Machine Learning Models for Predicting Length of Stay and Disposition Decisions in Emergency Depts. скачать в хорошем качестве

Machine Learning Models for Predicting Length of Stay and Disposition Decisions in Emergency Depts.

Speaker: Dr Long Song (University of Melbourne) Title: Developing Interpretable Machine Learning Models for Predicting Length of Stay and Disposition Decisions in Emergency Departments Summary: In this seminar, I will present the development and evaluation of interpretable machine learning models designed to predict patient Length of Stay (LOS) and Disposition Decisions (DD) in Emergency Departments (ED). By leveraging comprehensive data preprocessing and feature selection techniques, we created models that offer robust performance while remaining interpretable for clinical use. The seminar will highlight the importance of transparency in model development, and how these models can aid clinicians in decision-making processes by providing actionable insights into patient flow management. Biography: Dr Long Song is a Research Fellow at The University of Melbourne in the School of Computing and Information Systems, under the supervision of Prof. Uwe Aickelin. After completing his PhD in computer science at Wuhan University, he had many years of industrial and academic experiences. His interests include machine learning, disease prediction using machine learning methods, genomic data analysis, and bioinformatics.