Application of machine learning techniques to predict patient’s satisfaction of indoor environmental quality in Jordanian hospitals

The indoor environment is an integral part of the hospital design since it impacts patients’ health, well-being, and healing process. Although the machine learning approach has been widely adopted in many fields, limited studies applied the machine learning approach to indoor environmental quality (IEQ) in hospitals and the impact of the room type on patients’ satisfaction with IEQ. Accordingly, the current study aims to bridge this gap using the machine learning approach. The research used mixed design methods to assess indoor environmental quality. The data was gathered using self-reported data and field monitoring of environmental parameters inside patients’ rooms. King Abdullah University Hospital (KAUH) was used to represent hospitals in Jordan. Machine learning proceeded in several stages, starting from prepossessing, training the algorithms, and testing the results. The experiments were conducted with the same dataset for training and testing and evaluated using the same classification metrics using Python programming language. Besides, the most important features were conducted using Random Forest regardless of room type, in each room type, and each category of IEQ between room types. The present findings confirmed a variation in the essential features.