Related Experiment Video
Updated: Sep 11, 2025
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Beyond explainable AI: Enhancing trust and robustness in machine learning for sleep apnea diagnosis
1Faculty of Data Science, Musashino University, 3-3-3 Ariake Koto-ku, Tokyo, 135-8181, Japan.
This study critiques explainable AI (XAI) for sleep apnea detection, finding feature importances unreliable. It proposes unsupervised machine learning and nonparametric statistics for robust clinical validation.
Area of Science:
- Biomedical data analysis
- Artificial intelligence in healthcare
- Sleep medicine research
Background:
- Existing reviews highlight machine learning (ML) and deep learning (DL) for sleep apnea detection, focusing on explainable AI (XAI).
- Challenges include Apnea-Hypopnea Index (AHI) discrepancies and the reliability of feature importances derived from XAI tools like SHAP.
- High prediction accuracy does not ensure the validity of feature importance metrics, which lack ground truth validation.
More Related Videos
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
04:54Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
Published on: November 8, 2024
