Seminário do Programa de Doutoramento em Engenharia Biomédica da aluna Nafiseh Mollaei

Seminário do Programa de Doutoramento em Engenharia Biomédica

Length of Stay Prediction in Acute Intensive Care Unit in Cardiothoracic Surgery Patients

Nafiseh Mollaei

2ª, 21 de março de 2022-14h

Abstract:

The goal of this study was to apply machine learning (ML) methods to predict the Length of Stay in an Intensive Care Unit (LOS-ICU) based on preoperative factors. To optimize the capacity of the ICU in surgery department, the prediction of a long stay (more than 2 days) can support the clinical decision making on accepting or delaying a patient intervention, considering the ICU occupancy. A database with records from 7364 patients that were operated in the Cardiothoracic surgery department of a public Portuguese hospital was used as the base of ML algorithms training. Regarding the risk of the patients to be in the group of long LOS-ICU, we compared five machine learning algorithms including Gradient Boosting, Random Forest, Support Vector Machine (SVM), Adaboost and Logistic Regression. We studied the classifier performance to adjust the sensitivity of a long stay classification, in order to reduce the potential of long LOS-ICU classification being miss classified as a short LOS-ICU. About the author: Nafiseh Mollaei is a PhD student in Biomedical Engineering at the Science and Technology department of NOVA University of Lisbon. During her master’s degree, she had experience working with Diabetes patients. Currently, she is working in the domain of diagnosis and prognosis of occupational disorder at Volkswagen as a part of her doctoral thesis.Besides, she also cooperated in the Cardiothoracic surgery department to apply machine learning (ML) methods to predict the Length of Stay in an Intensive Care Unit (LOS-ICU) based on preoperative factors. Hence, In order to optimize the capacity of the ICU in the surgery department, predicting a long stay (more than 2 days) can help clinicians decide whether to accept or postpone a patient intervention based on ICU occupancy.