Table 3.
Included studies covering spatio-temporal monitoring of disease spread with machine learning and Bayesian models and their key aspects.
| Study | Key aspects |
|---|---|
| Stojanović et al. (41) | Introduced a spatio-temporal kernel function |
| Al-qaness et al. (42) | Forecast for the upcoming days with a fair amount of data |
| Fong et al. (43) | Develop forecasting model with insufficient amount of available data |
| Mehta et al. (44) | Estimate outbreak probability on county level |
| Pavlyshenko et al. (45) | Investigated impact on stock market |
| Suzuki et al. (46) | Use binary classification to see if number of cases will exceed a threshold |
| Ibrahim et al. (47) | Implement urban characteristics and index for NPIs |
| Nader et al. (48) | Estimate growth rate depending on specific NPI |
| Yeung et al. (49) | Compared non-time series ML algorithms to model pandemic |
NPI, Non-Pharmaceutical Intervention; ML, machine learning.