Previsão de mortalidade após cirurgia cardíaca congênita utilizando aprendizagem de máquina
Carregando...
Arquivos
Citações na Scopus
Tipo de produção
Dissertação
Data
2020
Autores
Binuesa, F.
Orientador
Chang Junior, João
Periódico
Título da Revista
ISSN da Revista
Título de Volume
Citação
BINUESA, F. Previsão de mortalidade após cirurgia cardíaca congênita utilizando aprendizagem de máquina. 2020. 113 f. Dissertação (Mestrado em Engenharia Mecânica) - Centro Universitário FEI, São Bernardo do Campo, 2020. Disponível em: https://doi.org/10.31414/EM.2020.D.131154.
Texto completo (DOI)
Palavras-chave
Machine learning,Cardiopatia congênita
Resumo
A doença cardíaca congênita (congenital heart diseases) é a causa mais comum de grandes anomalias de mesmo gênero, responsável por quse um terço de todas as principais anomalias congênitas. Os defeitos cardíacos congênitos são condições graves e comuns com impacto significativo na morbidade, mortalidade e custos de saúde para crianças e adultos. No tratamento de pacientes com cardiopatia congênita são rara as pesquisas relacionadas ao risco de mortalidade pré-cirúrgica. Este estudo tem como objetivo propor um modelo de previsão individual de risco de morte para cirurgia cardíaca de pacientes com cardiopatia congênita e auxiliar profissionais da saúde na compreensão de quais diagnósticos ou variáveis estão associadas ao risco de morte. Utilização de técnicas de aprendizagem de máquina (machine learning) como ferramenta de apoio à tomada de decisão na área da medicina vem aumentando nos últimos anos. De posse das informações de cirurgias realizadas em pacientes com cardiopatia congênita extraídas do banco de dados ASIST do InCor, foi possível treinar seis diferentes algoritmos de aprendizagem de máquina (machine learning0 na previsão de risco de mortalidade pré cirúrgica e compreender quais variáveis impactam o risco de mortes desses pacientes. Os algoritmos treinados neste estudo foram: Multilayer Perceptron (MLP), Random Forest (RF), Extra Trees (ET), Stochastic Gradient Boosting (SGB), AdaBoost Classification (ABC) e Bagged Decision Trees (BDT). Para prever o risco de mortalidade do paciente, o modelo com melhor desempenho foi o Random Forest (RF) com ROC AUC (area under the receiver operating characteristics) de 90,2%, índices de AP (avferage precision) de 0,73 e índice de sensibilidade (recall) de 92,2%. Os algoritmos de aprendizagem de máquina (machine learning) podem auxiliar na compreensão dos riscos de mortalidade de pacientes com cardioopatia congênita quando submetida a uma intervenção cirúrgica cardíaca e permitem que especialistas clínicos compreendam melhor os riscos associados à intervenção cirúrgica, fornecendo informações para apoio à decisão dos profissionais de saúde, pacientes e seus familiares
Congenital heart disease is the most common cause of major anomalies of the same gender, accounting for almost a third of all major congenital anomalies. Congenital heart defects are serious and common conditions with a significant impact on morbidity, martality and health costs for children and adults. In the treatment of patients with congenital heart disease, research related to the risk of pre-surgical mortality is rare. This study aims to propose a model ops individual risk of death prediction for cardiac surgery of patients with congenital heart disease and to assist health professionals in understanding which diagnoses or variables are assoaciated with the risk of death. Teh use of machine learning techniques as a tool to suppoort decision making in the field of medicine has been increasing in recent years. With the information on surgeries performed on patients with congenital heart disease extracted from the ASSIST database of InCor, it was possible to rtain six different machine learning algorithms in predictiong the risk of pre-surgical mortality and to understand which variables impact the risk death of these patients. The algorithms trained inthis study were: Miltilayer Perceptron (MLP), Random Forest (RF), Extra Trees (ET), Stochastic Gradient Boosting(SGB), AdaBoost Classification (ABC) and Bagged Decision Trees (BDT). To predict the risk of patient mortality, the model with the best performance was the Random Forest (RF) with ROC AUC (area under the receiver's operating characteritics) of 90,2%, AP indexes (average precision) 0f 0,73 and sensitivity index (recall) mof 92,2%. The machine learning algorithm (machine learning0 can assist in understanding the mortality risks of patients with congenital heart disease when undergoing cardiac surgery and using clinical drugs that understand the best risks associated with surgical interventions, providing information to support the decision, health professionals, patients and their families
Congenital heart disease is the most common cause of major anomalies of the same gender, accounting for almost a third of all major congenital anomalies. Congenital heart defects are serious and common conditions with a significant impact on morbidity, martality and health costs for children and adults. In the treatment of patients with congenital heart disease, research related to the risk of pre-surgical mortality is rare. This study aims to propose a model ops individual risk of death prediction for cardiac surgery of patients with congenital heart disease and to assist health professionals in understanding which diagnoses or variables are assoaciated with the risk of death. Teh use of machine learning techniques as a tool to suppoort decision making in the field of medicine has been increasing in recent years. With the information on surgeries performed on patients with congenital heart disease extracted from the ASSIST database of InCor, it was possible to rtain six different machine learning algorithms in predictiong the risk of pre-surgical mortality and to understand which variables impact the risk death of these patients. The algorithms trained inthis study were: Miltilayer Perceptron (MLP), Random Forest (RF), Extra Trees (ET), Stochastic Gradient Boosting(SGB), AdaBoost Classification (ABC) and Bagged Decision Trees (BDT). To predict the risk of patient mortality, the model with the best performance was the Random Forest (RF) with ROC AUC (area under the receiver's operating characteritics) of 90,2%, AP indexes (average precision) 0f 0,73 and sensitivity index (recall) mof 92,2%. The machine learning algorithm (machine learning0 can assist in understanding the mortality risks of patients with congenital heart disease when undergoing cardiac surgery and using clinical drugs that understand the best risks associated with surgical interventions, providing information to support the decision, health professionals, patients and their families