360 Using machine learning to analyze voice and detect aspiration

Objectives/Goals: Aspiration causes or aggravates lung diseases. While bedside swallow evaluations are not sensitive/specific, gold standard tests for aspiration are invasive, uncomfortable, expose patients to radiation, and are resource intensive. We propose the development and validation of an AI...

Full description

Saved in:
Bibliographic Details
Main Authors: Cyril Varghese, Jianwei Zhang, Sara A. Charney, Abdelmohaymin Abdalla, Stacy Holyfield, Adam Brown, Hunter Stearns, Michelle Higgins, Julie Liss, Nan Zhang, David G. Lott, Victor E. Ortega, Visar Berisha
Format: Article
Language:English
Published: Cambridge University Press 2025-04-01
Series:Journal of Clinical and Translational Science
Online Access:https://www.cambridge.org/core/product/identifier/S2059866124009865/type/journal_article
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850097875439058944
author Cyril Varghese
Jianwei Zhang
Sara A. Charney
Abdelmohaymin Abdalla
Stacy Holyfield
Adam Brown
Hunter Stearns
Michelle Higgins
Julie Liss
Nan Zhang
David G. Lott
Victor E. Ortega
Visar Berisha
author_facet Cyril Varghese
Jianwei Zhang
Sara A. Charney
Abdelmohaymin Abdalla
Stacy Holyfield
Adam Brown
Hunter Stearns
Michelle Higgins
Julie Liss
Nan Zhang
David G. Lott
Victor E. Ortega
Visar Berisha
author_sort Cyril Varghese
collection DOAJ
description Objectives/Goals: Aspiration causes or aggravates lung diseases. While bedside swallow evaluations are not sensitive/specific, gold standard tests for aspiration are invasive, uncomfortable, expose patients to radiation, and are resource intensive. We propose the development and validation of an AI model that analyzes voice to noninvasively predict aspiration. Methods/Study Population: Retrospectively recorded [i] phonations from 163 unique ENT patients were analyzed for acoustic features including jitter, shimmer, harmonic to noise ratio (HNR), etc. Patients were classified into three groups: aspirators (Penetration-Aspiration Scale, PAS 6–8), probable (PAS 3–5), and non-aspirators (PAS 1–2) based on video fluoroscopic swallow (VFSS) findings. Multivariate analysis evaluated patient demographics, history of head and neck surgery, radiation, neurological illness, obstructive sleep apnea, esophageal disease, body mass index, and vocal cord dysfunction. Supervised machine learning using five folds cross-validated neural additive network modelling (NAM) was performed on the phonations of aspirator versus non-aspirators. The model was then validated using an independent, external database. Results/Anticipated Results: Aspirators were found to have quantifiably worse quality of sound with higher jitter and shimmer but lower harmonics noise ratio. NAM modeling classified aspirators and non-aspirators as distinct groups (aspirator NAM risk score 0.528+0.2478 (mean + std) vs. non-aspirator (control) risk score of 0.252+0.241 (mean + std); p Discussion/Significance of Impact: We report the use of voice as a novel, noninvasive biomarker to detect aspiration risk using machine learning techniques. This tool has the potential to be used for the safe and early detection of aspiration in a variety of clinical settings including intensive care units, wards, outpatient clinics, and remote monitoring.
format Article
id doaj-art-a4056b4414c3458fa9d0e96d276f3cfd
institution DOAJ
issn 2059-8661
language English
publishDate 2025-04-01
publisher Cambridge University Press
record_format Article
series Journal of Clinical and Translational Science
spelling doaj-art-a4056b4414c3458fa9d0e96d276f3cfd2025-08-20T02:40:51ZengCambridge University PressJournal of Clinical and Translational Science2059-86612025-04-01911111110.1017/cts.2024.986360 Using machine learning to analyze voice and detect aspirationCyril Varghese0Jianwei Zhang1Sara A. Charney2Abdelmohaymin Abdalla3Stacy Holyfield4Adam Brown5Hunter Stearns6Michelle Higgins7Julie Liss8Nan Zhang9David G. Lott10Victor E. Ortega11Visar Berisha12Mayo ClinicMayo ClinicMayo ClinicMayo ClinicMayo ClinicMayo ClinicMayo ClinicMayo ClinicMayo ClinicMayo ClinicMayo ClinicMayo ClinicMayo Clinic Arizona and ^Arizona State UniversityObjectives/Goals: Aspiration causes or aggravates lung diseases. While bedside swallow evaluations are not sensitive/specific, gold standard tests for aspiration are invasive, uncomfortable, expose patients to radiation, and are resource intensive. We propose the development and validation of an AI model that analyzes voice to noninvasively predict aspiration. Methods/Study Population: Retrospectively recorded [i] phonations from 163 unique ENT patients were analyzed for acoustic features including jitter, shimmer, harmonic to noise ratio (HNR), etc. Patients were classified into three groups: aspirators (Penetration-Aspiration Scale, PAS 6–8), probable (PAS 3–5), and non-aspirators (PAS 1–2) based on video fluoroscopic swallow (VFSS) findings. Multivariate analysis evaluated patient demographics, history of head and neck surgery, radiation, neurological illness, obstructive sleep apnea, esophageal disease, body mass index, and vocal cord dysfunction. Supervised machine learning using five folds cross-validated neural additive network modelling (NAM) was performed on the phonations of aspirator versus non-aspirators. The model was then validated using an independent, external database. Results/Anticipated Results: Aspirators were found to have quantifiably worse quality of sound with higher jitter and shimmer but lower harmonics noise ratio. NAM modeling classified aspirators and non-aspirators as distinct groups (aspirator NAM risk score 0.528+0.2478 (mean + std) vs. non-aspirator (control) risk score of 0.252+0.241 (mean + std); p Discussion/Significance of Impact: We report the use of voice as a novel, noninvasive biomarker to detect aspiration risk using machine learning techniques. This tool has the potential to be used for the safe and early detection of aspiration in a variety of clinical settings including intensive care units, wards, outpatient clinics, and remote monitoring.https://www.cambridge.org/core/product/identifier/S2059866124009865/type/journal_article
spellingShingle Cyril Varghese
Jianwei Zhang
Sara A. Charney
Abdelmohaymin Abdalla
Stacy Holyfield
Adam Brown
Hunter Stearns
Michelle Higgins
Julie Liss
Nan Zhang
David G. Lott
Victor E. Ortega
Visar Berisha
360 Using machine learning to analyze voice and detect aspiration
Journal of Clinical and Translational Science
title 360 Using machine learning to analyze voice and detect aspiration
title_full 360 Using machine learning to analyze voice and detect aspiration
title_fullStr 360 Using machine learning to analyze voice and detect aspiration
title_full_unstemmed 360 Using machine learning to analyze voice and detect aspiration
title_short 360 Using machine learning to analyze voice and detect aspiration
title_sort 360 using machine learning to analyze voice and detect aspiration
url https://www.cambridge.org/core/product/identifier/S2059866124009865/type/journal_article
work_keys_str_mv AT cyrilvarghese 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT jianweizhang 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT saraacharney 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT abdelmohayminabdalla 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT stacyholyfield 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT adambrown 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT hunterstearns 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT michellehiggins 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT julieliss 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT nanzhang 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT davidglott 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT victoreortega 360usingmachinelearningtoanalyzevoiceanddetectaspiration
AT visarberisha 360usingmachinelearningtoanalyzevoiceanddetectaspiration