[Development of an Intelligent Multi-Parameter Sleep Diagnosis and Analysis System].

Area of Science:

• Sleep Medicine
• Biomedical Engineering
• Artificial Intelligence in Healthcare

Context:

• Sleep disordered breathing (SDB) prevalence is rising globally.
• Current polysomnography (PSG) methods for SDB diagnosis have limitations including lengthy interpretation times and inadequate data quality control.
• There is a critical need for advanced diagnostic tools in sleep clinical applications, particularly in China.

Purpose:

• To develop an intelligent PSG system addressing limitations of current diagnostic methods for SDB.
• To integrate enhanced data quality control, gas metabolism assessment, and hemodynamic monitoring into PSG.
• To leverage deep learning for intelligent data analysis and diagnostic support in SDB evaluation.

Summary:

• The new intelligent PSG system incorporates advanced hardware for monitoring traditional sleep parameters, end-tidal CO2 and O2 concentrations for gas metabolism, and impedance cardiography for hemodynamic assessment.
• Software development utilizes deep learning algorithms for intelligent data quality control and diagnostic techniques.
• The system aims to provide comprehensive sleep quality assessments to aid clinicians in diagnosing and managing SDB patients.

Impact:

• Potential to significantly reduce manual interpretation time for PSG data.
• Improved accuracy and comprehensiveness in SDB diagnosis through integrated monitoring and AI-driven analysis.
• Facilitates more effective clinical decision-making and personalized treatment strategies for SDB patients.