APPLYING HUNGER GAME SEARCH (HGS) FOR SELECTING SIGNIFICANT BLOOD INDICATORS FOR EARLY PREDICTION OF ICU COVID-19 SEVERITY
| Autor: | Safynaz Sayed, Abeer ElKorany, Sabah Sayed |
|---|---|
| Rok vydání: | 2023 |
| Předmět: | |
| Zdroj: | Computer Science. 24 |
| ISSN: | 2300-7036 1508-2806 |
| DOI: | 10.7494/csci.2023.24.1.4654 |
| Popis: | Millions of people around the world have been affected and some have died during the global pandemic Corona (COVID-19). This pandemic has created a global threat to people's lives and medical systems. The constraints of hospital resources and the pressures on healthcare workers during this period are among the reasons for wrong decisions and medical deterioration. Anticipating severe patients is an urgent matter of resource consumption by prioritizing patients at high risk to save their lives. This paper introduces an early prognostic model to predict the severity of patients and detect the most significant features based on clinical blood data. The proposed model predicts ICU severity within the first 2 hours of hospital admission, seeks to assist clinicians in decision-making and facilitates efficient use of hospital resources. The Hunger Game Search (HGS) meta-heuristic algorithm and the SVM are hybridized for building the proposed prediction model. Furthermore, they have been used for selecting the most informative features from the blood test data. Experiments have shown that using HGS for selecting the features with the SVM classifier achieved excellent results compared with the other four meta-heuristic algorithms. The model using the features selected by the HGS algorithm accomplished the topmost results, 98.6% and 96.5% for the best and mean accuracy, respectively, compared with using all features and features selected by other popular optimization algorithms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|