Behnaz Ghoraani

Abstract

Atrial fibrillation is the most common heart rhythm disorder and affects 2.3 million Americans. Ectopic beats from the pulmonary veins may trigger atrial fibrillation. To resolve this, a non-pharmacological ablation therapy called pulmonary vein isolation, which uses radiofrequency energy to cauterize the atrial tissue in the pulmonary vein's antrum, terminates atrial fibrillation and restores sinus rhythm. Unfortunately, this therapy remains suboptimal with long-term success rates of only 40% to 60%. The main issue is that this therapy fails to eliminate atrial fibrillation drivers outside the pulmonary veins. Their targeted elimination is key to improving outcome after atrial fibrillation ablation. Detection and ablation of the rotors has a very significant impact on the successful termination of atrial fibrillation.

The technology is a data-driven probabilistic algorithm that guides the movement of a conventional multi-pole diagnostic catheter in the atria and uses the recorded electrograms at each site to gradually develop a mask, which can reveal the location of the atrial fibrillation source in the atria. Thus, this system can be used to develop an atrial fibrillation ablation target map. The ablation target map reveals the locations of any atrial fibrillation sources in the atria. The method can be a software add-on to the 3-D mapping system in any of the existing atrial fibrillation mapping systems.

FAU is seeking partners to advance this technology into the marketplace through licensing or development partnerships.

Benefit

Market Application

Publications

Atrial fibrillation source area probability mapping using electrogram patterns of multipole catheters

Abstract

Cognitive impairments such as Alzheimer's disease (AD) and mild cognitive impairment (MCI) are major public health challenges, yet early detection remains difficult. Current solutions, including neuropsychological assessments, brain imaging (MRI, PET), and blood-based biomarker tests, are expensive, invasive, and require specialized facilities and personnel. These methods often result in late diagnoses, limited accessibility in primary care or community settings, and high patient burden. As a result, millions of older adults remain undiagnosed until disease progression has already compromised treatment effectiveness.

Researchers at Florida Atlantic University have developed a novel, non-invasive system that uses standard cameras (such as smartphones or tablets) combined with advanced computer vision and machine learning algorithms to detect early signs of Alzheimer's disease and related cognitive impairments through gait and balance analysis. Unlike current diagnostic methods, this technology requires no specialized facilities, expensive imaging equipment, or body-worn sensors. The system has demonstrated up to 90% accuracy in distinguishing patients with cognitive impairment from healthy individuals in clinical studies. The technology is currently at the proof-of-concept stage, supported by experimental validation with patient populations, and is positioned for further development toward clinical and commercial applications.

FAU seeks to advance this innovation into the marketplace through licensing or development partnerships.

Benefit

Market Application

Publications

Mild Cognitive Impairment Detection Through Gait Analysis and Standard Cameras

Human Pose Estimation and Gait Analysis with Convolutional Neural Networks for Alzheimer's Disease Detection