On Finding Explicit Rules for Personalized Forecasting of Obstructive Sleep Apnea Episodes

Falco, Ivanoe De; Pietro, Giuseppe De; Sannino, Giovanna

doi:10.1109/iri.2015.57

Cited by 8 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As changes in cardiac activity are expected to be more profound during respiratory events than in lead time duration, it is reasonable that pre‐90 segments performed worst among the pre‐OSA segments, as they were furthest from the respiratory events. Interestingly, we found that pre‐60 segments seemed to perform better than pre‐30 segments, contrary to our expectation that the performance would improve as segments got closer to a respiratory event as in other studies (Falco et al, 2015; Nasifoglu & Eroğul, 2021; Waxman et al, 2010). A possible explanation for this observation is that pre‐30 segments lay under CPAP effects in normalising the patient's respiration, as CPAP pressure opens the upper airway and normalises the cardiac activity (Karasulu et al, 2010; Kufoy et al, 2012).…”

Section: Discussioncontrasting

confidence: 99%

“…To address this issue, the current study aims to develop a novel machine-learning model for the early detection of sleep apnea events using single-lead electrocardiogram (ECG) signals. Inspired by the work of De Falco (Falco et al, 2015) and Huseyin Nasifoglu and Osman Erogul (Nasifoglu & Ero gul, 2021), we hypothesised that the changes in respiratory patterns could impact the autonomic nervous activity even before actual respiratory events occur, leading to alterations in ECG signals. ECG signals present a more convenient, less intrusive, and widely available alternative to respiratory flow trace across various clinical or home-based settings.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection of preceding sleep apnea using ECG spectrogram during CPAP titration night: A novel machine‐learning and bag‐of‐features framework

Linh

Trang

Lin

et al. 2023

Journal of Sleep Research

View full text Add to dashboard Cite

SummaryObstructive sleep apnea (OSA) has a heavy health‐related burden on patients and the healthcare system. Continuous positive airway pressure (CPAP) is effective in treating OSA, but adherence to it is often inadequate. A promising solution is to detect sleep apnea events in advance, and to adjust the pressure accordingly, which could improve the long‐term use of CPAP treatment. The use of CPAP titration data may reflect a similar response of patients to therapy at home. Our study aimed to develop a machine‐learning algorithm using retrospective electrocardiogram (ECG) data and CPAP titration to forecast sleep apnea events before they happen. We employed a support vector machine (SVM), k‐nearest neighbour (KNN), decision tree (DT), and linear discriminative analysis (LDA) to detect sleep apnea events 30–90 s in advance. Preprocessed 30 s segments were time–frequency transformed to spectrograms using continuous wavelet transform, followed by feature generation using the bag‐of‐features technique. Specific frequency bands of 0.5–50 Hz, 0.8–10 Hz, and 8–50 Hz were also extracted to detect the most detected band. Our results indicated that SVM outperformed KNN, LDA, and DT across frequency bands and leading time segments. The 8–50 Hz frequency band gave the best accuracy of 98.2%, and a F1‐score of 0.93. Segments 60 s before sleep events seemed to exhibit better performance than other pre‐OSA segments. Our findings demonstrate the feasibility of detecting sleep apnea events in advance using only a single‐lead ECG signal at CPAP titration, making our proposed framework a novel and promising approach to managing obstructive sleep apnea at home.

show abstract

Section: Discussioncontrasting

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Detection of preceding sleep apnea using ECG spectrogram during CPAP titration night: A novel machine‐learning and bag‐of‐features framework

Linh

Trang

Lin

et al. 2023

Journal of Sleep Research

View full text Add to dashboard Cite

show abstract

“…Compared to these results, automatic feature extraction with a CNN model promises to be a more efficient method of predicting OSA events. De Falco et al extracted heart rate variability (HRV) features from 35 subjects and classification with a set of IF-THEN rules resulted in an average accuracy of 84.26%, sensitivity of 84.70%, specificity of 81.17% [27]. However, the database was annotated for each 1-minute segments, and only checks for whether an apnea occurs within that period or not.…”

Section: Discussionmentioning

confidence: 99%

“…De Falco et al proposed a model to predict an OSA episode in the next minute, based on the information obtained from the last three minutes intervals. IF-THEN rules are applied for the development of the algorithm from heart rate variability parameters of 35 subjects [27]. Maali and Al-Jumaily compared three types of neural networks (Elman, radial basis function and feed-forward back propagation) for various lead times [28].…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks based OSA Event Prediction from ECG Scalograms and Spectrograms

Nasıfoğlu

Eroğul

2021

Preprint

View full text Add to dashboard Cite

In this study, we conducted a comparative analysis of deep convolutional neural network (CNN) models in predicting Obstructive Sleep Apnea (OSA) using electrocardiograms. Unlike other studies in the literature, this study automatically extracts time-frequency features by using CNNs instead of manual feature extraction from ECG recordings. For this purpose, the proposed model generates scalogram and spectrogram representations by transforming preprocessed 30-sec ECG segments from time domain to the frequency domain using Continuous Wavelet Transform (CWT) and Short Time Fourier transform (STFT), respectively. We examined AlexNet, GoogleNet and ResNet18 models in predicting OSA events. The effect of transfer learning on success is also investigated. Based on the observed results, we proposed a new model that is found more effective in estimation. In total, 152 ECG recordings were included in the study for training and evaluation of the models. The prediction using scalograms immediately 30 seconds before potential OSA onsets gave the best performance with 82.30% accuracy, 83.22% sensitivity, 82.27% specificity and 82.95% positive predictive value. On the other hand, the prediction using spectrograms also provided up to 80.13% accuracy and 81.99% sensitivity on prediction. The results show that the proposed CNN model can be used as a good indicator to accurately predict OSA events using ECG signals.

show abstract

“…The prediction system obtained best results using 30 s segments to predict events up to 30 s in advance. De Falco et al (2015) proposed a model to predict an OSA episode in the next minute, based on the information obtained from the last three minutes intervals. IF-THEN rules are applied for the development of the algorithm from HRV parameters of 35 subjects.…”

Section: Introductionmentioning

confidence: 99%

Obstructive sleep apnea prediction from electrocardiogram scalograms and spectrograms using convolutional neural networks

Nasıfoğlu¹,

Eroğul²

2021

Physiol. Meas.

View full text Add to dashboard Cite

Objective. In this study, we conducted a comparative analysis of deep convolutional neural network (CNN) models in predicting obstructive sleep apnea (OSA) using electrocardiograms. Unlike other studies in the literature, this study automatically extracts time-frequency features by using CNNs instead of manual feature extraction from ECG recordings. Approach. The proposed model generates scalogram and spectrogram representations by transforming preprocessed 30 s ECG segments from time domain to the frequency domain using continuous wavelet transform and short time Fourier transform, respectively. We examined AlexNet, GoogleNet and ResNet18 models in predicting OSA events. The effect of transfer learning on success is also investigated. Based on the observed results, we proposed a new model that is found more effective in estimation. In total, 152 ECG recordings were included in the study for training and evaluation of the models. Main results. The prediction using scalograms immediately 30 s before potential OSA onsets gave the best performance with 82.30% accuracy, 83.22% sensitivity, 82.27% specificity and 82.95% positive predictive value. The prediction using spectrograms also achieved up to 80.13% accuracy and 81.99% sensitivity on prediction. Per-recording classification suggested considerable results with 91.93% accuracy for prediction of OSA events. Significance. Time-frequency deep features of scalograms and spectrograms of ECG segments prior to OSA events provided reliable information about the possible events in the future. The proposed CNN model can be used as a good indicator to accurately predict OSA events using ECG recordings.

show abstract

On Finding Explicit Rules for Personalized Forecasting of Obstructive Sleep Apnea Episodes

Cited by 8 publications

References 25 publications

Detection of preceding sleep apnea using ECG spectrogram during CPAP titration night: A novel machine‐learning and bag‐of‐features framework

Detection of preceding sleep apnea using ECG spectrogram during CPAP titration night: A novel machine‐learning and bag‐of‐features framework

Convolutional Neural Networks based OSA Event Prediction from ECG Scalograms and Spectrograms

Obstructive sleep apnea prediction from electrocardiogram scalograms and spectrograms using convolutional neural networks

Contact Info

Product

Resources

About