Machine learning approaches in Covid-19 severity risk prediction in Morocco

Journal of Big Data

Mariam Naciri¹  Mariam Laatifi¹  Hind Ezzine¹  Younes Zaid²  Bouabid El Ouahidi³  Samira Douzi⁴  Jaafar Jaafari⁵  Abdelaziz Bouklouz⁶ 

[1] Department of Biology, Faculty of Sciences, Mohammed V University, Rabat, Morocco;Department of Biology, Faculty of Sciences, Mohammed V University, Rabat, Morocco;Research Center of Abulcasis University of Health Sciences, Cheikh Zaïd Hospital, Rabat, Morocco;Department of Computer Science, Faculty of Sciences, Mohammed V University, Rabat, Morocco;FMPR, University Mohammed V, Rabat, Morocco;FSTM, University Hassan II, Casablanca, Morocco;Laboratory of Pharmacology and Toxicology, Faculty of Medicine and Pharmacy, Rabat, Morocco;

关键词: COVID-19;    Severity;    Machine learning;    Feature selection;    Feature reduction;    Data analysis;   

DOI  :  10.1186/s40537-021-00557-0

来源: Springer

【 摘 要 】

The purpose of this study is to develop and test machine learning-based models for COVID-19 severity prediction. COVID-19 test samples from 337 COVID-19 positive patients at Cheikh Zaid Hospital were grouped according to the severity of their illness. Ours is the first study to estimate illness severity by combining biological and non-biological data from patients with COVID-19. Moreover the use of ML for therapeutic purposes in Morocco is currently restricted, and ours is the first study to investigate the severity of COVID-19. When data analysis approaches were used to uncover patterns and essential characteristics in the data, C-reactive protein, platelets, and D-dimers were determined to be the most associated to COVID-19 severity prediction. In this research, many data reduction algorithms were used, and Machine Learning models were trained to predict the severity of sickness using patient data. A new feature engineering method based on topological data analysis called Uniform Manifold Approximation and Projection (UMAP) shown that it achieves better results. It has 100% accuracy, specificity, sensitivity, and ROC curve in conducting a prognostic prediction using different machine learning classifiers such as X_GBoost, AdaBoost, Random Forest, and ExtraTrees. The proposed approach aims to assist hospitals and medical facilities in determining who should be seen first and who has a higher priority for admission to the hospital.

【 授权许可】

CC BY