The startup develops deep learning algorithms that analyze electrocardiogram signals to detect silent cardiac conditions, such as diastolic dysfunction and low ejection fraction, enabling early diagnosis and preventive therapy. By utilizing a foundational model that requires significantly less data for training, the technology enhances diagnostic accuracy and streamlines clinical workflows, addressing the limitations of conventional cardiac diagnostics.
Funding
$100K raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
FVFounders
Product
Problem
A significant percentage of heart attacks are silent, and many adults are projected to develop cardiovascular disease. Traditional cardiac diagnostic methods are often slow and expensive, hindering early detection of critical conditions.
Solution
Carelogix offers a suite of AI-powered algorithms that analyze electrocardiogram (ECG) signals to detect silent cardiac conditions, such as diastolic dysfunction, BNP elevation, and low ejection fraction. The platform utilizes a foundational model called HridAI, which requires less data for training, enhancing diagnostic accuracy and streamlining clinical workflows. The technology enables early diagnosis and initiation of preventive therapies, providing an accessible ECG-AI panel for improved readability and physician understanding. Carelogix's algorithms are generalizable across diverse datasets and populations, with ongoing clinical validation.
Target Audience
The primary target audience includes healthcare providers and institutions seeking early and accurate detection of silent cardiac conditions, as well as ECG manufacturers looking to integrate AI-powered diagnostics into their devices.
Features
- AI-powered detection of diastolic dysfunction, BNP elevation, low ejection fraction, right ventricular dysfunction, ventricular hypertrophy, atrial enlargement, left ventricular systolic volume, and left ventricular diastolic volume
- HridAI foundational model requiring only 10% of the data needed by industry-standard models
- Enhanced explainability, marking biologically relevant regions of the ECG for better physician understanding
- Superior AUROC performance compared to current gold standards and competitors
- Generalizable across diverse datasets and populations
- Deployed in collaboration with ECG manufacturers