Project Summary Mechanical ventilation is an essential intervention for many patients but is associated with a risk of preventable complications and is a modifiable determinant of outcomes. Current standard of care approaches utilize non- individualized “one-size fits all” strategies which may expose patients to ventilator induced lung injury (VILI) and other complications often leading to prolongation of ventilation and mortality. We propose that better understanding individualized respiratory physiology and patient-ventilator interaction using esophageal manometry and decision support can create more personalized mechanical ventilation and improve clinical information, ventilator settings and outcomes. Using esophageal pressure (Pes) provides accurate estimations of transpulmonary pressure, respiratory effort, intrinsic PEEP, and patient-ventilator interaction that can be used to prevent lung collapse, prevent lung injury, and optimize lung mechanics and oxygenation. Most major mechanical ventilator settings can be better optimized with the use of esophageal pressure. Unfortunately, esophageal pressure measurements are typically labor intensive, require repetitive training for proper placement, and parameters derived from them are not easily calculated or interpreted. Esophageal balloons need to be properly placed and inflated and carefully watched over time to ensure and maintain accuracy. For these reasons, Pes is not commonly used during mechanical ventilation, with most patients receiving standard ventilator modes/settings. In this grant, we propose to develop a patented system including decision support for the personalization and optimization of mechanical ventilation by simplifying and expanding the use of Pes in the ICU. The system will support the placement and inflation of the balloon, automatically monitor its accuracy over time, and calculate and interpret key parameters. Our team has extensive experience with Pes and optimization of mechanical ventilation. We propose two Aims in this Phase I SBIR grant to reduce the risk of the technology. Aim 1 – Build a prototype hardware and software system. Although some ventilators include Pes monitoring, most do not, and those that do are still difficult to use. We will design a hardware and software decision support system for all ventilators. The system will automatically inflate and monitor the balloon and obtain the required airway data. The Phase I software system will provide placement support, accuracy monitoring, and decision support for several key parameters. Aim 2 – Validate the value and ease of use of the system. Our goal is to prove that the system simplifies use of Pes and adds clinical value to ventilator care. We will use a Pes part task trainer and simulated patients to evaluate the performance of 10 RTs both with and without the system and assess the usability and acceptability of the system. This Phase I grant will create and evaluate a prototype Pes decision support syste...