Sleep apnea identification using ecg and ppg signals involving neural network

Abstract

Sleep apnea is one of the hypothetically severe sleep disorders that often stops and begins to breathe. The undiagnosed sleep apnea can be very serious, resulting in fast decreases in blood oxygen levels, during which developed insulin resistance and type 2 diabetes may increase. Several people do not know their condition, though. Typical for sleep diagnosis is an overnight polysomnography (PSG) in a dedicated sleep laboratory. Since these exams are expensive and beds are restricted due to the need for trained employees to evaluate the full. An automatic detection technique would allow faster diagnosis and more patients to be analyzed. Hence detection of sleep apnea is compulsory so that it could be treated. This study established an algorithm that signaled a short-term electrocardiographic event extraction (ECG) and combined neural network methodologies for automatic sleep apnea detection. This study provides users with visual experiences through visual parameters such as HRV measurements, Poincare plot, global and local return map. This enables the doctor evaluate whether or not the individual is suffering from sleep apnea.