학술논문
Artificial intelligence for the recognition of benign lesions of vocal folds from audio recordings.
Document Type
Academic Journal
Author
Marchese MR; Unità Operativa Complessa di Otorinolaringoiatria, Dipartimento di Neuroscienze, Organi di Senso e Torace, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy.; Sensoli F; Institute of Biorobotics, Scuola Superiore Sant'Anna, Pontedera, Italy.; Campagnini S; Institute of Biorobotics, Scuola Superiore Sant'Anna, Pontedera, Italy.; IRCCS Fondazione Don Carlo Gnocchi, Firenze, Italy.; Cianchetti M; Institute of Biorobotics, Scuola Superiore Sant'Anna, Pontedera, Italy.; Nacci A; U.O. Otorinolaringoiatria Audiologia e Foniatria, Azienda Ospedaliero Universitaria Pisana, Pisa, Italy.; Ursino F; Istituto Nazionale di Ricerche in Foniatria 'G. Bartalena', Pisa, Italy.; D'Alatri L; Unità Operativa Complessa di Otorinolaringoiatria, Dipartimento di Neuroscienze, Organi di Senso e Torace, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy.; Sezione di Otorinolaringoiatria, Dipartimento Universitario Testa-Collo e Organi di Senso, Università Cattolica del Sacro Cuore, Rome, Italy.; Galli J; Unità Operativa Complessa di Otorinolaringoiatria, Dipartimento di Neuroscienze, Organi di Senso e Torace, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy.; Sezione di Otorinolaringoiatria, Dipartimento Universitario Testa-Collo e Organi di Senso, Università Cattolica del Sacro Cuore, Rome, Italy.; Carrozza MC; Institute of Biorobotics, Scuola Superiore Sant'Anna, Pontedera, Italy.; Paludetti G; Unità Operativa Complessa di Otorinolaringoiatria, Dipartimento di Neuroscienze, Organi di Senso e Torace, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy.; Sezione di Otorinolaringoiatria, Dipartimento Universitario Testa-Collo e Organi di Senso, Università Cattolica del Sacro Cuore, Rome, Italy.; Mannini A; Institute of Biorobotics, Scuola Superiore Sant'Anna, Pontedera, Italy.; IRCCS Fondazione Don Carlo Gnocchi, Firenze, Italy.
Source
Publisher: Pacini editore Country of Publication: Italy NLM ID: 8213019 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1827-675X (Electronic) Linking ISSN: 0392100X NLM ISO Abbreviation: Acta Otorhinolaryngol Ital Subsets: MEDLINE
Subject
Language
English
Abstract
Objective: The diagnosis of benign lesions of the vocal fold (BLVF) is still challenging. The analysis of the acoustic signals through the implementation of machine learning models can be a viable solution aimed at offering support for clinical diagnosis.
Materials and Methods: In this study, a support vector machine was trained and cross-validated (10-fold cross-validation) using 138 features extracted from the acoustic signals of 418 patients with polyps, nodules, oedema, and cysts. The model's performance was presented as accuracy and average F1-score. The results were also analysed in male (M) and female (F) subgroups.
Results: The validation accuracy was 55%, 80%, and 54% on the overall cohort, and in M and F, respectively. Better performances were observed in the detection of cysts and nodules (58% and 62%, respectively) vs polyps and oedema (47% and 53%, respectively). The results on each lesion and the different patterns of the model on M and F are in line with clinical observations, obtaining better results on F and detection of sensitive polyps in M.
Conclusions: This study showed moderately accurate detection of four types of BLVF using acoustic signals. The analysis of the diagnostic results on gender subgroups highlights different behaviours of the diagnostic model.
(Copyright © 2023 Società Italiana di Otorinolaringoiatria e Chirurgia Cervico-Facciale, Rome, Italy.)
Materials and Methods: In this study, a support vector machine was trained and cross-validated (10-fold cross-validation) using 138 features extracted from the acoustic signals of 418 patients with polyps, nodules, oedema, and cysts. The model's performance was presented as accuracy and average F1-score. The results were also analysed in male (M) and female (F) subgroups.
Results: The validation accuracy was 55%, 80%, and 54% on the overall cohort, and in M and F, respectively. Better performances were observed in the detection of cysts and nodules (58% and 62%, respectively) vs polyps and oedema (47% and 53%, respectively). The results on each lesion and the different patterns of the model on M and F are in line with clinical observations, obtaining better results on F and detection of sensitive polyps in M.
Conclusions: This study showed moderately accurate detection of four types of BLVF using acoustic signals. The analysis of the diagnostic results on gender subgroups highlights different behaviours of the diagnostic model.
(Copyright © 2023 Società Italiana di Otorinolaringoiatria e Chirurgia Cervico-Facciale, Rome, Italy.)