摘要
Medical diagnosis is one of the most tedious and complex processes that healthcare personnel face in their day-to-day life. To establish an adequate treatment, it is essential to carry out a correct and early evaluation of each patient. Occasionally, given the number of tests that need to be performed, this evaluation process can require a significant amount of time, and can negatively affect the patient’s recovery. The objective of this work is the development of a new software that, using Artificial Intelligence (AI), offers the healthcare professional support in the process of diagnosing the patient, as well as preventing the probability of suffering a certain disease, based on test information analytics and demographic information available. The system allows storing multiple models based on Deep Learning (DL), previously trained for the diagnosis of different diseases. These models allow predictions to be made based on available medical information. As a use case, one of these models has been successfully tested in diagnosing stroke events.
Medical diagnosis is one of the most tedious and complex processes that healthcare personnel face in their day-to-day life. To establish an adequate treatment, it is essential to carry out a correct and early evaluation of each patient. Occasionally, given the number of tests that need to be performed, this evaluation process can require a significant amount of time, and can negatively affect the patient’s recovery. The objective of this work is the development of a new software that, using Artificial Intelligence (AI), offers the healthcare professional support in the process of diagnosing the patient, as well as preventing the probability of suffering a certain disease, based on test information analytics and demographic information available. The system allows storing multiple models based on Deep Learning (DL), previously trained for the diagnosis of different diseases. These models allow predictions to be made based on available medical information. As a use case, one of these models has been successfully tested in diagnosing stroke events.
