Genetic Programming for Classifying Data of Patients Infected with COVID-19

• Gianni R. S. Da Conceição UFRJ
• Camila S. De Magalhães UFRJ

DOI: https://doi.org/10.5753/ercas.2024.238720

Abstract

In this work, a Genetic Programming (GP) algorithm was developed to classify a database of COVID-19 infected patients. The algorithm presented about 85% of accuracy in predicting the disease prognosis based on symptoms, potentially serving as a valuable tool for prioritizing hospitalizations and identifying the main factors that may lead to mortality. Additionally, the algorithm was tested on reference datasets to validate its generalization capability, obtaining competitive results.

References

Cheruku, R., Edla, D. R., Kuppili, V., and Dharavath, R. (2018). Rst-batminer: A fuzzy rule miner integrating rough set feature selection and bat optimization for detection of diabetes disease. Applied Soft Computing, 67:764–780.

Dua, D. and Graff, C. (2019). Uci machine learning repository [link]. IEEE transactions on pattern analysis and machine intelligence, 1(1):1–29.

Eiben, A. E. and Smith, J. E. (2015). Introduction to evolutionary computing. Springer.

Harik, G. (1995). Finding multimodal solutions using restricted tournament selection.

Hu, T. (2023). Genetic Programming for Interpretable and Explainable Machine Learning. Springer Nature Singapore, Singapore.

Xu, B. et al. (2020). Epidemiological data from the covid-19 outbreak, real-time case information. Scientific data, 7(1):106.