A new artificial intelligence algorithm can now detect cardiac amyloidosis, a serious heart condition that doctors frequently miss, by analyzing routine electrocardiograms (ECGs) that patients already receive during standard cardiac evaluations. The AI tool, developed by Anumana and validated across 25,525 patients at four major U.S. health systems, achieved 78.9% sensitivity and 91.2% specificity in identifying the condition, meaning it caught nearly four out of five cases while maintaining high accuracy .

What Is Cardiac Amyloidosis and Why Is It So Hard to Detect?

Cardiac amyloidosis is a life-threatening condition caused by abnormal protein deposits that accumulate in the heart muscle, potentially leading to heart failure if left undiagnosed . The disease is frequently underdiagnosed because its symptoms overlap with much more common heart conditions, making it easy for clinicians to miss during routine evaluations. Early detection is critical because timely intervention can meaningfully improve patient outcomes, yet the subtle patterns on an ECG that suggest amyloidosis often go unnoticed by human interpretation .

In April 2026, the U.S. Food and Drug Administration (FDA) granted clearance to Anumana's ECG-AI algorithm for cardiac amyloidosis, marking the first and only FDA-cleared algorithm designed specifically for this indication using standard 12-lead ECGs . This clearance represents a significant milestone because it enables clinicians to leverage technology already embedded in routine clinical workflows without requiring additional testing or specialized equipment.

How Does the AI Algorithm Work in Clinical Practice?

Anumana's algorithm analyzes ECG waveforms to detect patterns associated with cardiac amyloidosis that are often invisible to the human eye . By processing data from ECGs already obtained during standard cardiac evaluations, the software integrates directly into existing hospital and clinic workflows, helping clinicians identify at-risk patients and determine appropriate next steps for further evaluation. The algorithm was initially developed at Mayo Clinic and subsequently validated in a large, independent, multi-center study involving both ATTR and AL cardiac amyloidosis subtypes at major referral centers with deep expertise in amyloidosis diagnosis .

"Cardiac amyloidosis can be challenging to detect early, especially when its signs overlap with more common heart conditions. A tool that helps clinicians recognize suspicion of amyloidosis from a routine ECG could support earlier diagnosis and more timely next steps in care," said Martha Grogan, M.D., consultant in Cardiovascular Medicine at Mayo Clinic and co-principal investigator of the clinical study.

Martha Grogan, M.D., Consultant in Cardiovascular Medicine at Mayo Clinic

How to Integrate AI Cardiac Screening Into Your Healthcare System

• Assess Current ECG Workflows: Evaluate how your institution currently captures and interprets ECGs to identify integration points where the AI algorithm can be deployed without disrupting existing processes.
• Train Clinical Staff on AI Output: Ensure cardiologists, internists, and emergency medicine physicians understand how to interpret AI-generated risk assessments and when to order confirmatory testing such as echocardiography or cardiac imaging.
• Establish Referral Pathways: Create clear protocols for referring patients flagged by the algorithm to specialists with expertise in amyloidosis diagnosis and management to ensure timely intervention.
• Monitor Reimbursement Eligibility: Confirm that your institution's payers cover the AI-enabled software-as-a-medical-device (SaMD), as Anumana's cleared algorithms are currently eligible for reimbursement in the United States.

The validation study included 25,525 patients across four U.S. health systems, making it one of the largest independent evaluations of an ECG-based AI algorithm for a specific cardiac condition . This rigorous validation approach strengthens confidence in the algorithm's performance across diverse patient populations and clinical settings.

"What makes this work especially meaningful is the rigor of the validation. This ECG-AI algorithm was validated in a large multicenter study that included both ATTR and AL cardiac amyloidosis at major referral centers with deep expertise in amyloidosis diagnosis, supporting its potential to help identify patients earlier," stated Angela Dispenzieri, M.D., hematologist at Mayo Clinic and co-principal investigator of the clinical study.

Angela Dispenzieri, M.D., Hematologist at Mayo Clinic

What Does This Clearance Mean for the Broader AI Healthcare Landscape?

This FDA clearance builds on Anumana's growing portfolio of FDA-cleared ECG-AI algorithms, which also includes solutions for detecting low ejection fraction and pulmonary hypertension . The company is developing additional algorithms to further expand its portfolio, with the goal of making a single ECG test increasingly valuable by enabling detection of multiple cardiovascular conditions from one routine test. Maulik Nanavaty, CEO of Anumana, emphasized this strategic direction, noting that each new clearance represents progress toward a more comprehensive diagnostic tool.

"Each of our FDA-cleared algorithms addresses a specific and frequently missed cardiovascular condition, and cardiac amyloidosis represents an important addition to that portfolio. The more conditions we can identify from a single ECG, the more valuable the test becomes in clinical practice," explained Maulik Nanavaty, CEO of Anumana.

Maulik Nanavaty, CEO of Anumana

The algorithm's ability to detect cardiac amyloidosis with 78.9% sensitivity and 91.2% specificity may support more efficient use of confirmatory testing, reducing unnecessary advanced imaging studies while ensuring that at-risk patients receive timely specialist evaluation . This efficiency gain could translate to faster diagnoses, reduced healthcare costs, and improved outcomes for patients with this serious but treatable condition. The FDA previously granted Anumana's cardiac amyloidosis algorithm Breakthrough Device Designation and selected it among the first 15 devices in the FDA's Total Product Life Cycle Advisory Program pilot, recognizing the potential clinical significance of this innovation .

As healthcare systems continue to adopt AI-driven diagnostic tools, the cardiac amyloidosis algorithm demonstrates how artificial intelligence can address a critical gap in clinical practice: detecting rare but serious conditions that human interpretation routinely misses. By leveraging data already collected during routine care, the technology removes barriers to adoption and positions early detection as an achievable goal for hospitals and clinics of all sizes.