MACHINE LEARNING TO RATE ATAXIC BREATHING SEVERITY

Opioid-induced respiratory depression is traditionally recognized by assessment of respiratory rate, arterial oxygen saturation, end-tidal CO2, and mental status. Although an irregular or ataxic breathing pattern is widely recognized as a manifestation of opioid effects, the presence of ataxic breathing is not routinely monitored or scored. A major obstacle to widespread monitoring for ataxic breathing is the necessity for manual, offline analysis.

University of Utah researchers have developed a machine learning algorithm that enables real-time, quantitative monitoring of patients’ breathing patterns. This algorithm determines the severity of ataxic breathing events and has been verified to classify those events in a manner consistent with manual analysis. Accordingly, the algorithm should enable detection of opioid-induced respiratory depression events and determine their severity.