AUTHOR=Xiong Xin , Wang Aikun , He Jianfeng , Wang Chunwu , Liu Ruixiang , Sun Zhiran , Zhang Jiancong , Zhang Jing 

TITLE=Application of LightGBM hybrid model based on TPE algorithm optimization in sleep apnea detection

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 18 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2024.1324933

DOI=10.3389/fnins.2024.1324933

ISSN=1662-453X

ABSTRACT=Sleep apnea syndrome (SAS) is a serious sleep disorder. Early detection of sleep apnea not only reduces treatment costs but also saves lives. Conventional polysomnography (PSG) is widely regarded as the gold standard diagnostic tool for sleep apnea. However, this method is expensive, time-consuming and inherently disrupts sleeping. Recent studies have demonstated that ECG analysis is a simple and effective diagnostic method for sleep apnea, which can help physicians to diagnose and reduce patient suffering. To this end, this paper proposes a LightGBM hybrid model based on ECG signals for efficient detection of sleep apnea. Firstly, the improved Isolation Forest algorithm is introduced to remove abnormal data and solve the imbalance data sample problem. Afterwards, the parameters of LightGBM algorithm are optimised by the improved Tree-structured Parzen Estimator algorithm (TPE) to determine the best parameter configuration of the model. At last, the fusion model TPE_OptGBM is used to detect sleep apnea. In the experimental phase, we validated the model based on the sleep apnea ECG database provided by Phillips-