EEG Feature Engineering for Machine Learning-Based CPAP Titration Optimization in Obstructive Sleep Apnea

다국어 초록 (Multilingual Abstract)

Obstructive sleep apnea (OSA) is one of the most prevalent sleep disorders that can lead to serious consequences, including hypertension and/or cardiovascular diseases, if not treated promptly. Continuous positive airway pressure (CPAP) is widely recognized as the most effective treatment for OSA, which needs the proper titration of airway pressure to achieve the most effective treatment results. However, the process of CPAP titration can be time-consuming and cumbersome. There is a growing importance in predicting personalized CPAP pressure before CPAP treatment. The primary objective of this study was to optimize the CPAP titration process for obstructive sleep apnea patients through EEG feature engineering with machine learning techniques. We aimed to identify and utilize the most critical EEG features to forecast key OSA predictive indicators, ultimately facilitating more precise and personalized CPAP treatment strategies. Here, we analyzed 126 OSA patients' PSG datasets before and after the CPAP treatment. We extracted 29 EEG features to predict the features that have high importance on the OSA prediction index which are AHI and SpO2 by applying the Shapley Additive exPlanation (SHAP) method. Through extracted EEG features, we confirmed the six EEG features that had high importance in predicting AHI and SpO2 using XGBoost, Support Vector Machine regression, and Random Forest Regression. By utilizing the predictive capabilities of EEG derived features for AHI and SpO2, we can better understand and evaluate the condition of patients undergoing CPAP treatment. The ability to predict these key indicators accurately provides more immediate insight into the patient’s sleep quality and potential disturbances. This not only ensures the efficiency of the diagnostic process but also provides more tailored and effective treatment approach. Consequently, the integration of EEG analysis into the sleep study protocol has the potential to revolutionize sleep diagnostics, offering a time-saving, and ultimately more effective evaluation for patients with sleep-related disorders.

참고문헌 (Reference)

1 이지은 ; 유선국, "수면 단계에 따른 심전도 신호의 상관관계 분석" 한국멀티미디어학회 21 (21): 1370-1378, 2018

2 김승수 ; 양광익, "비만 폐쇄수면무호흡 환자에서 기계학습을 통한 적정양압 예측모형" 대한수면연구학회 15 (15): 48-54, 2018

3 T. Chen, "Xgboost : A scalable tree boosting system" 785-794, 2016

4 B. Hjorth, "Time domain descriptors and their relation to a particular model for generation of eeg activity" 3-8, 1975

5 R. Staats, "The importance of sleep fragmentation on the hemodynamic dipping in ´obstructive sleep apnea patients" 11 : 104-, 2020

6 M. Albayrak, "The detection of an epileptiform activity on EEG signals by using data mining process" 4 (4): 1-12, 2009

7 C. Cortes, "Support-vector networks" 20 : 273-297, 1995

8 K. A. Hutchinson, "Sleep quality among burn survivors and the importance of intervention : a systematic review and meta-analysis" 43 (43): 1358-1379, 2022

9 Yu-Jin Lee ; Jong Won Kim ; Yu-Jin G. Lee ; Do-Un Jeong, "Sleep EEG Characteristics in Young and Elderly Patients with Obstructive Sleep Apnea Syndrome" 대한신경정신의학회 13 (13): 217-221, 2016

10 C. E. Sullivan, "Reversal of obstructive sleep apnoea by continuous positive airway pressure applied through the nares" 1 (1): 862-865, 1981

11 L. Breiman, "Random forests" 45 : 5-32, 2001

12 김여진 ; 양지선 ; 임도형 ; 오유란, "Prediction of Cognitive Ability Utilizing a Machine Learning approach based on Digital Therapeutics Log Data" 한국인터넷방송통신학회 12 (12): 17-24, 2023

13 F. A. Grewe, "Patterns of nightly cpap usage in osa patients with suboptimal treatment adherence" 74 : 109-115, 2020

14 A. B. Gardner, "One-class novelty detection for seizure analysis from intracranial eeg" 7 (7): 2006

15 M. D. Khursheed, "Machine learning based system for sleep apnea classification using eeg signal" IEEE 1-5, 2022

16 C. D. Turnbull, "In patients with minimally symptomatic osa can baseline characteristics and early patterns of cpap usage predict those who are likely to be longer-term users of cpap" 8 (8): 276-, 2016

17 W. S. Almuhammadi, "Efficient obstructive sleep apnea classification based on eeg signals" IEEE 1-6, 2015

18 R. Adams, "Effect of sleep apnea and insomnia on the association of depression with quantitative electroencephalogram measures (QEEG) in adult men during sleep – the MAILES study" Elsevier BV 40 : e5-e6, 2017

19 R. M. Mehmood, "Eeg-based affective state recognition from human brain signals by using hjorth-activity" 202 : 111738-, 2022

20 R. Bellman, "Dynamic programming" 153 (153): 34-37, 1966

21 P. Tovichien, "Comparing adherence of continuous and automatic positive airway pressure(cpap and apap)in obstructive sleep apnea(osa)children" 10 : 841705-, 2022

22 C. A. Kushida, "Clinical guidelines for the manual titration of positive airway pressure in patients with obstructive sleep apnea" 4 (4): 157-171, 2008

23 S. Ozs¸en, "Classification of sleep stages using class-dependent sequential feature selection and ¨artificial neural network" 23 : 1239-1250, 2013

24 Xiaoyun Zhao, "Classification of sleep apnea based on EEG sub-band signal characteristics" Springer Science and Business Media LLC 11 (11): 2021

25 V. Vimala, "An intelligent sleep apnea classification system based on eeg signals" 43 (43): 36-, 2019

26 C. Kang, "Age-integrated artificial intelligence framework for sleep stage classification and obstructive sleep apnea screening" 17 : 1059186-, 2023

27 L. J. Epstein, "Adult obstructive sleep apnea task force of the american academy of sleep medicine. clinical guideline for the evaluation, management and long-term care of obstructive sleep apnea in adults" 5 (5): 263-276, 2009

28 S. M. Lundberg, "A unified approach to interpreting model predictions" 30 : 2017

29 B. S¸en, "A comparative study on classification of sleep stage based on eeg signals using feature selection and classification algorithms" 38 : 1-21, 2014

30 Malatantis-Ewert S, "A Novel Quantitative Arousal-Associated EEG-Metric to Predict Severity of Respiratory Distress in Obstructive Sleep Apnea Patients" Frontiers Media SA 13 : 2022

31 P. Memar, "A Novel Multi-Class EEG-Based Sleep Stage Classification System" 26 (26): 84-95, 2018