Medical AI company
Anumana
ECG-AI company founded by nference and Mayo Clinic, offering FDA-cleared algorithms that detect heart disease from a standard 12-lead ECG.
Company overview
Anumana develops AI algorithms that analyze standard 10-second, 12-lead ECGs to detect signs of heart disease such as low ejection fraction, cardiac amyloidosis and pulmonary hypertension. The company was founded in 2021 by nference and Mayo Clinic and announces news from Cambridge, Massachusetts.
- Headquarters
- Cambridge, United States
- Founded
- 2021 source
- Company type
- AI Technology Developer
In its own words: “Anumana is a new AI-driven health technology company from nference, developing and delivering ECG algorithms enabling early diagnosis and intervention.” source
AI products and platforms
- ECG-AI LEFAI-powered
Algorithm that detects low left ventricular ejection fraction from a standard ECG.
Product page ↗ - ECG-AI cardiac amyloidosis algorithmAI-powered
Algorithm for detecting cardiac amyloidosis from a 12-lead ECG.
Product page ↗ - ECG-AI pulmonary hypertension algorithmAI-powered
Algorithm for early detection of pulmonary hypertension from ECG.
Product page ↗
Technology categories
Clinical applications
- ECG-based disease detection
- cardiology screening
Markets served
- United States
Relationships
Relationships are shown as stated on the cited page; the other party may not confirm them.
Regulatory information
- ECG-AI LEF FDA cleared (K250652) source
- FDA clearance for ECG-AI cardiac amyloidosis algorithm and for ECG-AI pulmonary hypertension algorithm (company announcements) source
As stated by the company or the cited regulator page. Authorisation is specific to a product, version and market; confirm the current status with the company and the regulator. About medical device regulation
Official sources
Last verified 29 October 2026 against the sources above.
Questions about Anumana
Does Medical AI have to explain how it reaches its outputs?
Not always in a technical sense, but transparency about the product is increasingly expected. Many machine learning models cannot give a simple step-by-step reason for each output, so regulators focus on clear information for users: intended use, inputs, how the model was developed and tested, performance, and known limitations.
In the US, one of the criteria for clinical decision support to fall outside device regulation is that a healthcare professional can independently review the basis for its recommendations. FDA has also published transparency principles for machine learning devices with Health Canada and MHRA.
For buyers, a vendor's ability to document how its model works and where it fails is often more useful than heat maps or confidence scores alone.
How is AI used with ECGs from wearables and remote monitors?
AI is used to screen large volumes of ECG data from patches, wearables and remote monitors, flagging possible arrhythmias or recordings that need clinician review. This helps manage the large amount of data produced by continuous monitoring.
Important distinctions for buyers:
- A consumer feature on a wearable and a clinical-grade analysis service can have very different intended uses and authorizations.
- Authorization often covers specific recording hardware, leads and populations.
- Signal quality and motion artifacts affect results.
In the US, software that analyzes physiological signals does not meet the criteria for non-device CDS. Confirm each product's status, and check how alerts are routed to clinicians and documented.
What is automation bias, and why does it matter for clinical AI?
Automation bias is the tendency of people to over-rely on a suggestion from an automated system, either following an incorrect output or missing something because the system did not flag it.
FDA's Clinical Decision Support Software guidance (issued January 2026) discusses automation bias and notes it increases in urgent situations where there is not enough time to consider other information. This is one reason FDA does not consider software intended for critical, time-sensitive decisions to meet the criteria for non-device CDS.
Organizations reduce automation bias through user training, clear display of the basis and limits of an output, workflows that keep independent clinical review, and monitoring of how the tool is actually used.