement.

As a co-founder, Mayo Clinic has a financial interest in the company.

References
¹ Ley L, Grimminger F, Richter M, Tello K, Ghofrani A, Bandorski D. The Early Detection of Pulmonary Hypertension. Dtsch Arztebl Int. 2023;120(48):823-830. doi:10.3238/arztebl.m2023.0222.
² Dardi F, McCullagh B, Madureira Antunes Ferreira F, Meandzija M, Neill W, Cruz-Utrilla A. Delays in the diagnosis and management of pulmonary arterial hypertension: A simulated patient cases study across four European countries. ERJ Open Research. 2026:01693-02025. doi:10.1183/23120541.01693-2025.
³ DuBrock HM, Silvert E, Doddahonnaiah D, et al. Assessing the Impact of Time to Diagnosis and Treatment for Patients With Pulmonary Arterial Hypertension. Pulm Circ. 2025;15(4):e70208. Published 2025 Dec 15. doi:10.1002/pul2.70208.
⁴ Kubota K, Miyanaga S, Akao M, et al. Association of delayed diagnosis of pulmonary arterial hypertension with its prognosis. Journal of Cardiology. 2024;83(6):365-370. doi:10.1016/j.jjcc.2023.08.004.
⁵ DuBrock HM, Wagner TE, Carlson K, et al. An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension. Eur Respir J. 2024;64(1):2400192. Published 2024 Jul 25. doi:10.1183/13993003.00192-2024.
⁶ Anumana data on file.