A Convolutional Neural Network Architecture to Enhance Oximetry Ability to Diagnose Pediatric Obstructive Sleep Apnea

Vaquerizo-Villar, Fernando; Álvarez, Daniel; Kheirandish‐Gozal, Leila; Gutiérrez‐Tobal, Gonzalo C.; Barroso-García, Verónica; Santamaría-Vázquez, Eduardo; Campo, Félix del; Gozal, David; Hornero, Roberto

doi:10.1109/jbhi.2020.3048901

Cited by 51 publications

(43 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is worth noting that, among the studies included in the meta-analysis, none of them considered HRV signals. Furthermore, the sample size from seventeen out of nineteen studies included in the systematic review was markedly smaller than the databases analyzed here, only being surpassed by the cohort included in the studies of Hornero et al [42] and Vaquerizo-Villar et al [58]. Therefore, these considerations along with the similar diagnostic performance reached in the 5 and 10 e/h severity thresholds reinforce the support for the use of HRV bispectral analysis as a potential alternative to overnight PSG for pediatric OSA diagnosis.…”

Section: Comparison With Previous Workmentioning

confidence: 76%

Bispectral Analysis of Heart Rate Variability to Characterize and Help Diagnose Pediatric Sleep Apnea

Martín-Montero

Gutiérrez‐Tobal

Gozal

et al. 2021

Entropy

Self Cite

View full text Add to dashboard Cite

Pediatric obstructive sleep apnea (OSA) is a breathing disorder that alters heart rate variability (HRV) dynamics during sleep. HRV in children is commonly assessed through conventional spectral analysis. However, bispectral analysis provides both linearity and stationarity information and has not been applied to the assessment of HRV in pediatric OSA. Here, this work aimed to assess HRV using bispectral analysis in children with OSA for signal characterization and diagnostic purposes in two large pediatric databases (0–13 years). The first database (training set) was composed of 981 overnight ECG recordings obtained during polysomnography. The second database (test set) was a subset of the Childhood Adenotonsillectomy Trial database (757 children). We characterized three bispectral regions based on the classic HRV frequency ranges (very low frequency: 0–0.04 Hz; low frequency: 0.04–0.15 Hz; and high frequency: 0.15–0.40 Hz), as well as three OSA-specific frequency ranges obtained in recent studies (BW1: 0.001–0.005 Hz; BW2: 0.028–0.074 Hz; BWRes: a subject-adaptive respiratory region). In each region, up to 14 bispectral features were computed. The fast correlation-based filter was applied to the features obtained from the classic and OSA-specific regions, showing complementary information regarding OSA alterations in HRV. This information was then used to train multi-layer perceptron (MLP) neural networks aimed at automatically detecting pediatric OSA using three clinically defined severity classifiers. Both classic and OSA-specific MLP models showed high and similar accuracy (Acc) and areas under the receiver operating characteristic curve (AUCs) for moderate (classic regions: Acc = 81.0%, AUC = 0.774; OSA-specific regions: Acc = 81.0%, AUC = 0.791) and severe (classic regions: Acc = 91.7%, AUC = 0.847; OSA-specific regions: Acc = 89.3%, AUC = 0.841) OSA levels. Thus, the current findings highlight the usefulness of bispectral analysis on HRV to characterize and diagnose pediatric OSA.

show abstract

Section: Comparison With Previous Workmentioning

confidence: 76%

Bispectral Analysis of Heart Rate Variability to Characterize and Help Diagnose Pediatric Sleep Apnea

Martín-Montero

Gutiérrez‐Tobal

Gozal

et al. 2021

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…ECG、EEG检测呼吸暂停. 其中，大多数研究侧重于使用SpO 2 [37,38] 和ECG [39][40][41] ，SpO 2 与呼吸暂停的相关性如1.2节中所述. 在呼吸暂停期间会以心动过缓的形式引起心律的周期性变化，继而在呼吸停止时出现心动过速，从ECG信号形态中可以观察到相应的现象，故而ECG被广泛应用于呼吸暂停检测.…”

Section: Eeg包含睡眠期间大脑活动的大量有价值且可解释的信息，这些信息不仅是区分nrem的3个睡unclassified

Sensing, computing and intervention for sleep health

Zhang¹

2021

Chin. Sci. Bull.

View full text Add to dashboard Cite

“…University of Chicago (UofC) database protocol is provided in the supplementary material of . This database was used in Vaquerizo-Villar et al (2021). Table 3.1 shows the sociodemographic and clinical data from this database.…”

Section: Objectivesmentioning

confidence: 99%

“…In the deep-learning branch, the pre-processing stage was simpler, as deeplearning approaches are able to automatically process raw data . In this respect, SpO 2 signal pre-processing consisted on: (i) downsampling of the SpO 2 recordings to 1 Hz in order to homogenize the frequency (Mostafa et al, 2017); and (ii) segmentation of the SpO 2 recordings into 20-min segments (1200 samples) prior to train the CNN-based deep-learning architecture (Vaquerizo-Villar et al, 2021).…”

Section: Pre-processingmentioning

confidence: 99%

“…As aforementioned, deep-learning methods have beaten conventional approaches in many fields (LeCun et al, 2015), including the OSA context , primarily due to their capability to automatically discover intricate patterns from the raw data using ANNs with a high number of hidden layers . In this research, we have evaluated a new deep-learning model based on CNNs (Vaquerizo-Villar et al, 2021), the most widely-used deeplearning architecture in the OSA context .…”

Section: Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Automated analysis of the oximetry signal to simplify the diagnosis of pediatric sleep apnea: from feature-engineering to deep-learning approaches

Villar¹

View full text Add to dashboard Cite

Agradecimientosboth personally and profesionally. Thanks Thomas for giving me the opportunity to collaborate in international research projects. I am also very grateful to Niels Wessel, Jan Kraemer, and Hua Qin for their help, advice, and feedback with my work, as well as to all the nice people in Berlin who made me feel like home.Finalmente, quiero dar las gracias a mi familia, que fueron los primeros que me animaron a seguir este camino. He tenido los mejores padres, hermanos, abuelos, tíos, primos y demás familia, que se han esforzado desde el día que nací para que pudiera llegar hasta aquí, aunque algunos no vayáis a poder verlo. Tampoco me puedo olvidar de mi novia, ni de mis amigos, que se han convertido en la segunda familia por su preocupación, apoyo y ayuda a que lo difícil fuera fácil.En este sentido, estoy especialmente agradecido a Alex B. por su ayuda con las ilustraciones del documento.

show abstract

A Convolutional Neural Network Architecture to Enhance Oximetry Ability to Diagnose Pediatric Obstructive Sleep Apnea

Cited by 51 publications

References 42 publications

Bispectral Analysis of Heart Rate Variability to Characterize and Help Diagnose Pediatric Sleep Apnea

Bispectral Analysis of Heart Rate Variability to Characterize and Help Diagnose Pediatric Sleep Apnea

Sensing, computing and intervention for sleep health

Automated analysis of the oximetry signal to simplify the diagnosis of pediatric sleep apnea: from feature-engineering to deep-learning approaches

Contact Info

Product

Resources

About