The first large-scale study to show a noninvasive sensor and AI algorithm with comparable performance to implanted sensors in estimating cardiac filling pressure
Cardiosense, a medical AI company transforming the management of cardiovascular disease, today announced the publication of results from its SEISMIC-HF I study in the Journal of the American College of Cardiology: Heart Failure (JACC: Heart Failure). The study demonstrates the ability of Cardiosense's novel machine learning (ML) algorithm to noninvasively estimate pulmonary capillary wedge pressure (PCWP) in patients with heart failure with reduced ejection fraction (HFrEF).
The prospective, multi-center SEISMIC-HF I study enabled the development and evaluation of Cardiosense’s ML algorithm in 310 patients with HFrEF undergoing right heart catheterization (RHC). The study population enrolled a diverse set of participants with demographics and clinical characteristics reflective of the broader population with HFrEF to ensure ML models generalize across all patients. Patients enrolled in the study wore the CardioTag device–a multi-modal sensor that captures seismocardiogram (SCG), electrocardiogram (ECG), and photoplethysmogram (PPG) signals–on their sternum during the RHC procedure used to provide gold standard assessment of an individual’s PCWP.
Key findings from the 15-site study show that the device:
- Estimated absolute PCWP values with accuracy on par with implantable hemodynamic sensors, suggesting that Cardiosense’s noninvasive, AI-enabled technology has the potential to increase access to hemodynamic-guided care.
- Demonstrated a consistent performance across sex, race, ethnicity, and body mass index.
- Additional analysis available in the full manuscript, titled “Noninvasive Pulmonary Capillary Wedge Pressure Estimation in Heart Failure Patients With the Use of Wearable Sensing and AI,” available now in JACC: Heart Failure.
"Heart failure management remains one of our most significant clinical challenges and most promising opportunities to directly impact patient outcomes," said Liviu Klein, MD, MS, Section Chief of Advanced Heart Failure, Mechanical Circulatory Support, Pulmonary Hypertension, and Heart Transplant at UCSF, lead author on the study and lead clinical advisor for Cardiosense. "We know that hemodynamic-guided care reduces hospital readmissions and mortality, yet routine cardiac pressure measurements remain inaccessible due to cost and risk. SEISMIC-HF I is a critical advancement toward the quest for noninvasive technology delivering on the promise of fast, safe, and accessible pressure-guided heart failure management.”
Initial results from Cardiosense's SEISMIC-HF I study were presented as Late-Breaking Science at the American Heart Association's 2024 Scientific Sessions.
“This analysis marks a real milestone in our journey to revolutionize heart failure management with our proprietary AI technology that leverages noninvasive sensor data to deliver critical information on cardiac function,” said Omer Inan, PhD, Cardiosense Co-founder and Chief Scientific Officer. “The results are a culmination of more than a decade of research and a testament to the cross-disciplinary collaboration from our team of medical and clinical experts, data scientists, and engineers.”
For the latest news and information, follow Cardiosense on X and LinkedIn, or visit: www.cardiosense.com.
About Cardiosense
Cardiosense is a leading medical AI company redefining how we detect, monitor, and manage cardiac disease. Built on over a decade of clinical and scientific research, the company is developing novel wearable sensors and machine learning algorithms that translate raw physiological signals into clinically actionable parameters to detect early signs of cardiac disease, guide personalized therapy, and improve patient outcomes.
The CardioTag device is an investigational device limited by federal law to investigational use. The CardioTag device is not available for commercial distribution.
PCWP Analysis Software is an investigational device limited by federal law to investigational use. PCWP Analysis Software is not available for commercial distribution.
View source version on businesswire.com: https://www.businesswire.com/news/home/20250624881106/en/
Contacts
Eric Schudiske
eric@s2spr.com
