Discriminant Audio Properties in Deep Learning Based Respiratory Insufficiency Detection in Brazilian Portuguese

Author(s):Show less -

Gauy, Marcelo Matheus ; Berti, Larissa Cristina ; Candido, Arnaldo, Jr. ; Neto, Augusto Camargo ; Goldman, Alfredo ; Shafferman Levin, Anna Sara ; Martins, Marcus ; de Medeiros, Beatriz Raposo ; Queiroz, Marcelo ; Sabino, Ester Cerdeira ; Fernandes Svartman, Flaviane Romani ; Finger, Marcelo

• Document type: Journal article
• Source: ARTIFICIAL INTELLIGENCE IN MEDICINE, AIME 2023; v. 13897, p. 5-pg., 2023-01-01.

Abstract

This work investigates Artificial Intelligence (AI) systems that detect respiratory insufficiency (RI) by analyzing speech audios, thus treating speech as a RI biomarker. Previous works [2,6] collected RI data (P1) from COVID-19 patients during the first phase of the pandemic and trained modern AI models, such as CNNs and Transformers, which achieved 96.5% accuracy, showing the feasibility of RI detection via AI. Here, we collect RI patient data (P2) with several causes besides COVID-19, aiming at extending AI-based RI detection. We also collected control data from hospital patients without RI. We show that the considered models, when trained on P1, do not generalize to P2, indicating that COVID-19 RI has features that may not be found in all RI types. (AU)

• FAPESP's process: 19/07665-4 - Center for Artificial Intelligence
• Grantee: Fabio Gagliardi Cozman
• Support Opportunities: Research Grants - Research Program in eScience and Data Science - Research Centers in Engineering Program
• FAPESP's process: 20/16543-7 - Pre-trained neural models for detecting respiratory insufficiency in speech
• Grantee: Marcelo Matheus Gauy
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• FAPESP's process: 20/06443-5 - Spira: system for early-detection of respiratory insufficiency by voice audio analysis
• Grantee: Marcelo Finger
• Support Opportunities: Regular Research Grants