Diagnostics & imaging AI · ECG-AI heart disease detection
Anumana
Anumana is a Cambridge, Massachusetts company founded by nference and Mayo Clinic whose FDA-cleared ECG-AI software reads a standard 12-lead ECG to flag patients who may have low ejection fraction, pulmonary hypertension, or cardiac amyloidosis.
Strong fit
- Health systems that run high volumes of 12-lead ECGs in primary care and cardiology
- Programs that want earlier heart failure detection without new hardware
- Hospitals that want AI ECG analysis with CPT codes and a CMS payment rate
Weak fit
- Clinics that rarely order ECGs
- Buyers looking for a consumer wearable
- Sites that cannot connect AI results to their ECG management system or EHR
Bottom line
Anumana reads signals in a routine 12-lead ECG that clinicians cannot see and flags patients who may have low ejection fraction, pulmonary hypertension, or cardiac amyloidosis. It fits health systems that already run many ECGs and want to find heart failure earlier. The value depends on a clear follow-up path, usually an echocardiogram, for the patients it flags.
Score breakdown
Weights: Outcomes 35% · Product 30% · Implementation 20% · Pricing clarity 15%.
Anumana sells to health systems, cardiology groups, and primary care networks that already record many 12-lead ECGs. Its ECG-AI LEF algorithm looks at a standard 10-second tracing and estimates whether the patient may have low ejection fraction, a sign that the heart is pumping weakly and a common early marker of heart failure. Clinicians use the result to decide who should get an echocardiogram. The company was founded by nference and Mayo Clinic, and its about page reports 90.2% sensitivity and 85.1% specificity for low ejection fraction.
The closest alternative is Eko Health, whose digital stethoscopes run FDA-cleared AI that flags low ejection fraction during a routine exam. Eko requires new hardware at the bedside, while Anumana runs on ECGs a hospital already records. Echocardiography AI tools such as Ultromics work later in the same care path, after a patient has been sent for an echo. Pricing follows CPT billing codes; CEO Maulik Nanavaty told Pulse 2.0 that CMS set a $128.90 payment rate for ECG-AI LEF effective January 2025.
The product line has grown beyond low ejection fraction. Anumana now has FDA-cleared algorithms for pulmonary hypertension and, as of April 2026, cardiac amyloidosis, a condition caused by protein deposits in the heart that is often found late. In a validation study of 25,525 patients across four U.S. health systems, the amyloidosis model showed 78.9% sensitivity and 91.2% specificity.
Commercial deployment of ECG-AI LEF began in 2025, and Anumana's revenue is an estimated $5 million a year. Nanavaty, a former Boston Scientific executive, became CEO in October 2023.
The main limit is follow-through. An AI flag only helps if the care team knows who orders the echocardiogram and who reads it, and clinics with few ECGs will see few alerts. Results also need to reach the clinician inside the ECG system or EHR.
What clinicians and buyers say
What people like
"A normal-looking ECG can still point to low ejection fraction, and the AI flag changes who we send for an echo."
"The CPT codes and the CMS payment rate made the budget conversation easier than for most AI tools."
What people don't like
"If every borderline ECG fires an alert and nobody owns the follow-up, the flags get ignored."
"Without a clean connection to our ECG system, clinicians never see the result."
Where customer reviews couldn't be found, our analysts attempted to give a voice to buyer sentiment, drawing on real information from review sites, forums, and product documentation.
Based on: Anumana about page, cardiac amyloidosis clearance announcement, and Pulse 2.0 interview with Maulik Nanavaty.
Competitor landscape
| Vendor | Overall | Ease of implementation |
|---|---|---|
| Anumana | 7.5 | 6.6 |
| Eko Health | 7.9 | 8.6 |
Pricing
| Item | Detail |
|---|---|
| Model | Software license for ECG-AI algorithms that run on standard 12-lead ECGs. Health system contract terms are not published. |
| Reimbursement | Category III CPT codes 0764T and 0765T were issued in 2023, and CMS set a hospital outpatient payment of $128.90 for ECG-AI LEF effective January 2025. |
| What drives cost | ECG volume, the number of algorithms licensed, and integration with the ECG management system and EHR. |
Leadership
Recent news
- April 2026: Anumana received FDA clearance for its ECG-AI cardiac amyloidosis algorithm, the first cleared for that use on a standard 12-lead ECG.
Methodology
| Weight | Factor | What it measures |
|---|---|---|
| 35% | Customer outcomes | Whether buyers get measurable operational or clinical-workflow results after go-live |
| 30% | Product | Capability depth, reliability, and fit for the job the category buys |
| 20% | Implementation | How hard it is to stand up, integrate, train, and stabilize |
| 15% | Pricing clarity | Whether a buyer can model total cost without a mystery quote |
| Label | Meaning |
|---|---|
| Highly recommend | Strong outcomes and product with manageable caveats |
| Recommend | Solid fit for the right buyer; know the tradeoffs |
| Conditional | Only with a specific use case or heavy caveats |
| Not recommended | Avoid for most buyers in this category |
Read our full methodology for how we weight scores and assign recommend labels.