| dc.description.abstract | Hospitals are extremely important care points for ensuring the proper treatment of human health. One of the main problems to be faced is the increasingly overcrowded patient care queues, who end up getting more and more time with health problems without proper treatment. The allocation of health professionals in hospital environments is not able to adapt to the demands of patients, and there are times when rooms with little use have idle professionals, and rooms with a lot of use having fewer professionals than necessary. Previous works end up not solving the problem since they focus on ways to automate the treatment of health, but not on techniques for better allocating available human resources. Against this background, the present work proposes ElHealth, an IoT-focused model able to identify patients’ use of the rooms and, through data prediction techniques, to identify when a room will have a demand that exceeds the capacity of care, proposing actions to move human resources to adapt to future patients demand. The main contribution of ElHealth is the definition of Multi-level Predictive Elasticity of Human Resources, an extension of the concept of resource elasticity in Cloud Computing to manage the use of human resources at different levels of a healthcare environment, and the definition of Proactive Human Resource Elastic Speedup, an extension of the Speedup concept of parallel computing to identify the gain of medical care time with the dynamic parallel use of human resources for care in a hospital environment. ElHealth was simulated a hospital environment using data from a Brazilian polyclinic, and obtained promising results, being able to decrease the average number of patients waiting, and reduce waiting time for care in the proposed environment. | en |
