Voice-based prediction of prediabetes using classical machine learning models
Voice-based prediction models show potential for prediabetes screening in controlled populations, but their performance declines when applied across geographic or demographic boundaries. These findings highlight the need for more diverse training data and population-specific model tuning to support real-world applicability.
Authors
- Jessica Oreskovic (ORCID: https://orcid.org/0009-0007-9778-8728)
- Yan Fossat (ORCID: https://orcid.org/0000-0002-1271-2633)
- Jaycee Kaufman (ORCID: https://orcid.org/0000-0001-8183-0206)
- Ghazal S. Fazli (ORCID: https://orcid.org/0000-0002-8157-7762)
- Vasudeva Varma (ORCID: https://orcid.org/0000-0003-1923-1725)
- Karenina Nurmelita Malik
Institutions
- Humber Polytechnic (CA)
- General Electric (Canada) (CA)
- KLE Academy of Higher Education and Research (IN)
Publication Details
- Journal
- Frontiers in Clinical Diabetes and Healthcare
- Published
- 2025-11-27
- DOI
- https://doi.org/10.3389/fcdhc.2025.1697769
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- Natural Sciences and Engineering Research Council of Canada