Biomarkers for detecting changes in asthma control and vocal fold dysfunction by audio

• Grant number: 24/21681-0
• Support Opportunities: Scholarships in Brazil - Master
• Start date: September 01, 2025
• End date: August 31, 2027
• Field of knowledge: Health Sciences - Physiotherapy and Occupational Therapy
• Principal Investigator: Celso Ricardo Fernandes de Carvalho
• Grantee: Yan Anderson Pires de Oliveira
• Host Institution: Faculdade de Medicina (FM). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated research grant: 23/00488-5 - SPIRA-BM: biomarkers for respiratory conditions on mobile devices using audio analysis with artificial intelligence, AP.TEM

Abstract

Introduction: Asthma is a complex and heterogeneous disease and the lack of asthma control and vocal fold dysfunction (VFD) are among the main factors that cause worsening symptoms and loss of quality of life. However, both conditions are either difficult to detect by the patient or the diagnosis is invasive and generates a lot of discomfort. Aim: To develop biomarkers using voice and speech audio signals for the detection of lack of asthma control and VPD in patients with moderate to severe asthma. Methods: Patients with moderate to severe asthma will be assessed during a routine outpatient visit, regardless of their level of asthma control. Patients will be divided into four groups: asthma with clinical control (ACC), asthma without clinical control (ASC), asthma with clinical control and DPV (ACCDPV) and asthma without clinical control and DPV. Subjects will be controlled for gender, body mass index (BMI) and age. Asthma control will be assessed using the Asthma Control Questionnaire (ACQ) and the presence of PVD will be diagnosed by bronchoscopy by specialist physicians. Patients will be approached and asked to take part in the study. If they accept, they will be asked to make a recording in which audio and voice recordings will be made of three components: a sustained vowel, a sentence and a nursery rhyme. The recording will be made on a cell phone obtained with the resources of the thematic project and with the application "System for Early Detection of Respiratory Failure by Audio Analysis" (SPIRA) developed especially for this project. Analyses will be carried out using small and big data. The small data analysis will include voice variables (fundamental frequency, standard deviation of fundamental frequency, jitter, shimmer and signal-to-noise ratio) and speech variables (total sentence length, number of pauses and duration of pauses), while the big data analysis will be carried out using artificial intelligence by researchers from the SPIRA project. 100 patients will be assessed and the sample calculation was based on a voice variable (fundamental frequency, fo; in Hz) and a speech variable (total sentence duration, sec). (AU)