Table 1.
Author, publication year | Number of articles | Objective | Comparison of information provided in previous vs. those provide in this review | |||
---|---|---|---|---|---|---|
Saleem et al., 2022 (7) | 57 | To highlight the latest developments in analyzing the COVID-19 data using machine learning and deep learning algorithms. | Articles with the following outcomes ✓Hospitalization ✓Mortality |
Data-related aspects ✓Type of data ✓Country ✓Single/multi-country data sources x Type of covariates x Primary vs. secondary data |
AI models-related aspects ✓Model ✓Model's performance ✓External validation x Internal validation x Type of filtering/prioritization x Supervised/not supervised x Calibration x Bias according to the prediction model risk of bias assessment tool |
Epidemiological aspects x Nationwide/sampled population x Risk factors for mortality x Risk factors for hospitalization x Disease risk score for severe COVID-19 disease (death or hospitalization) |
Napolitano et al., 2022 (8) | 17 269 | To identify the application of machine learning methods on COVID-19. | Articles with the following outcomes ✓Hospitalization ✓Mortality |
Data-related aspects x Type of data x Country x Single/multi-country data sources ✓Type of covariates x Primary vs. secondary data |
AI models-related aspects ✓Model ✓Model's performance x External validation x Internal validation x Type of filtering/prioritization x Supervised/not supervised x Calibration x Bias according |
Epidemiological aspects x Nationwide/sampled population ✓Risk factors for mortality ✓Risk factors for hospitalization x Disease risk score for severe COVID-19 disease (death or hospitalization) |
Lyu et al., 2022 (9) | 19 | To analyze the papers that used artificial intelligence (AI) models to forecast COVID-19 outcomes | Articles with the following outcomes ✓Hospitalization ✓Mortality |
Data-related aspects x Type of data ✓Country x Single/multi-country data sources x Type of covariates x Primary vs. secondary data |
AI models-related aspects ✓Model ✓Model's performance x External validation x Internal validation x Type of filtering/prioritization x Supervised/not supervised x Calibration x Bias according to the prediction model risk of bias assessment tool |
Epidemiological aspects x Nationwide/sampled population x Risk factors for mortality x Risk factors for hospitalization x Disease risk score for severe COVID-19 disease (death or hospitalization) |
Bottino et al., 2021 (10) | 24 | To look into the studies that implemented machine learning, including deep learning, methods in COVID mortality prediction | Articles with the following outcomes x Hospitalization ✓Mortality |
Data-related aspects ✓Type of data ✓Country ✓Single/multi-country data sources ✓Type of covariates Primary vs. secondary data |
AI models-related aspects ✓Model ✓Model's performance ✓External validation ✓Internal validation ✓Type of filtering/prioritization ✓Supervised/not supervised x Calibration x Bias according to the prediction model risk of bias assessment tool |
Epidemiological aspects x Nationwide/sampled population ✓Risk factors for mortality x Risk factors for hospitalization x Disease risk score for severe COVID-19 disease (death or hospitalization) |
Guo et al., 2021 (11) | 794 | To summarize how artificial intelligence (AI) is being applied in COVID-19 research and determine whether these AI applications integrated heterogeneous data from different sources for modeling. | Articles with the following outcomes ✓Hospitalization ✓Mortality |
Data-related aspects ✓Type of data ✓Country ✓Single/multi-country data sources ✓Type of covariates x Primary vs. secondary data |
AI models-related aspects ✓Model x Model's performance x External validation x Internal validation x Type of filtering/prioritization x Supervised/not supervised x Calibration x Bias according to the prediction model risk of bias assessment tool |
Epidemiological aspects x Nationwide/sampled population x Risk factors for mortality x Risk factors for hospitalization x Disease risk score for severe COVID-19 disease (death or hospitalization) |
Shi et al., 2021 (12) | 27 | To assess the potential predictors of mortality in patients with COVID-19. | Articles with the following outcomes x Hospitalization ✓Mortality |
Data-related aspects ✓Type of data ✓Country x Single/multi-country data sources ✓Type of covariates x Primary vs. secondary data |
AI models-related aspects ✓Model ✓Model's performance x External validation x Internal validation x Type of filtering/prioritization x Supervised/not supervised x Calibration xBias according to the prediction model risk of bias assessment tool |
Epidemiological aspects x Nationwide/sampled population ✓Risk factors for mortality x Risk factors for hospitalization x Disease risk score for severe COVID-19 disease (death or hospitalization) |
Syed et al., 2021 (13) | 8 | To identify the deep learning techniques that have been applied to predict hospital mortality in COVID-19 patients. | Articles with the following outcomes x Hospitalization ✓Mortality |
Data-related aspects ✓Type of data x Country x Single/multi-country data sources ✓Type of covariates x Primary vs. secondary data |
AI models-related aspects ✓Model ✓Model's performance x External validation x Internal validation x Type of filtering/prioritization x Supervised/not supervised x Calibration x Bias according to the prediction model risk of bias assessment tool |
Epidemiological aspects x Nationwide/sampled population x Risk factors for mortality x Risk factors for hospitalization x Disease risk score for severe COVID-19 disease (death or hospitalization) |
Alballa et al., 2021 (14) | 52 | To focus on the potential of ML for two main applications: diagnosis of COVID-19 and prediction of mortality risk and severity, using readily available clinical and laboratory data. | Articles with the following outcomes x Hospitalization ✓Mortality |
Data-related aspects ✓Type of data x Country x Single/multi-country data sources ✓Type of covariates x Primary vs. secondary data |
AI models-related aspects ✓Model ✓Model's performance ✓External validation ✓Internal validation ✓Type of filtering/prioritization ✓Supervised/not supervised x Calibration x Bias according to the prediction model risk of bias assessment tool |
Epidemiological aspects x Nationwide/sampled population ✓Risk factors for mortality x Risk factors for hospitalization ✓Disease risk score for severe COVID-19 disease (death or hospitalization) |