View in EDS

Identifying bias in models that detect vocal fold paralysis from audio recordings using explainable machine learning and clinician ratings.

Saved in:
Bibliographic Details
Title: Identifying bias in models that detect vocal fold paralysis from audio recordings using explainable machine learning and clinician ratings.
Authors: Low DM; Program in Speech and Hearing Bioscience and Technology, Harvard Medical School, Boston, Massachusetts, United States of America.; McGovern Institute for Brain Research, MIT, Cambridge, Massachusetts, United States of America., Rao V; Department of Biomedical Engineering, Columbia University, New York, New York, United States of America.; Department of Otolaryngology-Head and Neck Surgery, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, United States of America., Randolph G; Department of Otolaryngology-Head and Neck Surgery, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, United States of America.; Department of Otolaryngology-Head and Neck Surgery, Harvard Medical School, Boston, Massachusetts, United States of America., Song PC; Department of Otolaryngology-Head and Neck Surgery, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, United States of America.; Department of Otolaryngology-Head and Neck Surgery, Harvard Medical School, Boston, Massachusetts, United States of America., Ghosh SS; Program in Speech and Hearing Bioscience and Technology, Harvard Medical School, Boston, Massachusetts, United States of America.; McGovern Institute for Brain Research, MIT, Cambridge, Massachusetts, United States of America.; Department of Otolaryngology-Head and Neck Surgery, Harvard Medical School, Boston, Massachusetts, United States of America.
Source: PLOS digital health [PLOS Digit Health] 2024 May 30; Vol. 3 (5), pp. e0000516. Date of Electronic Publication: 2024 May 30 (Print Publication: 2024).
Publication Type: Journal Article
Journal Info: Publisher: PLOS Country of Publication: United States NLM ID: 9918335064206676 Publication Model: eCollection Cited Medium: Internet ISSN: 2767-3170 (Electronic) Linking ISSN: 27673170 NLM ISO Abbreviation: PLOS Digit Health Subsets: PubMed not MEDLINE
Database: MEDLINE Ultimate
Description
ISSN:2767-3170
DOI:10.1371/journal.pdig.0000516