Research Article
Voice Disorder Detection via an m-Health System: Design and
Results of a Clinical Study to Evaluate Vox4Health
Ugo Cesari,
1
Giuseppe De Pietro,
2
Elio Marciano,
3
Ciro Niri,
4
Giovanna Sannino ,
2
and Laura Verde
5
1
Department of Otorhinolaryngology, University Hospital (Policlinico) Federico II of Naples, Via S. Pansini 5, Naples, Italy
2
Institute of High Performance Computing and Networking (ICAR-CNR), Via Pietro Castellino 111, Naples, Italy
3
Area of Audiology, Department of Neurosciences, Reproductive and Odontostomatological Sciences,
University of Naples Federico II, Via S. Pansini 5, Naples, Italy
4
Independent Doctor Surgeon, Specialized in Audiology and Phoniatrics, Naples, Italy
5
Department of Engineering, University of Naples “Parthenope”, Centro Direzionale di Napoli, Isola C4, Naples, Italy
Correspondence should be addressed to Giovanna Sannino; giovanna.sannino@icar.cnr.it
Received 28 February 2018; Revised 25 June 2018; Accepted 24 July 2018; Published 8 August 2018
Academic Editor: Valeria Rolla
Copyright © 2018 Ugo Cesari et al. Tis is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Objectives. Te current study presents a clinical evaluation of Vox4Health, an m-health system able to estimate the possible
presence of a voice disorder by calculating and analyzing the main acoustic measures required for the acoustic analysis, namely,
the Fundamental Frequency, jitter, shimmer, and Harmonic to Noise Ratio. Te acoustic analysis is an objective, efective, and
noninvasive tool used in clinical practice to perform a quantitative evaluation of voice quality. Materials and Methods. A clinical
study was carried out in collaboration with medical staf of the University of Naples Federico II. 208 volunteers were recruited
(mean age, 44.2 ± 13.9 years), 58 healthy subjects (mean age, 36.7 ± 13.3 years) and 150 pathological ones (mean age, 47 ± 13.1 years).
Te evaluation of Vox4Health was made in terms of classifcation performance, i.e., sensitivity, specifcity, and accuracy, by using
a rule-based algorithm that considers the most characteristic acoustic parameters to classify if the voice is healthy or pathological.
Te performance has been compared with that achieved by using Praat, one of the most commonly used tools in clinical practice.
Results. Using a rule-based algorithm, the best accuracy in the detection of voice disorders, 72.6%, was obtained by using the jitter or
shimmer value. Moreover, the best sensitivity is about 96% and it was always obtained by using jitter. Finally, the best specifcity was
achieved by using the Fundamental Frequency and it is equal to 56.9%. Additionally, in order to improve the classifcation accuracy
of the next version of the Vox4Health app, an evaluation by using machine learning techniques was conducted. We performed
some preliminary tests adopting diferent machine learning techniques able to classify the voice as healthy or pathological. Te
best accuracy (77.4%) was obtained by the Logistic Model Tree algorithm, while the best sensitivity (99.3%) was achieved using the
Support Vector Machine. Finally, Instance-based Learning performed the best specifcity (36.2%). Conclusions. Considering the
achieved accuracy, Vox4Health has been considered by the medical experts as a “good screening tool” for the detection of voice
disorders in its current version. However, this accuracy is improved when machine learning classifers are considered rather than
the rule-based algorithm.
1. Introduction
Voice signals are sounds produced by air pressure vibrations
exhaled from the lungs and modulated and shaped by the
vibrations of the vocal folds and the resonance of the vocal
tract. Te physiological process that leads to the production
of the voice involves several structures, such as
(i) the respiratory system, the main component that infu-
ences the intensity of the voice thanks to modulation
of an expiratory fow with a variable pressure below
the vocal folds;
(ii) the larynx, the cornerstone of the production of
the voice, especially through the vocal folds whose
vibration determines the sound;
Hindawi
BioMed Research International
Volume 2018, Article ID 8193694, 19 pages
https://doi.org/10.1155/2018/8193694