Atrial fibrillation prediction model and system

Abstract

The present invention provides an atrial fibrillation prediction system including an electrocardiogram acquisition unit and a non-transitory machine-readable medium. The non-transitory machine-readable medium stores a program, and is configured to obtain a prediction result when the program is executed by a processing unit. The program includes a reference database acquisition module, a referencefeature selection module, a training module, a target feature selection module, and a comparison module. In this way, the atrial fibrillation prediction system can be used to predict the incidence ofstroke in a subject.

Description

technical field [0001] The invention relates to a medical information analysis model and system, in particular to an atrial fibrillation prediction model and an atrial fibrillation prediction system. Background technique [0002] Atrial fibrillation (atrial fibrillation) is a condition in which the heart beats irregularly and often too fast, up to 350 beats per minute, due to a malfunction in the production of rhythmic signals in the heart. Atrial fibrillation is the most common abnormal heart rhythm. On average, 1 in 100 people in the whole population suffers from atrial fibrillation. The proportion of atrial fibrillation increases with age. Four in 100 people over the age of 60 suffer from atrial fibrillation, and one in 10 people over the age of 80 suffers from atrial fibrillation. In 2010, an estimated 33.5 million people worldwide suffered from atrial fibrillation, and there may be many potential patients who are undiagnosed because they are asymptomatic. In 2050, the...

AI Technical Summary

Problems solved by technology

[0004] The electrocardiogram provides information on atrial fibrillation, such as the frequency and type of attacks in a day, but the data is huge and cannot be analyzed step by step manually. Therefore, there is a lack of conventional technology that can efficiently

Images