[1H4-J-13] AI application: medicine

[1H4-J-13-03] Sleep Apnea Detection by Combining Long Short-Term Memory and Heart Rate Variability

〇Ayako Iwasaki¹, Chikao Nakayama², Koichi Fujiwara^2,3, Yukiyoshi Sumi⁴, Masahiro Matsuo⁴, Manabu Kano², Hiroshi Kadotani⁵ (1. Faculty of Medicine, Kyoto University, 2. Graduate School of Informatics, Kyoto University, 3. Graduate School of Engineering, Nagoya University, 4. Department of Psychiatry, Shiga University of Medical Science, 5. Department of Sleep and Behavioral Sciences, Shiga University of Medical Science)

Keywords:Sleep, Sleep Apnea Syndrome, Heart Rate Variability, Wearable Device, Long Short-Term Memory

Sleep apnea syndrome (SAS) is a prevalent disorder which causes daytime fatigue with increased risk of cardiovascular diseases. A large number of patients are undiagnosed and untreated partly because of the difficulty in performing its gold standard test, polysomnography (PSG). In this research, we propose a simple screening method utilizing heart rate variability (HRV) and long short-term memory (LSTM) which is a kind of the neural network techniques. The result of applying this algorithm to clinical data demonstrates that it can discriminate between patients and healthy people with sensitivity (100%) and specificity (100%).