Four New Studies Demonstrate that Viz.ai Finds New Patients with Hypertrophic Cardiomyopathy Earlier When Embedded into the Clinical Workflow
Real-world evidence to be presented at the
This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20250326744258/en/

Viz HCM: Patient card displaying key clinical information, including ECG and echocardiographic findings.
“It’s exciting to see the growing real-world evidence showing how AI-enhanced ECG analysis can play a pivotal role in identifying new patients with hypertrophic cardiomyopathy,” said
Viz HCM uses artificial intelligence to analyze all 12-lead electrocardiograms (ECGs) at the point of care from across a health system to identify suspected HCM cases, notify cardiology care teams and increase the likelihood that patients get the right follow-up and diagnosis. The Viz HCM module was granted
“The findings from our study highlight the potential of AI-based ECG analysis to identify hypertrophic cardiomyopathy well before a clinical diagnosis is made,” said
The following clinical studies are being presented at ACC:
-
“Real-World Artificial Intelligence–Based Electrocardiographic Analysis to Diagnose Hypertrophic Cardiomyopathy" evaluated the performance of Viz HCM for detecting HCM at the
Cleveland Clinic . The study, published in JACC: Clinical Electrophysiology and set to be presented live at ACC 2025, demonstrated that Viz HCM achieved a high degree of accuracy in detecting HCM. The AI-ECG successfully identified 574 HCM patients, and 691 were determined to have an alternate clinically relevant diagnosis, highlighting Viz HCM’s value for more effective disease detection. -
“A Retrospective Assessment of Delays in HCM Diagnosis and the Potential Impact of an Artificial-Intelligence-assisted Electrocardiogram Screening” used Viz HCM to predict HCM from serial 12-lead ECGs first and after which, the confirmatory diagnosis was assessed by expert clinicians at an
HCM Center of Excellence . Results indicate that Viz HCM could have identified HCM patients from an ECG earlier. Among the 155 patients with AI-based ECG identifications of HCM, 20.0% could have been diagnosed more than one year prior, 12.9% more than 3 years prior, 9.0% more than 5 years prior, and 4.5% more than 10 years prior. - “A Multicenter, Prospective Cohort Pilot Study on the Clinical Implementation and Utilization of an AI-based ECG Tool for HCM Detection and Care Coordination” evaluated the implementation of Viz HCM into the clinical workflow to detect HCM and triage patients to the right specialist. Out of 145,848 screened patients, 3% were flagged for suspected HCM and directed to the appropriate specialist. A total of 217 patients met the study criteria and were enrolled, representing a diverse population—23% Black, 9.2% Asian, and 12.4% Hispanic or Latino. Out of the 217 patients, 17 new HCM patients were identified, including 8 inpatient and 9 outpatient diagnoses. The findings suggest that AI-assisted ECG screening can be successfully integrated into clinical workflows to aid in improved HCM identification and care coordination.
- “Machine-learning Algorithm for the Detection of Hypertrophic Cardiomyopathy from Standard Electrocardiogram” evaluated the performance of the Viz HCM algorithm in identifying HCM confirmed by cardiac MRI. The study found that Viz HCM identified 87 of 156 patients with HCM, rendering its sensitivity 56%, specificity 100%, and positive predictive value of 100%.
“At Viz.ai, we are committed to integrating AI into clinical workflows to ensure the reliable detection and timely triage of underdiagnosed conditions like HCM, ultimately enhancing care and outcomes for more patients,” said
To learn more about Viz.ai, visit us at ACC at booth 11055.
About Viz.ai, Inc.
Viz.ai is the pioneer in the use of AI algorithms and machine learning to increase the speed of diagnosis and care across 1,700+ hospitals and health systems in the
View source version on businesswire.com: https://www.businesswire.com/news/home/20250326744258/en/
Media Contacts
carolyn.jones@viz.ai
daniel.yunger@kekstcnc.com
Source: Viz.ai