Maximum Value Attribute based Decision Tree and Random Forest for COVID-19 Prediction
International Journal of Innovations in Science and Technology · 28.11.2025 · 2940
DOI: 10.33411/ijist/1659 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovations in Science and Technology, online erschienen am 28.11.2025. Verfasst von Khurram Gulzar und 5 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The Corona Virus Disease2019 (COVID-19) is the most threatening disease of thepresentcenturythatdisturbedthewholeworldfromaneconomicandlife perspective.TheincreasednumberofpositiveCOVID-19patientsputthe healthsectorunderstresstotackletheoutbreakofthisvirus.Inthecurrentdecade,the usage of Machine Learning (ML) in medical science has increased, particularly in thedetectionofHeartfailure,Pneumonia,Dengue,Breastcancer,andDiabetes. Similarly, the COVID-19 symptoms can be utilized for an early prediction of COVID-19toreducethespreadrateofinfectioninsociety.SeveralMLtechniques detectedtheCOVID-19disease,andensemble-basedmethodslikeDecisionTree and Random Forest perform well in terms of accuracy as compared to other standardclassifiers.However,theexecutiontimeanditerationsarethemajorareasof concern for these ensemble-based methods,as early and timely detection of COVID-19canreduceitsinfectionrate.Inthisstudy,themainfocusison the identificationoffatalCoronavirususingMLtechniques.Forthatpurpose,Rough Set Theory(RST)based Maximum Value Attribute(MVA)is integrated with classical Decision Tree(DT)andRandomForesttoefficientlypredictCOVID-19 in terms of time and iterations. The proposed model can detect the result ofCOVID-19asnegativeorpositiveonthe eight basic relevant clinical symptoms. Accordingly,theperformanceofclassicalDTandRFclassifiersisenhancedby integrating MVA. ML models are implemented to evaluate the model performanceoverclinicalsymptomsof136294COVID-19patients.Theinformation is extracted from the open-source GitHub website. Based on the symptoms of the COVID-19dataset,fourMLmodels,DT,RF,MaximumValueAttribute-based Decision Tree (MVA-DT), and Maximum Value Attribute-based Random Forest(MVA-RF)were implemented in Jupyter Notebook via Python repository to forecast the result of COVID-19. Standard performance parameters of the classificationprocessareconsideredtotestmodelreliabilityagainstthepredictionof COVID-19.Fromthetimeanditerationperspective,theproposedMVA-DTout-performedtheotherthreemodels,andthe MVA-RFtechniquepredictedCOVID-19 diseasecomparativelybetter,having95.82%accuracy,81.90%precision,59.28% recall, and 68.77% F1 score.
Zitieren
APA
Gulzar, K., Hassan, B. A., Abbas, M., Ahmad, Z., Anis, M., & Ullah, H. (2025). Maximum Value Attribute based Decision Tree and Random Forest for COVID-19 Prediction. International Journal of Innovations in Science and Technology, 2940. https://doi.org/10.33411/ijist/1659
Vancouver
Gulzar K, Hassan BA, Abbas M, Ahmad Z, Anis M, Ullah H. Maximum Value Attribute based Decision Tree and Random Forest for COVID-19 Prediction. International Journal of Innovations in Science and Technology. 2025:2940. doi:10.33411/ijist/1659
BibTeX
@article{Gulzar2025,
author = {Gulzar, Khurram and Hassan, Basharat Ahmad and Abbas, Muhammad and Ahmad, Zubair and Anis, Muhammad and Ullah, Hasnat},
title = {Maximum Value Attribute based Decision Tree and Random Forest for COVID-19 Prediction},
journal = {International Journal of Innovations in Science and Technology},
year = {2025},
pages = {2940},
doi = {10.33411/ijist/1659}
}
EUVIMED