Usefulness of Artificial Neural Networks in the Diagnosis and Treatment of Sleep Apnea-Hypopnea Syndrome

Álvarez, Daniel; Cerezo-Hernández, Ana; Lopez-Muniz, Graciela; Castro, Tania Alvaro-De; Ruiz-Albi, Tomas; Hornero, Roberto; Campo, Félix del

doi:10.5772/66570

Cited by 7 publications

(23 citation statements)

References 99 publications

(108 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the context of automated signal processing and pattern recognition, the following stages are essential to compose and optimize a high-performance as well as generalizable model [24]:…”

Section: Advanced Signal Processing and Automated Pattern Recognitionmentioning

confidence: 99%

“…Different studies reported significantly decreased CTM values, i.e., higher variability, in SpO2 recordings from OSAS patients due to the recurrent desaturations, both in adults [29] and in children [15,24]. Similarly, the Lempel & Ziv complexity (LZC) is a nonlinear measure of complexity linked with the number of new patterns and their repetition along the signal.…”

Section: Advanced Signal Processing and Automated Pattern Recognitionmentioning

confidence: 99%

“…Regarding conventional statistical classifiers, linear discriminant analysis (LDA) and logistic regression (LR) have been widely applied in the context of OSAS diagnosis from oximetry, whereas quadratic discriminant analysis (QDA) has been marginally used [24]. On the other hand, high-performance techniques such as artificial neural networks (ANNs) are reliable alternatives.…”

Section: Binary and Multiclass Approachesmentioning

confidence: 99%

“…Nevertheless, the multilayer perceptron (MLP) is probably the most widely used approach due to its simplicity as well as high performance [24]. Table 1 summarizes the main characteristics of studies using pattern recognition techniques for classification of suspected OSAS patients.…”

Section: Binary and Multiclass Approachesmentioning

confidence: 99%

“…In the study by Almazaydeh et al [34] An alternative pattern recognition approach also used to detect OSAS from oximetry are support vector machines (SVMs). SVMs are high-performance classifiers able to reach high generalization both in classification and regression problems [24]. In this regard, Álvarez et al [29] compared the diagnostic performance obtained with SVM, LDA, and LR in this context.…”

Section: Binary and Multiclass Approachesmentioning

confidence: 99%

See 4 more Smart Citations

Oximetry use in obstructive sleep apnea

Campo

Crespo

Cerezo-Hernández

et al. 2018

Expert Review of Respiratory Medicine

Self Cite

View full text Add to dashboard Cite

Introduction. Overnight oximetry has been proposed as an accessible, simple, and reliable technique for obstructive sleep apnea syndrome (OSAS) diagnosis. From visual inspection to advanced signal processing, several studies have demonstrated the usefulness of oximetry as a screening tool. However, there is still controversy regarding the general application of oximetry as a single screening methodology for OSAS.Areas covered. Currently, high-resolution portable devices combined with pattern recognitionbased applications are able to achieve high performance in the detection this disease. In this review, recent studies involving automated analysis of oximetry by means of advanced signal processing and machine learning algorithms are analyzed. Advantages and limitations are highlighted and novel research lines aimed at improving the screening ability of oximetry are proposed. Expert commentary. Oximetry is a cost-effective tool for OSAS screening in patients showinghigh pretest probability for the disease. Nevertheless, exhaustive analyses are still needed to further assess unattended oximetry monitoring as a single diagnostic test for sleep apnea, particularly in the pediatric population and in especial groups with significant comorbidities. In the following years, communication technologies and big data analysis will overcome current limitations of simplified sleep testing approaches, changing the detection and management of OSAS.

show abstract

“…In the context of automated signal processing and pattern recognition, the following stages are essential to compose and optimize a high-performance as well as generalizable model [24]:…”

Section: Advanced Signal Processing and Automated Pattern Recognitionmentioning

confidence: 99%

Section: Advanced Signal Processing and Automated Pattern Recognitionmentioning

confidence: 99%

Section: Binary and Multiclass Approachesmentioning

confidence: 99%

Section: Binary and Multiclass Approachesmentioning

confidence: 99%

Section: Binary and Multiclass Approachesmentioning

confidence: 99%

See 3 more Smart Citations

Oximetry use in obstructive sleep apnea

Campo

Crespo

Cerezo-Hernández

et al. 2018

Expert Review of Respiratory Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

Developing and comparing machine learning models to detect sleep apnoea using single-lead electrocardiogram (ECG) monitoring

Hedman

Rojas

Arora

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundSleep apnoea has a high disease burden but remains underdiagnosed, in part due to the expensive and resource intensive nature of polysomnography, its definitive investigation. Emerging literature suggests that it may be possible to detect sleep apnoea using single-lead ECG signals, such as those obtained from smartwatches. In this study, we use two forms of recurrent neural networks (RNNs) to detect sleep apnoea events from single-lead ECG signals.MethodsWe use single-lead ECG data from the PhysioNet Apnea-ECG database, which contains data from 70 patients. We train a bidirectional gated recurrent unit (GRU) model and a bidirectional long short-term memory (LSTM) model on labelled ECG signals from 35 patients and test the models on the remaining 35 patients in the dataset.ResultsBoth models achieved 97.1% accuracy, sensitivity and specificity to detect whether the ECG recordings belonged to a patient diagnosed with sleep apnoea. This corresponds to 34/35 patients in the dataset. At detecting individual apnoea events, the GRU and LSTM models achieved 90.4% and 91.7% accuracies respectively.DiscussionThe models achieved high levels of accuracy, specificity and sensitivity. Bidirectional RNNs are strengthened by the ability of the models to be informed by both past and future states when analysing sequential data, such as ECGs. The models also require minimal human intervention as they automatically extract features from the data. If single-lead ECGs prove a suitable tool for sleep apnoea detection, this may enhance the diagnosis of sleep apnoea and potentially allow widespread screening for the condition.ConclusionsWe note that using models such as bidirectional RNNs has the potential to augment model performance. However, more research and validation is required in order to test whether these may be applicable to other datasets and in clinical practice.

show abstract