A Bayesian decision analysis approach to assess voice disorder risks by using acoustic features

Abstract

Vocal fold nodules are recognized as an occupational disease for all collective of workers performing activities for which maintained and continued use of voice is required.Computer-aided systems based on features extracted from voice recordings have been considered as potential noninvasive and low cost tools to diagnose some voice-related diseases. A Bayesian decision analysis approach has been proposed to classify university lectures in three levels of risk: low, medium, and high, based on the information provided by acoustic features extracted from healthy controls and people suffering from vocal fold nodules. The proposed risk groups are associated with different treatments. The approach is based on the calculation of posterior probabilities of developing vocal fold nodules and considers utility functions that include the financial cost and the probability of recovery for the corresponding treatment. Maximization of the expected utilities is considered. By using this approach, the risk of having vocal fold nodules is identified for each university lecturer, so he/she can be properly assigned to the right treatment. The approach has been applied to university lecturers according to the Disease Prevention Program of the University of Extremadura. However, it can also be applied to other voice professionals (singers, speakers, coaches, actors…).

Voice as an Indicator for Laryngeal Disorders Using Data Mining Approach

“…These disorders can occur for various reasons, such as infections, trauma, cancer, or neurological conditions. One of the main symptoms of laryngeal disorders is changes in the voice, which can range from hoarseness, breathiness, or weakness to complete loss of voice [2]. Detecting laryngeal disorders early is crucial for effective treatment and prevention of complications.…”