Aortocoronary bypass surgery is an open-heart procedure that involves a significant hospital stay and therefore an increase in costs. Length of stay (LOS) is an important parameter for monitoring patients and is a useful tool for doctors and hospital administrators to assess the efficiency of the hospital. For the correct management of beds and to reduce costs, it is necessary to analyze and evaluate the procedures for reducing hospital admissions. This study was conducted with the aim of predicting LOS for all patients undergoing aortocoronary bypass surgery in the University Hospital “San Giovanni di Dio e Ruggi d’Aragona” of Salerno (Italy) and the A.O.R.N. “Antonio Cardarelli” of Naples (Italy). The analysis was conducted with the implementation of Machine Learning algorithms: Decision Tree (DT), Random Forest (RF) and Gradient Boosted Trees (GBT). Accuracy and error have been analyzed to demonstrate the accuracy of the model.
Machine Learning Algorithms to Predict LOS in Patients Undergoing Heart Bypass Surgery: A Bicentric Study / Scala, A.; Marino, M. R.; Giglio, C.; Majolo, M.; Longo, G.; Ferrucci, G.; Borrelli, A.; Triassi, M.. - 13637 LNBI:(2023), pp. 375-383. (Intervento presentato al convegno International Symposium on Biomedical and Computational Biology) [10.1007/978-3-031-25191-7_33].
Machine Learning Algorithms to Predict LOS in Patients Undergoing Heart Bypass Surgery: A Bicentric Study
Scala A.Primo
;Majolo M.;Triassi M.Ultimo
2023
Abstract
Aortocoronary bypass surgery is an open-heart procedure that involves a significant hospital stay and therefore an increase in costs. Length of stay (LOS) is an important parameter for monitoring patients and is a useful tool for doctors and hospital administrators to assess the efficiency of the hospital. For the correct management of beds and to reduce costs, it is necessary to analyze and evaluate the procedures for reducing hospital admissions. This study was conducted with the aim of predicting LOS for all patients undergoing aortocoronary bypass surgery in the University Hospital “San Giovanni di Dio e Ruggi d’Aragona” of Salerno (Italy) and the A.O.R.N. “Antonio Cardarelli” of Naples (Italy). The analysis was conducted with the implementation of Machine Learning algorithms: Decision Tree (DT), Random Forest (RF) and Gradient Boosted Trees (GBT). Accuracy and error have been analyzed to demonstrate the accuracy of the model.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
