Predicting the Urgency Demand of COPD Patients From Environmental Sensors Within Smart Cities With High-Environmental Sensitivity

Predicting the urgency demand of patients at health centers in smart cities supposes a challenge for adapting emergency service in advance. In this paper, we propose a methodology to predict the number of cases of chronic obstructive pulmonary disease (COPD) from environmental sensors located in the city of Jaén (Spain). The approach presents a general methodology to predict events from environmental sensors within smart cities based on four stages: 1) summarize and expand features by means of temporal aggregations; 2) evaluate the correlation for selecting relevant features; 3) integrate straightforwardly expert knowledge under a fuzzy linguistic approach; and 4) predict the target event with the sequence-based classifier long short-term memory under a sliding window approach. The results show an encouraging performance of the methodology over the COPD patients of the city of Jaén based on a quantitative regression analysis and qualitative categorization of data.