Analysis of Airborne Bacteria Count by Room According to Changes in the Number of Visiting Patients in the Outpatient Department of a General Hospital

Recently, infectious airborne pathogens of foreign origin have increased, causing individual and group infections of the respiratory tract. In particular, the indoor spread of airborne bacteria must be prevented because they spread rapidly and are difficult to contain owing to the effects of air currents. A subject space was selected in an outpatient department of a general hospital to measure the number of visiting patients, airflow volumes of the supply and exhaust systems, and differential pressures between rooms. The number of visiting patients was used in a machine learning (ML) algorithm to generate a “predicted visiting schedule of outpatients” and produce an “airborne bacteria generation prediction data” by applying human CO₂ emissions and behavior variables. Furthermore, after conducting an airflow analysis simulation, we evaluated the distribution of airborne bacteria in each room of the outpatient department. The results of this study show that it is necessary to predict the changes in the number of visiting patients in a hospital such that real-time air conditioning control methods can be employed to ensure adequate air quality. Furthermore, we obtained the basic data for predictive air-conditioning control to prevent the spread of airborne diseases in general hospitals.