Performance Analysis for the Diagnosis of COVID-19 Prediction by Mathematical Modeling & Simulation
Abstract
Machine learning is a type of artificial intelligence (AI) method. The system can be conscious and adaptable to changes in concepts when emphatically programmed for presence based on prior experience. The study built and examined several sorts of ML algorithms in this work by creating a classifier depending on a predefined model to estimate COVID-19. The ML approach might be used in any sector of medicine, including diagnostics. COVID-19 forecast research is still needed, and there is a need to improve the diagnostic COVID-19 methodology. Several investigations have varied objectives regarding COVID-19 estimation methods that employ techniques. The purpose of this effort was to provide an integrative strategy to enhance the accuracy, precision, and recall of the COVID-19 proposed method. This study supports the utilization of ML and DL approaches. It is an essential element in the analysis of ML approaches such as K-Means and is applied to both supervised and unsupervised learning concepts. Several of these ML algorithms use various approaches to examine and perform the Decision Tree ,Naive Bayes and Multi-Layer Perceptron algorithms. Equivalent data sets were examined for clustering and classification approaches, including K-Means techniques. It was demonstrated that outcomes could be foreseen that were efficient, effective, and accurate.The best algorithmic outcome for COVID-19 case detection was achieved by combining K-Means with Multi-Layer Perceptrons (MLPs), resulting in an accuracy of 99.88%.
References
[2] Amara, Sara Aicha, Estefany Daniella Díaz, Lakshmi Krishna Menon, Priyanka Singh, Liudmila Rozanova, and Antoine Flahault. "COVID-19 Outbreak Management and Vaccination Strategy in The United States of America." Epidemiologia 2, no. 3 (2021): 426-453.
[3] Simoes, Eduardo J., and Jeannette Jackson-Thompson. "The United States public health services failure to control the coronavirus epidemic." Preventive Medicine Reports (2022): 102090.
[4] Benchimol-Elkaim, Brandon, Scott Dryden-Peterson, Donald R. Miller, Howard K. Koh, and Alan C. Geller. "Oral Antiviral Therapy Utilization Among Adults with Recent COVID-19 in the United States." Journal of General Internal Medicine (2023): 1-5.
[5] Benchimol-Elkaim, Brandon, Scott Dryden-Peterson, Donald R. Miller, Howard K. Koh, and Alan C. Geller. "Oral Antiviral Therapy Utilization Among Adults with Recent COVID-19 in the United States." Journal of General Internal Medicine (2023): 1-5.
[6] Nurmaini, Siti, Alexander Edo Tondas, Radiyati Umi Partan, Muhammad Naufal Rachmatullah, Annisa Darmawahyuni, Firdaus Firdaus, Bambang Tutuko, Rachmat Hidayat, and Ade Iriani Sapitri. "Automated Detection of COVID-19 Infected Lesion on Computed Tomography Images Using Faster-RCNNs." Engineering Letters 28, no. 4 (2020).
[7] Tostmann, Alma, John Bradley, Teun Bousema, Wing-Kee Yiek, Minke Holwerda, Chantal Bleeker-Rovers, Jaap Ten Oever et al. "Strong associations and moderate predictive value of early symptoms for SARS-CoV-2 test positivity among healthcare workers, the Netherlands, March 2020." Eurosurveillance 25, no. 16 (2020): 2000508.
[8] Punn, Narinder Singh, Sanjay Kumar Sonbhadra, Sonali Agarwal, and Gaurav Rai. "Monitoring COVID-19 social distancing with person detection and tracking via fine-tuned YOLO v3 and Deepsort techniques." arXiv preprint arXiv:2005.01385 (2020).
[9] Mei, Xueyan, Hao-Chih Lee, Kai-yue Diao, Mingqian Huang, Bin Lin, Chenyu Liu, Zongyu Xie et al. "Artificial intelligence–enabled rapid diagnosis of patients with COVID-19." Nature medicine 26, no. 8 (2020): 1224-1228.
[10] Feng, Cong, Lili Wang, Xin Chen, Yongzhi Zhai, Feng Zhu, Hua Chen, Yingchan Wang et al. "A Novel triage tool of artificial intelligence-assisted diagnosis aid system for suspected COVID-19 pneumonia in fever clinics." MedRxiv (2020): 2020-03.
