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

被引:24
|
作者
Debjit, Kumar [1 ]
Islam, Md Saiful [2 ]
Rahman, Md. Abadur [3 ]
Pinki, Farhana Tazmim [4 ]
Nath, Rajan Dev [5 ]
Al-Ahmadi, Saad [2 ]
Hossain, Md. Shahadat [6 ]
Mumenin, Khondoker Mirazul [7 ]
Awal, Md. Abdul [7 ]
机构
[1] Univ Southern Queensland, Fac Hlth Engn & Sci, Toowoomba, Qld 4350, Australia
[2] King Saud Univ, Coll Comp & Informat Sci, Dept Comp Sci, Riyadh 11543, Saudi Arabia
[3] Southern Cross Univ, Fac Sci & Engn, East Lismore, NSW 2480, Australia
[4] Khulna Univ KU, Comp Sci & Engn Discipline CSE, Khulna 9208, Bangladesh
[5] Univ Southern Queensland, Sch Commerce, Fac Business Educ Law & Arts, Darling Heights, Qld 4350, Australia
[6] Int Univ Business Agr & Technol, Dept Quantitat Sci, Dhaka 1230, Bangladesh
[7] Khulna Univ KU, Elect & Commun Engn ECE Discipline, Khulna 9208, Bangladesh
关键词
big COVID-19 data; HHO; machine learning; decision support system; healthcare;
D O I
10.3390/diagnostics12051023
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
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.
引用
收藏
页数:19
相关论文
共 50 条
  • [1] Analysis and Prediction of COVID-19 using Machine Learning
    Parthiban, M.
    Alphy, Anna
    2024 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATION AND APPLIED INFORMATICS, ACCAI 2024, 2024,
  • [2] Detection of COVID-19 severity using blood gas analysis parameters and Harris hawks optimized extreme learning machine
    Hu, Jiao
    Han, Zhengyuan
    Heidari, Ali Asghar
    Shou, Yeqi
    Ye, Hua
    Wang, Liangxing
    Huang, Xiaoying
    Chen, Huiling
    Chen, Yanfan
    Wu, Peiliang
    COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 142
  • [3] Pandemic coronavirus disease (Covid-19): World effects analysis and prediction using machine-learning techniques
    Tiwari, Dimple
    Bhati, Bhoopesh Singh
    Al-Turjman, Fadi
    Nagpal, Bharti
    EXPERT SYSTEMS, 2022, 39 (03)
  • [4] Coronavirus disease (COVID-19) cases analysis using machine-learning applications
    Kwekha-Rashid, Ameer Sardar
    Abduljabbar, Heamn N.
    Alhayani, Bilal
    APPLIED NANOSCIENCE, 2021, 13 (3) : 2013 - 2025
  • [5] Coronavirus disease (COVID-19) cases analysis using machine-learning applications
    Ameer Sardar Kwekha-Rashid
    Heamn N. Abduljabbar
    Bilal Alhayani
    Applied Nanoscience, 2023, 13 : 2013 - 2025
  • [6] Prediction of Covid-19 and post Covid-19 patients with reduced feature extraction using Machine Learning Techniques
    Bano, Shehr
    Hussain, Syed Fawad
    2021 INTERNATIONAL CONFERENCE ON FRONTIERS OF INFORMATION TECHNOLOGY (FIT 2021), 2021, : 37 - 42
  • [7] Analysis and Prediction of COVID-19 Data using Machine Learning Models
    Chrin, Richvichanak
    Wang, Sujing
    ACM International Conference Proceeding Series, 2021, : 296 - 301
  • [8] COVID-19 Prediction model using Machine Learning
    Jadi, Amr
    INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2021, 21 (08): : 247 - 253
  • [9] Prediction of COVID-19 severity using machine learning
    Karaduzovic-Hadziabdic, Kanita
    Adilovic, Muhamed
    Zhang, Lu
    Lumley, Andrew, I
    Shah, Pranay
    Shoaib, Muhammad
    Satagopam, Venkata
    Srivastava, Prashant Kumar
    Emanueli, Costanza
    Greco, Simona
    Made, Alisia
    Padro, Teresa
    Domingo, Pedro
    Lustrek, Mitja
    Scholz, Markus
    Rosolowski, Maciej
    Jordan, Marko
    Benczik, Bettina
    Agg, Bence
    Ferdinandy, Peter
    Baker, Andrew H.
    Fagherazzi, Guy
    Ollert, Markus
    Michel, Joanna
    Sanchez, Gabriel
    Firat, Hueseyin
    Brandenburger, Timo
    Martelli, Fabio
    Badimon, Lina
    Devaux, Yvan
    CLINICAL AND TRANSLATIONAL MEDICINE, 2024, 14 (10):
  • [10] Deep learning model optimization for crop prediction and recommendation using Harris Hawks optimization
    Latha, P.
    Kumaresan, P.
    ENVIRONMENTAL RESEARCH COMMUNICATIONS, 2025, 7 (04):