I-Corps: Translation Potential of Virtual Lung Simulations

This I-Corps project focuses on the development of computer-assisted prediction tools for the real-time personalized therapy of patients suffering from acute respiratory distress, which are often associated with secondary complications (like ventilator-induced lung injury). To reduce the high mortality rates that are common among such patients, real-time decision-making tools are needed urgently. The solution helps to understand and predict the air flow variations in the respiratory systems of individual patients (e.g., during mechanical ventilation) and diagnosing the level of lung damage (e.g., ascertaining the level of disease progression). The computer model of the lung can be customized for personalized therapy of individual patients. Such assisted therapies include optimization of the mechanical ventilator settings, while simultaneously avoiding unnecessary stress and strain on lung tissue, thus avoiding or minimizing damage to the lungs of these patients. In addition, software prediction tools can be used for training medical students and trainees. This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. This solution is based on the development of digital twins of lungs of patients with acute respiratory distress syndrome. The long-term goal involves the development and commercialization of a virtual lung model for personalized therapy of individual patients. Artificial Intelligence (AI) and machine learning techniques were explored for efficient model order reduction. By leveraging AI, equivalent network representations of lungs can be developed which consists of non-linear flow impedances. The flow regimes range from turbulent flows (in the trachea, which is several centimeters diameter) to laminar flows (in smaller bronchi/ bronchioles and alveoli, which are millimeters to microns in diameter). The model enables real-time personalized therapies of such patients and helps reduce the high patient mortality in acute respiratory distress, which is often caused by secondary complications. This technology produces network-simulation models for predicting patient outcomes and for optimizing ventilator settings. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria. NSF Award ID: 2529593 | Program: 01002526DB NSF RESEARCH & RELATED ACTIVIT | Principal Investigator: Debjyoti Banerjee | Institution: Texas A&M Engineering Experiment Station, COLLEGE STATION, TX | Award Amount: $50,000 View on NSF Award Search: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2529593 View on Research.gov: https://www.research.gov/awardapi-service/v1/awards/2529593.html