Authors: Hamed Fayyaz, Abigail Strang, Niharika S. D’Souza, Rahmatollah Beheshti

Published on: February 24, 2024

Impact Score: 7.4

Arxiv code: Arxiv:2402.17788

Summary

• What is new: The model works with any combination of available modalities and maintains high performance in the presence of noise or missingness.
• Why this is important: Noisy and missing modalities in polysomnography data hinder accurate sleep apnea detection.
• What the research proposes: A comprehensive pipeline that compensates for missing or noisy modalities in sleep apnea detection.
• Results: The proposed model outperforms state-of-the-art approaches, achieving high performance (AUROC0.9) even with high levels of noise or missingness.

Technical Details

Technological frameworks used: nan

Models used: nan

Data used: Polysomnography data

Potential Impact

Healthcare providers, sleep study equipment manufacturers, and telehealth companies

Want to implement this idea in a business?

We have generated a startup concept here: SleepGuard.