Anumana, Inc.
Anumana is an AI-driven health technology company from nference, dedicated to building and commercializing AI solutions to improve patient care throughout the cardiac care continuum. Their mission is to unlock the electrical signals of the heart to enable earlier and improved diagnosis, treatment, and interventions in cardiology, leveraging cutting-edge AI and deep electrophysiological data. They develop investigational medical devices, including FDA-cleared algorithms for early disease detection, and collaborate with leading clinical experts and institutions to advance cardiac care.
Industries
Nr. of Employees
medium (51-250)
Patents
System and method for visualization of vectorcardiograms for ablation procedures
US-12329463-B1
View DetailsApparatus and method for generating a quality diagnostic of ECG (electrocardiogram) data
US-12329543-B1
View DetailsSystems and methods for diagnosing a health condition based on patient time series data
US-12327638-B2
View DetailsSystems and methods for standardization of electrocardiogram signal images
US-12327343-B1
View Details
System and method for visualization of vectorcardiograms for ablation procedures
US-12329463-B1
View DetailsApparatus and method for generating a quality diagnostic of ECG (electrocardiogram) data
US-12329543-B1
View DetailsSystems and methods for diagnosing a health condition based on patient time series data
US-12327638-B2
View DetailsSystems and methods for standardization of electrocardiogram signal images
US-12327343-B1
View DetailsProducts
AI algorithm for detection of low left ventricular ejection fraction (LEF)
A regulated software algorithm that analyzes standard 12-lead ECGs to screen for low left ventricular ejection fraction, trained on large paired ECG–echocardiogram datasets and validated in multi-site studies.
Web-based ECG Viewer (zero-footprint clinical dashboard)
A secure, web-based dashboard that displays patient ECG waveforms and history, real-time AI results, and workflow tools integrated into the EHR.
Peri-procedural electrophysiology decision support solution (development)
In-development software intended to provide intra-procedural analytics and visualization for structural heart, interventional cardiology, and electrophysiology procedures.
AI algorithm for detection of low left ventricular ejection fraction (LEF)
A regulated software algorithm that analyzes standard 12-lead ECGs to screen for low left ventricular ejection fraction, trained on large paired ECG–echocardiogram datasets and validated in multi-site studies.
Web-based ECG Viewer (zero-footprint clinical dashboard)
A secure, web-based dashboard that displays patient ECG waveforms and history, real-time AI results, and workflow tools integrated into the EHR.
Peri-procedural electrophysiology decision support solution (development)
In-development software intended to provide intra-procedural analytics and visualization for structural heart, interventional cardiology, and electrophysiology procedures.
Services
Design and execution support for retrospective and prospective clinical studies, including multi-site and randomized pragmatic trials to validate AI algorithms.
Integration of AI outputs and ECG Viewer dashboards into existing EHRs and ECG information management systems for point-of-care access.
Provisioning of de-identified longitudinal multi-modal datasets and data engineering to support model development, validation, and translational research.
Development and deployment support for low-latency, intra-procedural software tools aimed at assisting decision-making during electrophysiology procedures.
Design and execution support for retrospective and prospective clinical studies, including multi-site and randomized pragmatic trials to validate AI algorithms.
Integration of AI outputs and ECG Viewer dashboards into existing EHRs and ECG information management systems for point-of-care access.
Provisioning of de-identified longitudinal multi-modal datasets and data engineering to support model development, validation, and translational research.
Development and deployment support for low-latency, intra-procedural software tools aimed at assisting decision-making during electrophysiology procedures.
Expertise Areas
- AI-enabled diagnostic electrocardiography
- Clinical trial design and pragmatic study execution
- Regulatory compliance and medical device (SaMD) commercialization
- Electrophysiology peri-procedural decision support
Key Technologies
- Deep learning for ECG/EGM analysis
- Electrocardiography (ECG) signal processing
- Electrogram (EGM) analytics
- Real-world evidence (RWE) platforms and EHR de-identification
News & Updates
This study demonstrates that AI applied to routine ECGs can identify asymptomatic left ventricular dysfunction with high accuracy, achieving an AUC of 0.93, sensitivity of 86.3%, and specificity of 85.7%. In patients without current dysfunction, a positive AI screen indicated a fourfold increase in detection.
This study assessed the effects of gender-affirming hormone therapy on ECG patterns in transgender individuals using an AI algorithm. Among transgender women, GAHT significantly lowered the probability of a male ECG pattern, while among transgender men, it increased the probability.
This study evaluated echocardiographic characteristics and mortality risk in patients with false positive results from an AI-based ECG model that detects low ejection fraction. FP patients had more echocardiographic abnormalities than true negatives, with 97% showing some abnormalities.
This study in Nigeria investigated AI-guided screening for diagnosing left ventricular systolic dysfunction in pregnant and postpartum women. Participants were randomized to AI screening or usual care.
This study assessed if an AI-enhanced ECG model could predict survival in patients with cardiac amyloidosis. The AI score was significantly associated with increased risk of death.
This study demonstrates that AI applied to routine ECGs can identify asymptomatic left ventricular dysfunction with high accuracy, achieving an AUC of 0.93, sensitivity of 86.3%, and specificity of 85.7%. In patients without current dysfunction, a positive AI screen indicated a fourfold increase in detection.
This study assessed the effects of gender-affirming hormone therapy on ECG patterns in transgender individuals using an AI algorithm. Among transgender women, GAHT significantly lowered the probability of a male ECG pattern, while among transgender men, it increased the probability.
This study evaluated echocardiographic characteristics and mortality risk in patients with false positive results from an AI-based ECG model that detects low ejection fraction. FP patients had more echocardiographic abnormalities than true negatives, with 97% showing some abnormalities.
This study in Nigeria investigated AI-guided screening for diagnosing left ventricular systolic dysfunction in pregnant and postpartum women. Participants were randomized to AI screening or usual care.
This study assessed if an AI-enhanced ECG model could predict survival in patients with cardiac amyloidosis. The AI score was significantly associated with increased risk of death.