A Machine Learning Approach for Monitoring and Classifying Healthcare Data-A Case of Emergency Department of KSA Hospitals

Abstract

The Emergency Departments (EDs), in hospitals located in a few important areas in Saudi Arabia, experience a heavy inflow of patients due to viral illnesses, pandemics, and even on a few special occasions events such as Hajj or Umrah, when pilgrims travel from one region to another with severe disease conditions. Apart from the EDs, it is critical to monitor the movements of patients from EDs to other wards inside the hospital or in the region. This is to track the spread of viral illnesses that require more attention. In this scenario, Machine Learning (ML) algorithms can be used to classify the data into many classes and track the target audience. The current research article presents a Machine Learning-based Medical Data Monitoring and Classification Model for the EDs of the KSA hospitals and is named MLMDMC-ED technique. The most important aim of the proposed MLMDMC-ED technique is to monitor and track the patient's visits to the EDs, the treatment given to them based on the Canadian Emergency Department Triage and Acuity Scale (CTAS), and their Length Of Stay (LOS) in the hospital, based on their treatment requirements. A patient's clinical history is crucial in terms of making decisions during health emergencies or pandemics. So, the data should be processed so that it can be classified and visualized in different formats using the ML technique. The current research work aims at extracting the textual features from the patients' data using the metaheuristic Non-Defeatable Genetic Algorithm II (NSGA II). The data, collected from the hospitals, are classified using the Graph Convolutional Network (GCN) model. Grey Wolf Optimizer (GWO) is exploited for fine-tuning the parameters to optimize the performance of the GCN model. The proposed MLMDMC-ED technique was experimentally validated on the healthcare data and the outcomes indicated the improvements of the MLMDMC-ED technique over other models with a maximum accuracy of 91.87%.

Keywords: emergency department; feature selection; healthcare system; hyperparameter tuning; machine learning; metaheuristics.

Figure 1

Emergency Department Process.

Figure 2

Working procedure of the MLMDMC-ED system.

Figure 3

Flowchart of NSGA II Algorithm.

Figure 4

Confusion matrices of MLMDMC-ED method on Cleveland dataset (a,b) TR and TS database of 80:20 and (c,d) TR and TS database of 70:30.

Figure 5

Average analysis results of the MLMDMC-ED algorithm on the Cleveland dataset.

Figure 6

$T{R}_{acc}$ and $V{L}_{acc}$ analyse the results of the MLMDMC-ED algorithm on the Cleveland dataset.

Figure 7

$T{R}_{loss}$ and $V{L}_{loss}$ analysis results of the MLMDMC-ED algorithm on the Cleveland dataset.

Figure 8

Confusion matrices of MLMDMC-ED method under Statlog dataset (a,b) TR and TS database of 80:20 and (c,d) TR and TS database of 70:30.

Figure 9

Average analysis results of the MLMDMC-ED algorithm upon Statlog dataset.

Figure 10

$T{R}_{acc}$ and $V{L}_{acc}$ analyse the results of the MLMDMC-ED algorithm on the Statlog dataset.

Figure 11

$T{R}_{loss}$ and $V{L}_{loss}$ analyses results of the MLMDMC-ED algorithm on the Statlog dataset.

Figure 12

Accuracy analysis outcomes of the proposed MLMDMC-ED algorithm and other recent algorithms.