HGSOXGB: Hunger-Games-Search-Optimization-Based Framework to Predict the Need for ICU Admission for COVID-19 Patients Using eXtreme Gradient Boosting
Millions of people died in the COVID-19 pandemic, which pressured hospitals and healthcare workers into keeping up with the speed and intensity of the outbreak, resulting in a scarcity of ICU beds for COVID-19 patients. Therefore, researchers have developed machine learning (ML) algorithms to assist...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/18/3960 |
| _version_ | 1797578951344783360 |
|---|---|
| author | Farhana Tazmim Pinki Md Abdul Awal Khondoker Mirazul Mumenin Md. Shahadat Hossain Jabed Al Faysal Rajib Rana Latifah Almuqren Amel Ksibi Md Abdus Samad |
| author_facet | Farhana Tazmim Pinki Md Abdul Awal Khondoker Mirazul Mumenin Md. Shahadat Hossain Jabed Al Faysal Rajib Rana Latifah Almuqren Amel Ksibi Md Abdus Samad |
| author_sort | Farhana Tazmim Pinki |
| collection | DOAJ |
| description | Millions of people died in the COVID-19 pandemic, which pressured hospitals and healthcare workers into keeping up with the speed and intensity of the outbreak, resulting in a scarcity of ICU beds for COVID-19 patients. Therefore, researchers have developed machine learning (ML) algorithms to assist in identifying patients at increased risk of requiring an ICU bed. However, many of these studies used state-of-the-art ML algorithms with arbitrary or default hyperparameters to control the learning process. Hyperparameter optimization is essential in enhancing the classification effectiveness and ensuring the optimal use of ML algorithms. Therefore, this study utilized an improved Hunger Games Search Optimization (HGSO) algorithm coupled with a robust extreme gradient boosting (XGB) classifier to predict a COVID-19 patient’s need for ICU transfer. To further mitigate the random initialization inherent in HGSO and facilitate an efficient convergence toward optimal solutions, the Metropolis–Hastings (MH) method is proposed for integration with HGSO. In addition, population diversity was reintroduced to effectively escape local optima. To evaluate the efficacy of the MH-based HGSO algorithm, the proposed method was compared with the original HGSO algorithm using the Congress on Evolutionary Computation benchmark function. The analysis revealed that the proposed algorithm converges better than the original method and exhibits statistical significance. Consequently, the proposed algorithm optimizes the XGB hyperparameters to further predict the need for ICU transfer for COVID-19 patients. Various evaluation metrics, including the receiver operating curve (ROC), precision–recall curve, bootstrap ROC, and recall vs. decision boundary, were used to estimate the effectiveness of the proposed HGSOXGB model. The model achieves the highest accuracy of 97.39% and an area under the ROC curve of 99.10% compared with other classifiers. Additionally, the important features that significantly affect the prediction of ICU transfer need using XGB were calculated. |
| first_indexed | 2024-03-10T22:29:56Z |
| format | Article |
| id | doaj.art-5cb128c309c94d0281ba03fb54cd13a4 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T22:29:56Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-5cb128c309c94d0281ba03fb54cd13a42023-11-19T11:49:59ZengMDPI AGMathematics2227-73902023-09-011118396010.3390/math11183960HGSOXGB: Hunger-Games-Search-Optimization-Based Framework to Predict the Need for ICU Admission for COVID-19 Patients Using eXtreme Gradient BoostingFarhana Tazmim Pinki0Md Abdul Awal1Khondoker Mirazul Mumenin2Md. Shahadat Hossain3Jabed Al Faysal4Rajib Rana5Latifah Almuqren6Amel Ksibi7Md Abdus Samad8Computer Science and Engineering Discipline, Khulna University, Khulna 9208, BangladeshElectronics and Communication Engineering Discipline, Khulna University, Khulna 9208, BangladeshElectronics and Communication Engineering Discipline, Khulna University, Khulna 9208, BangladeshDepartment of Quantitative Sciences, International University of Business Agriculture and Technology, Dhaka 1230, BangladeshComputer Science and Engineering Discipline, Khulna University, Khulna 9208, BangladeshSchool of Mathematics, Physics and Computing, Springfield Campus, University of Southern Queensland, Springfield Education City, QLD 4300, AustraliaDepartment of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh 11671, Saudi ArabiaDepartment of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh 11671, Saudi ArabiaDepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan-si 38541, Gyeongsangbuk-do, Republic of KoreaMillions of people died in the COVID-19 pandemic, which pressured hospitals and healthcare workers into keeping up with the speed and intensity of the outbreak, resulting in a scarcity of ICU beds for COVID-19 patients. Therefore, researchers have developed machine learning (ML) algorithms to assist in identifying patients at increased risk of requiring an ICU bed. However, many of these studies used state-of-the-art ML algorithms with arbitrary or default hyperparameters to control the learning process. Hyperparameter optimization is essential in enhancing the classification effectiveness and ensuring the optimal use of ML algorithms. Therefore, this study utilized an improved Hunger Games Search Optimization (HGSO) algorithm coupled with a robust extreme gradient boosting (XGB) classifier to predict a COVID-19 patient’s need for ICU transfer. To further mitigate the random initialization inherent in HGSO and facilitate an efficient convergence toward optimal solutions, the Metropolis–Hastings (MH) method is proposed for integration with HGSO. In addition, population diversity was reintroduced to effectively escape local optima. To evaluate the efficacy of the MH-based HGSO algorithm, the proposed method was compared with the original HGSO algorithm using the Congress on Evolutionary Computation benchmark function. The analysis revealed that the proposed algorithm converges better than the original method and exhibits statistical significance. Consequently, the proposed algorithm optimizes the XGB hyperparameters to further predict the need for ICU transfer for COVID-19 patients. Various evaluation metrics, including the receiver operating curve (ROC), precision–recall curve, bootstrap ROC, and recall vs. decision boundary, were used to estimate the effectiveness of the proposed HGSOXGB model. The model achieves the highest accuracy of 97.39% and an area under the ROC curve of 99.10% compared with other classifiers. Additionally, the important features that significantly affect the prediction of ICU transfer need using XGB were calculated.https://www.mdpi.com/2227-7390/11/18/3960COVID-19ICU predictioneXtreme gradient boostinghunger games search optimizationMetropolis–Hastings |
| spellingShingle | Farhana Tazmim Pinki Md Abdul Awal Khondoker Mirazul Mumenin Md. Shahadat Hossain Jabed Al Faysal Rajib Rana Latifah Almuqren Amel Ksibi Md Abdus Samad HGSOXGB: Hunger-Games-Search-Optimization-Based Framework to Predict the Need for ICU Admission for COVID-19 Patients Using eXtreme Gradient Boosting Mathematics COVID-19 ICU prediction eXtreme gradient boosting hunger games search optimization Metropolis–Hastings |
| title | HGSOXGB: Hunger-Games-Search-Optimization-Based Framework to Predict the Need for ICU Admission for COVID-19 Patients Using eXtreme Gradient Boosting |
| title_full | HGSOXGB: Hunger-Games-Search-Optimization-Based Framework to Predict the Need for ICU Admission for COVID-19 Patients Using eXtreme Gradient Boosting |
| title_fullStr | HGSOXGB: Hunger-Games-Search-Optimization-Based Framework to Predict the Need for ICU Admission for COVID-19 Patients Using eXtreme Gradient Boosting |
| title_full_unstemmed | HGSOXGB: Hunger-Games-Search-Optimization-Based Framework to Predict the Need for ICU Admission for COVID-19 Patients Using eXtreme Gradient Boosting |
| title_short | HGSOXGB: Hunger-Games-Search-Optimization-Based Framework to Predict the Need for ICU Admission for COVID-19 Patients Using eXtreme Gradient Boosting |
| title_sort | hgsoxgb hunger games search optimization based framework to predict the need for icu admission for covid 19 patients using extreme gradient boosting |
| topic | COVID-19 ICU prediction eXtreme gradient boosting hunger games search optimization Metropolis–Hastings |
| url | https://www.mdpi.com/2227-7390/11/18/3960 |
| work_keys_str_mv | AT farhanatazmimpinki hgsoxgbhungergamessearchoptimizationbasedframeworktopredicttheneedforicuadmissionforcovid19patientsusingextremegradientboosting AT mdabdulawal hgsoxgbhungergamessearchoptimizationbasedframeworktopredicttheneedforicuadmissionforcovid19patientsusingextremegradientboosting AT khondokermirazulmumenin hgsoxgbhungergamessearchoptimizationbasedframeworktopredicttheneedforicuadmissionforcovid19patientsusingextremegradientboosting AT mdshahadathossain hgsoxgbhungergamessearchoptimizationbasedframeworktopredicttheneedforicuadmissionforcovid19patientsusingextremegradientboosting AT jabedalfaysal hgsoxgbhungergamessearchoptimizationbasedframeworktopredicttheneedforicuadmissionforcovid19patientsusingextremegradientboosting AT rajibrana hgsoxgbhungergamessearchoptimizationbasedframeworktopredicttheneedforicuadmissionforcovid19patientsusingextremegradientboosting AT latifahalmuqren hgsoxgbhungergamessearchoptimizationbasedframeworktopredicttheneedforicuadmissionforcovid19patientsusingextremegradientboosting AT amelksibi hgsoxgbhungergamessearchoptimizationbasedframeworktopredicttheneedforicuadmissionforcovid19patientsusingextremegradientboosting AT mdabdussamad hgsoxgbhungergamessearchoptimizationbasedframeworktopredicttheneedforicuadmissionforcovid19patientsusingextremegradientboosting |