Um modelo computacional de recomendação de tratamento terapêutico personalizado para paciente com quadro séptico

Abstract

Health Informatics provides resources for the generation, maintenance, and storage of necessary patient data through medical records built from systems. This study addresses the identified gap in the literature regarding technical support for physicians, specifically for the automatic and Machine Learning-assisted provision of medication suggestions for patients with septic conditions. Within the Health area, SEPSIS presents itself as a clinical condition in which the response time for this condition is vital for the patient. If not treated efficiently and effectively, the patient may die in less than 24 hours. In this context, the main idea of this work is to provide a Machine Learning model to automatically predict therapeutics to assist the doctor in their decision-making and personalized for the patient. Satisfactory results were found in the tested models for the suggestion, becoming a promising path for mitigating deaths resulting from SEPSIS.