In order to minimize surgical site infections, indoor air quality in hospital operating rooms is a major concern. A wide range of literature on the relevant issue has shown that air contamination diminution can be attained by applying a more efficient set of monitoring and controlling systems that improve and optimize the indoor air status level. This paper discusses a fuzzy inference system (FIS) and the integrated model neuro-fuzzy inference system (ANFIS) focusing on the control of contamination via proper airflow distribution in an operating room, which is essential to guarantee the accuracy of the surgical procedure. A deep learning estimation approach is proposed to predict incidence in the presence of airborne contamination. The project's goal is to reduce airborne contamination to improve the surgical environment and reduce the predicted incidence during surgeries. The neuro-fuzzy deep learning model was trained with a neural network structure and tested by considering 3 important parameters that affected the air quality introducing the specialization of the system to control the model’s target. Finally, the proposed approach has been put into practice by making use of data collected by sensors placed within a real operating room in a hospital in Mashhad, Iran. The proposed model attains 97.3% and 95% validation accuracy for estimating the relative humidity and particles, respectively. The efficacy of the proposed neuro-fuzzy indicates that the system significantly lowers risk values and enhances indoor air quality.