Towards optimal design of patient isolation units in emergency rooms to prevent airborne virus transmission: From computational fluid dynamics to data-driven modeling

• Published in: Computers in biology and medicine Vol. 173; p. 108309
• Main Authors: Lee, Jong Hyeon, Shim, Jae Woo, Lim, Min Hyuk, Baek, Changhoon, Jeon, Byoungjun, Cho, Minwoo, Park, Sungwoo, Choi, Dong Hyun, Kim, Byeong Soo, Yoon, Dan, Kim, Young Gyun, Cho, Seung Yeon, Lee, Kyung-Min, Yeo, Myoung-Souk, Zo, Hangman, Shin, Sang Do, Kim, Sungwan
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.05.2024; Elsevier Limited
• Subjects: Air flow; Airborne virus; Computational fluid dynamics; Computer applications; Computer Simulation; COVID-19; Data-driven machine-learning-based modeling; Design optimization; Emergency medical care; Emergency medical services; Emergency Service, Hospital; Humans; Hydrodynamics; Infection Control - methods; Infectious diseases; Internal Medicine; Isolation units; Machine learning; Mathematical models; Other; Pandemics; Parameter identification; Patient Isolation; Patient isolation unit; Simulation; Ventilation; COVID-19; Patient isolation unit; Computational fluid dynamics; Data-driven machine-learning-based modeling; Airborne virus
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108309

Patient isolation units (PIUs) can be an effective method for effective infection control. Computational fluid dynamics (CFD) is commonly used for PIU design; however, optimizing this design requires extensive computational resources. Our study aims to provide data-driven models to determine the PIU settings, thereby promoting a more rapid design process. Using CFD simulations, we evaluated various PIU parameters and room conditions to assess the impact of PIU installation on ventilation and isolation. We investigated particle dispersion from coughing subjects and airflow patterns. Machine-learning models were trained using CFD simulation data to estimate the performance and identify significant parameters. Physical isolation alone was insufficient to prevent the dispersion of smaller particles. However, a properly installed fan filter unit (FFU) generally enhanced the effectiveness of physical isolation. Ventilation and isolation performance under various conditions were predicted with a mean absolute percentage error of within 13%. The position of the FFU was found to be the most important factor affecting the PIU performance. Data-driven modeling based on CFD simulations can expedite the PIU design process by offering predictive capabilities and clarifying important performance factors. Reducing the time required to design a PIU is critical when a rapid response is required. [Display omitted] •Machine-learning models trained with computational fluid dynamics simulation data•Data-driven models inform important variables for patient isolation unit design•Data-driven models can expedite the design process of patient isolation units•Physical isolation alone is insufficient to prevent small particle dispersion•Properly installed fan filter unit enhanced the effectiveness of physical isolation