딥러닝을 이용한 액티그래피 데이터에서의 수면장애 예측
Prediction of Sleep Disorder From Actigraphy Data Using Deep Learning
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: The aim of this study was to classify polysomnography (PSG)-based sleep disorders using actigraphy data using a convolutional neural network (CNN).Methods: Actigraphy data, PSG data, and diagnoses were obtained from 214 patients from a single-center sleep clinic. Patients diagnosed with circadian sleep disorders, narcolepsy, or periodic limb movement disorders were excluded. From the actigraphy data, three types of data were selected from the first 5 days, namely, sleep-wake status, activity count, and light exposure per epoch. The data were processed into a two-dimensional array with four instances, namely, 24-hour full-day data and data for 6, 8, and 10 hours timepoints after sleep onset, and then analyzed. Using a CNN, we attempted to classify the processed data into PSG-based diagnoses.Results: Overfitting of the training data was observed. The CNN showed near-perfect accuracy on the test data, but failed to classify the validation data (area under the curve: 24-hour full-day data: 0.6031, 6 hours after sleep onset: 0.5148, 8 hours: 0.6122, and 10 hours: 0.5769).Conclusions: The lack and inaccuracy of data were responsible for the results. A higher sampling rate and additional ancillary data, such as PSG or heart rate variability data, are necessary for accurate classification. Additionally, alternative approaches to machine learning, such as transformers, should be considered in future studies.
Abstract
Objectives: The aim of this study was to classify polysomnography (PSG)-based sleep disorders using actigraphy data using a convolutional neural network (CNN).Methods: Actigraphy data, PSG data, and diagnoses were obtained from 214 patients from a single-center sleep clinic. Patients diagnosed with circadian sleep disorders, narcolepsy, or periodic limb movement disorders were excluded. From the actigraphy data, three types of data were selected from the first 5 days, namely, sleep-wake status, activity count, and light exposure per epoch. The data were processed into a two-dimensional array with four instances, namely, 24-hour full-day data and data for 6, 8, and 10 hours timepoints after sleep onset, and then analyzed. Using a CNN, we attempted to classify the processed data into PSG-based diagnoses.Results: Overfitting of the training data was observed. The CNN showed near-perfect accuracy on the test data, but failed to classify the validation data (area under the curve: 24-hour full-day data: 0.6031, 6 hours after sleep onset: 0.5148, 8 hours: 0.6122, and 10 hours: 0.5769).Conclusions: The lack and inaccuracy of data were responsible for the results. A higher sampling rate and additional ancillary data, such as PSG or heart rate variability data, are necessary for accurate classification. Additionally, alternative approaches to machine learning, such as transformers, should be considered in future studies.
참고문헌 (24)
- Lee S, "The association between sleep quality and quality of life : a population-based study", Sleep Med, 84, pp.121~126 (2021)[DOI]
- Rundo JV, "Polysomnography", Handb Clin Neurol, 160, pp.381~392 (2019)[DOI]
- Barion A, "A clinical approach to circadian rhythm sleep disorders", Sleep Med, 8, pp.566~577 (2007)[DOI]
- Byun JH, "The first night effect during polysomnography, and patients’ estimates of sleep quality", Psychiatry Res, 274, pp.27~29 (2019)[DOI]
- Collop NA, "Portable monitoring for the diagnosis of obstructive sleep apnea", Curr Opin Pulm Med, 14, pp.525~529 (2008)[DOI]
- Chakrabarti S, "Smart consumer wearables as digital diagnostic tools : a review", Diagnostics(Basel), 12, pp.2110~ (2022)[DOI]
- "Multichannel bed pressure sensor for sleep monitoring" (2012)[URL]
- Goldstein CA, "Artificial intelligence in sleep medicine : background and implications for clinicians", J Clin Sleep Med, 16, pp.609~618 (2020)[DOI]
- Lunsford-Avery JR, "Validation of the sleep regularity index in older adults and associations with cardiometabolic risk", Sci Rep, 8, pp.14158~ (2018)[DOI]
- Sateia MJ, "International classification of sleep disorders-third edition : highlights and modifications", Chest, 146, pp.1387~1394 (2014)[DOI]
- Sweetman A, "Co-morbid insomnia and sleep apnea(COMISA) : prevalence, consequences, methodological considerations, and recent randomized controlled trials", Brain Sci, 9, pp.371~ (2019)[DOI]
- Hedner J, "A novel adaptive wrist actigraphy algorithm for sleep-wake assessment in sleep apnea patients", Sleep, 27, pp.1560~1566 (2004)[DOI]
- García-Díaz E, "Respiratory polygraphy with actigraphy in the diagnosis of sleep apnea-hypopnea syndrome", Chest, 131, pp.725~732 (2007)[DOI]
- Lee XK, "Validation of a consumer sleep wearable device with actigraphy and polysomnography in adolescents across sleep opportunity manipulations", J Clin Sleep Med, 15, pp.1337~1346 (2019)[DOI]
- Buysse DJ, "The Pittsburgh sleep quality index : a new instrument for psychiatric practice and research", Psychiatry Res, 28, pp.193~213 (1989)[DOI]
- Sohn SI, "The reliability and validity of the Korean version of the Pittsburgh sleep quality index", Sleep Breath, 16, pp.803~812 (2012)[DOI]
- Bastien CH, "Validation of the insomnia severity index as an outcome measure for insomnia research", Sleep Med, 2, pp.297~307 (2001)[DOI]
- Cho YW, "Validation of a Korean version of the insomnia severity index", J Clin Neurol, 10, pp.210~215 (2014)[DOI]
- Sung HM, "A study on the reliability and the validity of Korean version of the Beck depression inventory-II(BDI-II)", J Korean Soc Biol Ther Psychiatry, 14, pp.201~212 (2008)
- Beck AT, "Manual for the Beck depression inventory-II" (1996), Psychological Corporation
- Kim H, "Automation of classification of sleep stages and estimation of sleep efficiency using actigraphy", Front Public Health, 10, pp.1092222~ (2023)[DOI]
- Radha M, "Sleep stage classification from heart-rate variability using long short-term memory neural networks", Sci Rep, 9, pp.14149~ (2019)[DOI]