Table 1.
Outlining the reviewed machine learning-based models in COVID-19 pandemic related tasks.
| Paper | Technique | Task | Data type | Accuracy | Explainability |
|---|---|---|---|---|---|
| Mahdy et al. [46] | SVM | Covid-19 lung image classification | X-ray image | High | Low |
| Yu et al. [47], | Decision Tree | Severity detection of COVID-19 paediatric cases | Chest radiography and CT images | Medium | High |
| Too and Mirjalili [48]. | KNN | Prediction of the death and recovery conditions | The patients' information (Gender, Age, Country, etc.) and their symptoms | Medium | Medium |
| Song et al. [49] | Time-dependent model parameters. | forecasting the dynamic spread of COVID-19 | Daily reported cases in China and the United States | High | Low |
| Kumar and Kumar [50] | Fuzzy clustering and time series model | Prediction of COVID-19 infected cases and deaths | Daily reported cases in India | Medium | Low |
| Cobre et al. [51] | KNN, Neural Networks, Partial Least Squares Discriminant Analysis, etc. | Diagnosis and prediction of COVID-19 severity | Biochemical, hematological, and urinary biomarkers | Medium | Low |
| Arvind et al. [52] | Sliding-window approach | Prediction of intubation among hospitalized patients | laboratory and vitals data COVID-19+ patients | Medium | Low |
| Pahar et al. [53] | Residual neural networks | Classification of COVID-19 cough | Coughing sounds recorded during or after the acute phase of COVID-19 | Medium | Low |
| Ebinger et al. [54] | Logistic regression, SVM, KNN, etc. | Prediction of duration of hospitalization in COVID-19 patients | Electronic health record data from COVID-19 patients | Medium | Low |
| Zhang et al. [55] | Least absolute shrinkage and selection operator regression and least absolute shrinkage and selection operator neural network models. | Identification and validation of prognostic factors in COVID-19 patients | Demographic data including, clinical data including and outcome (28-day mortality) | Medium | Low |
| Gulati et al. [56] | Linear SVC, Perceptron, Passive Aggressive, Logistic Regression, etc. | Sentiment classification of discussion related to COVID-19 pandemic | Tweets related to COVID-19 pandemic | Medium | Low |
| Singh et al. [57] | Ensemble Support Vector Machine | COVID-19 detection | Lung tomography scan data | High | Low |
| Wu et al. [58] | Joint Classification and Segmentation | COVID-19 diagnosis | Chest CT images | Medium | Medium |
| Yang et al. [59] | Decision Tree | Death outcome prediction | Medical records (demographics, clinical characteristics, and laboratory test results) | Medium | High |
| Lella and Pja [60] | Deep Convolutional Neural Network | Diagnosis of COVID-19 disease | Human respiratory sounds such as voice, dry cough, and breath, | High | Low |
| Qayyum et al. [61] | Depth-wise deep learning | Detection and diagnosis of COVID-19 infection | Lungs X-rays images | High | Low |
| Roy et al. [62] | Spatial Transformer Networks-based Deep learning | Classification and Localization of COVID-19 Markers | Lung ultrasonography (LUS) images. | High | Low |
| Shamsi et al. [63] | Deep transfer learning | Diagnosis of COVID-19 | Chest X-ray and CT images | High | Low |
| Islam et al. [64] | Deep Convolutional Neural Network and LSTM | Detection of COVID-19 | X-ray images | High | Low |
| Hall et al. [65] | Deep Convolutional Neural Network | Detection of COVID-19 | Chest x-rays | High | Low |
| Ahmadian et al. [66] | Deep Neuroevolution | Diagnosis of COVID-19 | Chest x-rays | High | Low |