Reviewing the connection between speech and obstructive sleep apnea
Entity
UAM. Departamento de Tecnología Electrónica y de las ComunicacionesPublisher
BioMed Central Ltd.Date
2016-12Citation
10.1186/s12938-016-0138-5
BioMedical Engineering Online 15 (2016): 20
ISSN
1475-925XDOI
10.1186/s12938-016-0138-5Funded by
Authors thank to Sonia Martinez Diaz for her effort in collecting the OSA database that is used in this study. This research was partly supported by the Ministry of Economy and Competitiveness of Spain and the European Union (FEDER) under project "CMC-V2", TEC2012-37585-C02.Project
Gobierno de España. TEC2012-37585-C02Editor's Version
http://dx.doi.org/10.1186/s12938-016-0138-5Subjects
Obstructive sleep apnea; Speech; Clinical variables; Speaker’s voice characterization; Supervector; Gaussian mixture models; i-vector; Support vector regression; TelecomunicacionesNote
The electronic version of this article is the complete one and can be found online at: http://link.springer.com/article/10.1186/s12938-016-0138-5Rights
© 2016 Espinoza-Cuadros et al.Abstract
Background: Sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). The altered UA structure or function in OSA speakers has led to hypothesize the automatic analysis of speech for OSA assessment. In this paper we critically review several
approaches using speech analysis and machine learning techniques for OSA detection, and discuss the limitations that can arise when using machine learning techniques for diagnostic applications.
Methods: A large speech database including 426 male Spanish speakers suspected to suffer OSA and derived to a sleep disorders unit was used to study the clinical validity of several proposals using machine learning techniques to predict the apnea–hypopnea index (AHI) or classify individuals according to their OSA severity. AHI describes the severity of patients’ condition. We first evaluate AHI prediction using state-of-theart speaker recognition technologies: speech spectral information is modelled using supervectors or i-vectors techniques, and AHI is predicted through support vector
regression (SVR). Using the same database we then critically review several OSA classification approaches previously proposed. The influence and possible interference of other clinical variables or characteristics available for our OSA population: age, height,
weight, body mass index, and cervical perimeter, are also studied.
Results: The poor results obtained when estimating AHI using supervectors or i-vectors followed by SVR contrast with the positive results reported by previous research.
This fact prompted us to a careful review of these approaches, also testing some reported results over our database. Several methodological limitations and deficiencies were detected that may have led to overoptimistic results.
Conclusion: The methodological deficiencies observed after critically reviewing previous research can be relevant examples of potential pitfalls when using machine learning techniques for diagnostic applications. We have found two common limitations that can explain the likelihood of false discovery in previous research: (1) the use of
prediction models derived from sources, such as speech, which are also correlated with other patient characteristics (age, height, sex,…) that act as confounding factors; and (2) overfitting of feature selection and validation methods when working with a high number of variables compared to the number of cases. We hope this study could not
only be a useful example of relevant issues when using machine learning for medical diagnosis, but it will also help in guiding further research on the connection between speech and OSA.
Files in this item
Google Scholar:Espinoza-Cuadros, Fernando
-
Fernández Pozo, Rubén
-
Toledano, Doroteo T.
-
Alcázar Ramírez, José Daniel
-
López Gonzalo, Eduardo
-
Hernández Gómez, Luis Alfonso
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.
-
Speech Signal and Facial Image Processing for Obstructive Sleep Apnea Assessment
Espinoza Cuadros, Fernando Manuel; Fernández Pozo, Rubén; Toledano, Doroteo T.; Alcázar Ramírez, José Daniel; López Gonzalo, Eduardo; Hernández Gómez, Luis Alfonso
2015 -
Assessment of severe apnoea through voice analysis, automatic speech, and speaker recognition techniques
Fernández Pozo, Rubén; Blanco, José Luis; Hernández Gómez, Luis; López Gonzalo, Eduardo; Alcázar Ramírez, José; Toledano, Doroteo T.
2009-06-14 -
Analyzing training dependencies and posterior fusion in discriminant classification of apnea patients based on sustained and connected speech
Blanco, José Luis; Fernández Pozo, Rubén; Toledano, Doroteo T.; Caminero, F. Javier; López Gonzalo, Eduardo
2011-08