Aprendizado de máquina para classificação da desocupação de leitos pós-cirúrgicos: Aprendizado de máquina para classificação da desocupação de leitos pós-cirúrgicos

Congenital heart diseases are among the most common congenital anomalies and if they aren’t discovered and treated properly at na early stage, babies and children can have a poor quality of life and may die over time. In many cases, surgical intervention is necessary before the first year of life and when it occurs, it is importante to estimate the length of stay in post-surgical beds, both for capacity management, planning and optimization of resources by the hospital and to guide patients and their families. The present study aims to propose two models, through the use of Machine Learning algorithms, one to classify the length of stay in post-surgical ICU beds and the other to classify the length of stay in post-surgical ward beds, since research related to the length of stay in postsurgical ward beds is rare. The data used to train the algoritgms are regarding cardiac surgeries performed on congenital heart patients extracted from the ASSIST, private database of the Instituto do Coração do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (InCor - FMUSP). The trained algorithms were: Random Forest, Extra Trees, Gradient Boosting, Adaboost, Support Vector Machine and the Multilayer Perceptron neural network trained with the Backpropagation algorithm. The model that presented the best performance to classify the length of stay in ICU beds was the Random Forest and to classify the length of stay of ward beds was the Gradient Boosting