Refining sleep staging accuracy: transfer learning coupled with scorability models
Fine-tuning a pretrained neural network through targeted TL significantly enhances sleep staging performance for an atypical montage, achieving and surpassing human expert agreement levels. The introduction of a scorability assessment provides a robust measure of reliability, ensuring quality control and enhancing the practical application of the system before deployment. This approach marks an important advancement in automated sleep analysis, demonstrating the potential for AI to exceed human performance in clinical settings.
Authors
- Wolfgang Ganglberger (ORCID: https://orcid.org/0000-0002-6029-2450)
- Michael Brandon Westover (ORCID: https://orcid.org/0000-0003-4803-312X)
- Chol Shin (ORCID: https://orcid.org/0000-0002-2928-8576)
- ROBERT JOSEPH THOMAS (ORCID: https://orcid.org/0000-0002-5575-3953)
- Samaneh Nasiri (ORCID: https://orcid.org/0000-0002-4216-026X)
- Haoqi Sun (ORCID: https://orcid.org/0000-0002-5041-8312)
- Soriul Kim (ORCID: https://orcid.org/0000-0002-6161-1636)
Institutions
- Beth Israel Deaconess Medical Center (US)
- Harvard University (US)
- Emory and Henry College (US)
- Korea University (KR)
- Ansan University (KR)
- Massachusetts General Hospital (US)
- Center for Genomic Science (IT)
Publication Details
- Journal
- SLEEP
- Published
- 2024-08-31
- DOI
- https://doi.org/10.1093/sleep/zsae202
- Citations
- 9
- Primary Topic
- Obstructive Sleep Apnea Research
- Type
- article
- Field-Weighted Citation Impact
- 2.94