Comparison of neural networks for prediction of sleep apnea

Yashar Maali; Adel Al-Jumaily

doi:10.5220/0004701400600064

Comparison of neural networks for prediction of sleep apnea

Yashar Maali, Adel Al-Jumaily

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

1 Citation (Scopus)

Abstract

Sleep apnea (SA) is the most important and common component of sleep disorders which has several short term and long term side effects on health. There are several studies on automated SA detection but not too much works have been done on SA prediction. This paper discusses the application of artificial neural networks (ANNs) to predict sleep apnea. Three types of neural networks were investigated: Elman, cascade-forward and feed-forward back propagation. We assessed the performance of the models using the Receiver Operating Characteristic (ROC) curve, particularly the area under the ROC curves (AUC), and statistically compare the cross validated estimate of the AUC of different models. Based on the obtained results, generally cascade-forward model results are better with average of AUC around 80%.

Original language	English
Title of host publication	Neurotechnix 2013
Subtitle of host publication	proceedings of the international congress on neurotechnology, electronics and informatics
Editors	Ana Rita Londral, Pedro Encarnação, Jose Luis Pons
Place of Publication	Vilamoura, Portugal
Publisher	SciTePress
Pages	60-64
Number of pages	5
ISBN (Print)	9789898565808
DOIs	https://doi.org/10.5220/0004701400600064
Publication status	Published - 2013
Externally published	Yes
Event	International congress on neurotechnology, electronics and informatics - Vilamoura, Portugal Duration: 18 Sept 2013 → 20 Sept 2013

Conference

Conference	International congress on neurotechnology, electronics and informatics
City	Vilamoura, Portugal
Period	18/09/13 → 20/09/13

Keywords

Sleep apnea
Neural networks
Prediction

Access to Document

10.5220/0004701400600064

Cite this

@inproceedings{c87d834195034bcea284392fec4f67c9,

title = "Comparison of neural networks for prediction of sleep apnea",

abstract = "Sleep apnea (SA) is the most important and common component of sleep disorders which has several short term and long term side effects on health. There are several studies on automated SA detection but not too much works have been done on SA prediction. This paper discusses the application of artificial neural networks (ANNs) to predict sleep apnea. Three types of neural networks were investigated: Elman, cascade-forward and feed-forward back propagation. We assessed the performance of the models using the Receiver Operating Characteristic (ROC) curve, particularly the area under the ROC curves (AUC), and statistically compare the cross validated estimate of the AUC of different models. Based on the obtained results, generally cascade-forward model results are better with average of AUC around 80%.",

keywords = "Sleep apnea, Neural networks, Prediction",

author = "Yashar Maali and Adel Al-Jumaily",

year = "2013",

doi = "10.5220/0004701400600064",

language = "English",

isbn = "9789898565808",

pages = "60--64",

editor = "Londral, {Ana Rita} and Pedro Encarna{\c c}{\~a}o and Pons, {Jose Luis}",

booktitle = "Neurotechnix 2013",

publisher = "SciTePress",

note = "International congress on neurotechnology, electronics and informatics ; Conference date: 18-09-2013 Through 20-09-2013",

}

Maali, Y & Al-Jumaily, A 2013, Comparison of neural networks for prediction of sleep apnea. in AR Londral, P Encarnação & JL Pons (eds), Neurotechnix 2013: proceedings of the international congress on neurotechnology, electronics and informatics. SciTePress, Vilamoura, Portugal, pp. 60-64, International congress on neurotechnology, electronics and informatics, Vilamoura, Portugal, 18/09/13. https://doi.org/10.5220/0004701400600064

Comparison of neural networks for prediction of sleep apnea. / Maali, Yashar; Al-Jumaily, Adel.
Neurotechnix 2013: proceedings of the international congress on neurotechnology, electronics and informatics. ed. / Ana Rita Londral; Pedro Encarnação; Jose Luis Pons. Vilamoura, Portugal: SciTePress, 2013. p. 60-64.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Comparison of neural networks for prediction of sleep apnea

AU - Maali, Yashar

AU - Al-Jumaily, Adel

PY - 2013

Y1 - 2013

N2 - Sleep apnea (SA) is the most important and common component of sleep disorders which has several short term and long term side effects on health. There are several studies on automated SA detection but not too much works have been done on SA prediction. This paper discusses the application of artificial neural networks (ANNs) to predict sleep apnea. Three types of neural networks were investigated: Elman, cascade-forward and feed-forward back propagation. We assessed the performance of the models using the Receiver Operating Characteristic (ROC) curve, particularly the area under the ROC curves (AUC), and statistically compare the cross validated estimate of the AUC of different models. Based on the obtained results, generally cascade-forward model results are better with average of AUC around 80%.

AB - Sleep apnea (SA) is the most important and common component of sleep disorders which has several short term and long term side effects on health. There are several studies on automated SA detection but not too much works have been done on SA prediction. This paper discusses the application of artificial neural networks (ANNs) to predict sleep apnea. Three types of neural networks were investigated: Elman, cascade-forward and feed-forward back propagation. We assessed the performance of the models using the Receiver Operating Characteristic (ROC) curve, particularly the area under the ROC curves (AUC), and statistically compare the cross validated estimate of the AUC of different models. Based on the obtained results, generally cascade-forward model results are better with average of AUC around 80%.

KW - Sleep apnea

KW - Neural networks

KW - Prediction

U2 - 10.5220/0004701400600064

DO - 10.5220/0004701400600064

M3 - Conference proceeding contribution

SN - 9789898565808

SP - 60

EP - 64

BT - Neurotechnix 2013

A2 - Londral, Ana Rita

A2 - Encarnação, Pedro

A2 - Pons, Jose Luis

PB - SciTePress

CY - Vilamoura, Portugal

T2 - International congress on neurotechnology, electronics and informatics

Y2 - 18 September 2013 through 20 September 2013

ER -

Comparison of neural networks for prediction of sleep apnea

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this