The principle of the image-based AFib discriminating system is based on the consistency that irregular cardiac cycles can both be detected on the waveforms of electrocardiography and rPPG. The quantity of the blood varies from time to time is captured by a general camera. Signals from RGB channels are then synthesized through the core algorithm to eliminate noise and generate stable rPPG signals. The processed signals are then classified as AFib or not by a sample-size model. According to the IRB evaluation in En Chu Kong Hospital, the AFib can be well detected with an accuracy of 97.1%.
The major breakthrough technology of video-based atrial fibrillation detection is only with a general camera and without an EKG or wearable device. This technology can be integrated into personal devices, such as smartphones, tablets, or PC. Through a camera on personal devices to capture the face image and then detect whether the atrial fibrillation happened or not.
The IRB result in the En Chu Kong Hospital revealed that the proposed new technology is not only more convenient to use but has high detection accuracy even matching the existing solutions in diagnosing atrial fibrillation.
Atrial fibrillation is the most frequent cardiac arrhythmia. 17% of patients have no obvious symptoms, and three-quarters of patients do not know that they are sick at all before diagnosis. Therefore, atrial fibrillation is very difficult to detect. Atrial fibrillation is often discovered after a stroke happened. The technology "Contact-Free Screening for Cardiac Pulse and Atrial Fibrillation Detection" can provide ordinary people, sub-healthy groups, and patients with atrial fibrillation for their daily health records, or follow-up disease records after surgery.
線上展網址:
https://tievirtual.twtm.com.tw/iframe/015bedfd-af0b-46b0-9dfa-5d396f5bedd2?group=23bfb1fa-dd5b-4836-81a1-4a1809b1bae5&lang=en
Plant-Based Milk Beverage Blending Platform and Integrated Application in the Industry Chain
Intelligent Quick Structural Safety Screening System based on Neural Network Entropy and Convolution Neural Network
Integrated Multiple Machine Learning and Deep Learning Algorithms to Construct Prediction Model of Incident Cardiac Dysrhythmia and Coronary Heart Disease
Cholesteric Liquid Crystal AI Electric-Optical AIoT System for Environmental Detection, Medical Test, Epidemic Prevention and Green energy applications
Technology maturity:Prototype
Exhibiting purpose:Technology transactions、Patent transactions、Product promotion、Display of scientific results
Trading preferences:Technical license/cooperation、Negotiate by self
Coming soon!