Development of an Algorithm That Predicts Hypoventilation Due to an Opioid Overdose

Overview

RTM Vital Signs, LLC is developing a miniature wearable tracheal sound sensor that communicates with a cell phone containing a machine-learning diagnostic algorithm designed to detect and predict the onset of mild, moderate, and severe hypoventilation (respiratory depression) due to an opioid overdose. The purpose of this clinical trial is to develop/validate diagnostic algorithms capable of detecting/predicting the onset of hypoventilation induced by a controlled intravenous infusion of fentanyl. The wearable sensor and algorithms will provide a series of alerts and alarms to the person, caregiver, and/or emergency personnel.

More than 64,000 Americans died from a drug overdose in 2016 and drug overdose is now the most common cause of death for people under 50 years old in the United States. The purpose of this study is to design a wearable tracheal sound sensor and develop an experimental computer program (diagnostic algorithm) that can accurately detect and predict the onset of mild, moderate, and severe hypoventilation (slow and shallow breathing) due to an opioid (fentanyl) overdose Opioid pain medications routinely cause a person's breathing to become slower and shallower, leading to an increased amount of carbon dioxide and decreased amount of oxygen in the bloodstream. Microphone trachea sound sensors will be used to measure and record sounds produced by air movement in and out of a person's trachea (windpipe) during inhalation and exhalation. Blood will be frequently sampled from a catheter placed within a wrist artery to measure the concentration of carbon dioxide and oxygen. An intravenous infusion of fentanyl will be used to decrease the person's respiratory rate and depth of breathing over a 1 to 3 hour period. Other sensors will be used to accurately measure and record the person's respiratory rate, tidal volume, hemoglobin oxygen saturation, electrocardiogram, blood pressure, temperature, body activity level, and body position. Each sensor's output signal will be processed and filtered to enhance the signal-to-noise ratio. The Trachea Sound Sensor and reference respiratory sensor information will be used to develop/validate risk-index algorithms that can recognize a significant change in an individual's "normal or baseline" pattern of respiratory rate, tidal volume, body activity, and body position. The hypoventilation monitoring system will not require previous knowledge of an individual's age, height, weight, model of the respiratory tract, or external calibration.