New acoustic monitoring system quantifying aspiration risk during monitored anaesthesia care

Area of Science:

• Anesthesiology and Respiratory Medicine
• Biomedical Engineering
• Artificial Intelligence in Healthcare

Background:

• Patient safety during monitored anesthesia care (MAC) is paramount, especially for procedures with high aspiration risk like dental interventions.
• Current methods lack the ability to effectively assess aspiration risk in real-time.
• Fluid retention in the upper airway poses a significant, yet difficult-to-monitor, threat during MAC.

Purpose of the Study:

• To introduce and evaluate a novel acoustic monitoring system for detecting upper airway fluid retention during MAC.
• To assess the system's ability to identify fluid accumulation using artificial intelligence (AI) analysis of respiratory sounds.
• To explore the potential of this technology in mitigating aspiration risks.

Main Methods:

• A prospective observational study involving 60 participants undergoing dental treatment under MAC.
• Utilized a prototype acoustic monitoring system analyzing inspiratory sounds.
• Simulated fluid retention by intraoral water injection and analyzed respiratory sounds pre- and post-injection, as well as during coughing events using AI.

Main Results:

• The acoustic system detected significant increases in the Stridor Quantitative Value (STQV) with intraoral water injection.
• STQV was substantially higher immediately post-coughing in patients who coughed.
• AI analysis correlated breath sounds with detected instances of apnoea and coughing events.

Conclusions:

• The novel AI-driven acoustic monitoring system accurately evaluates upper airway fluid retention.
• This technology shows promise for real-time risk assessment and mitigation of aspiration during MAC.
• Further development could significantly enhance patient safety in anesthesia settings.