An Improved Machine-Learning Approach for COVID-19 Prediction Using Harris Hawks Optimization and Feature Analysis Using SHAP

Article


Debjit, Kumar, Islam, Md Saiful, Rahman, Md. Abadur, Pinki, Farhana Tazmim, Nath, Rajan Dev, Al-Ahmadi, Saad, Hossain, Md. Shahadat, Mumenin, Khondoker Mirazul and Awal, Md. Abdul. 2022. "An Improved Machine-Learning Approach for COVID-19 Prediction Using Harris Hawks Optimization and Feature Analysis Using SHAP." Diagnostics. 12 (5). https://doi.org/10.3390/diagnostics12051023
Article Title

An Improved Machine-Learning Approach for COVID-19 Prediction Using Harris Hawks Optimization and Feature Analysis Using SHAP

ERA Journal ID212275
Article CategoryArticle
AuthorsDebjit, Kumar, Islam, Md Saiful, Rahman, Md. Abadur, Pinki, Farhana Tazmim, Nath, Rajan Dev, Al-Ahmadi, Saad, Hossain, Md. Shahadat, Mumenin, Khondoker Mirazul and Awal, Md. Abdul
Journal TitleDiagnostics
Journal Citation12 (5)
Article Number1023
Number of Pages19
Year2022
PublisherMDPI AG
Place of PublicationSwitzerland
ISSN2075-4418
Digital Object Identifier (DOI)https://doi.org/10.3390/diagnostics12051023
Web Address (URL)https://www.mdpi.com/2075-4418/12/5/1023
Abstract

A healthcare monitoring system needs the support of recent technologies such as artificial intelligence (AI), machine learning (ML), and big data, especially during the COVID-19 pandemic. This global pandemic has already taken millions of lives. Both infected and uninfected people have generated big data where AI and ML can use to combat and detect COVID-19 at an early stage. Motivated by this, an improved ML framework for the early detection of this disease is proposed in this paper. The state-of-the-art Harris hawks optimization (HHO) algorithm with an improved objective function is proposed and applied to optimize the hyperparameters of the ML algorithms, namely HHO-based eXtreme gradient boosting (HHOXGB), light gradient boosting (HHOLGB), categorical boosting (HHOCAT), random forest (HHORF) and support vector classifier (HHOSVC). An ensemble technique was applied to these optimized ML models to improve the prediction performance. Our proposed method was applied to publicly available big COVID-19 data and yielded a prediction accuracy of 92.38% using the ensemble model. In contrast, HHOXGB provided the highest accuracy of 92.23% as a single optimized model. The performance of the proposed method was compared with the traditional algorithms and other ML-based methods. In both cases, our proposed method performed better. Furthermore, not only the classification improvement, but also the features are analyzed in terms of feature importance calculated by SHapely adaptive exPlanations (SHAP) values. A graphical user interface is also discussed as a potential tool for nonspecialist users such as clinical staff and nurses. The processed data, trained model, and codes related to this study are available at GitHub.

Keywordsbig COVID-19 data; healthcare; decision support system; machine learning; HHO
Byline AffiliationsUniversity of Southern Queensland
King Saud University, Saudi Arabia
Southern Cross University
Khulna University, Bangladesh
International University of Business Agriculture and Technology, Bangladesh
Permalink -

https://research.usq.edu.au/item/z01x5/an-improved-machine-learning-approach-for-covid-19-prediction-using-harris-hawks-optimization-and-feature-analysis-using-shap

Download files


Published Version
diagnostics-12-01023.pdf
License: CC BY 4.0
File access level: Anyone

  • 29
    total views
  • 24
    total downloads
  • 0
    views this month
  • 0
    downloads this month

Export as

Related outputs

HGSOXGB: Hunger-Games-Search-Optimization-Based Framework to Predict the Need for ICU Admission for COVID-19 Patients Using eXtreme Gradient Boosting
Pinki, Farhana Tazmim, Awal, Md Abdul, Mumenin, Khondoker Mirazu, Hossain, Md. Shahadat, Faysal, Jabed Al, Rana, Rajib, Almuqren, Rajib, Ksibi, Amel and Samad, Md Abdus. 2023. "HGSOXGB: Hunger-Games-Search-Optimization-Based Framework to Predict the Need for ICU Admission for COVID-19 Patients Using eXtreme Gradient Boosting." Mathematics. 11 (18). https://doi.org/10.3390/math11183960
Psychosocial health of school-going adolescents during the COVID-19 pandemic: Findings from a nationwide survey in Bangladesh
Koly, Kamrun Nahar, Islam, Md. Saiful, Potenza, Marc N., Mahumud, Rashidul Alam, Islam, Md. Shefatul, Uddin, Md. Salim, Sarwa, Md. Afzal Hossain, Begum, Farzana and Reidpath, Daniel D.. 2023. "Psychosocial health of school-going adolescents during the COVID-19 pandemic: Findings from a nationwide survey in Bangladesh." PLoS One. 18 (3). https://doi.org/10.1371/journal.pone.0283374
Silk fibers and their unidirectional polymer composites
Ahmed, Mansur, Islam, Md Saiful, Ahsan, Qumrul and Islam, Md Mainul. 2012. "Silk fibers and their unidirectional polymer composites." Thomas, Sabu, Ninan, Neethu, Mohan, Mohan and Francis, Elizabeth (ed.) Natural polymers, biopolymers, biomaterials, and their composites, blends, and IPNs. Oakville, ON. Canada . Apple Academic Press (CRC Press). pp. 79-90
Fabrication and characterization of unidirectional silk fibre composites
Ahmed, Mansur, Islam, Md Saiful, Ahsan, Qumrul and Islam, Md Mainul. 2011. "Fabrication and characterization of unidirectional silk fibre composites." Key Engineering Materials. 471-472 (1), pp. 20-25. https://doi.org/10.4028/www.scientific.net/KEM.471-472.20
Physical and tensile properties of raw and treated silk fibres
Ahmed, Mansur, Islam, Md Saiful, Ahsan, Qumrul and Islam, Md Mainul. 2010. "Physical and tensile properties of raw and treated silk fibres." 2nd International Conference on Natural Polymers, Bio-Polymers, Bio-Materials, their Composites, Blends, IPN's and Gels Polyelectrolytes and Gels: Macro to Nano Scales (ICNP - 2010). Kottayam, India 24 - 26 Sep 2010 India.