Title | ||
---|---|---|
A Deep Learning Approach for Classifying Patient Attendance Disposal from Emergency Departments |
Abstract | ||
---|---|---|
In recent years, the non-urgent patient treatment at the Accident and Emergency (A&E) departments becomes an ever-increasing research topic. Due to a large number of unplanned admissions at the A&E departments, it is of vital importance to study the classification of the patient attendance disposal with the hope to improve the medical treatment and to save the costs of human and medical resources at the A&E departments. In our work, a popular deep neural network called the deep belief network (DBN) is employed to analyse the patient attendance data from a local A&E department in London, UK. For comparison, two traditional classification algorithms, the k-nearest neighbour (KNN) and the artificial neural network (ANN) approaches are also applied to the patient classification problem for data analysis. Experiment results demonstrate that the DBN outperforms both the KNN and ANN approaches in terms of the classification accuracy. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICCA.2019.8899730 | 2019 IEEE 15th International Conference on Control and Automation (ICCA) |
Keywords | Field | DocType |
human resources,medical resources,A&E departments,deep neural network,deep belief network,DBN,patient attendance data,artificial neural network approaches,patient classification problem,ANN approaches,deep learning approach,emergency departments,nonurgent patient treatment,unplanned admissions,medical treatment,patient attendance disposal classification,accident and emergency departments,London,UK,k-nearest neighbour,KNN | Deep belief network,Control engineering,Medical treatment,Artificial intelligence,Engineering,Deep learning,Statistical classification,Artificial neural network,Attendance,Machine learning,Patient treatment | Conference |
ISSN | ISBN | Citations |
1948-3449 | 978-1-7281-1165-0 | 0 |
PageRank | References | Authors |
0.34 | 8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Weibo Liu | 1 | 520 | 16.88 |
Zidong Wang | 2 | 11003 | 578.11 |
Liang Hu | 3 | 0 | 0.34 |
Xiaohui Liu | 4 | 5042 | 269.99 |