TABLE 2.
Categorization and current status of research topics on predictive modeling for diarrheal disease.
| Primary Category | Sub‐category | Modeling methods for existing predictive models |
|---|---|---|
| Disease forecast | All‐cause diarrhea | Random Forest, autoregressive integrated moving average (ARIMA/X), seasonal‐auto‐regressive‐integrated‐moving‐average (SARIMA/X), multiplicative Holt‐Winters method, compartmental susceptible‐infected‐recovered‐susceptible (SIRS) model, Parsimony Model, gravity models, Multiple Linear Regression, Random Forest Regression, Support Vector Regression, Gradient Boosting Regression, Extreme Gradient Boosting Regression, Convolutional Neural Network, Neural Network Regression |
| Cholera | SIRS‐like models, data assimilation: ensemble Kalfman filter, individual‐based spatially‐explicit stochastic model, logistic regression, SARIMA, model, auto regression model, multiple regression models | |
| Disease/pathogen detection | All‐cause diarrhea | Naïve Bayes, linear discriminant analysis, quadratic discriminant analysis, support vector machine, Artificial Neural Network |
| Viral etiology | Random Forest, logistic regression | |
| Bacterial etiology | Random Forest, logistic regression | |
| Rotavirus | Classification trees | |
| Strain dynamics | Rotavirus | Fourier analysis |
| Norovirus | Fitness models | |
| Shigella | Logistic regression, Neural Network, support vector machines | |
| Outcomes | Dehydration | Logistic regression/recursive partitioning model |
| Malnutrition | Linear regression | |
| Hospitalization | None | |
| Prolonged/persistent diarrhea | None | |
| Mortality | None | |
| Seasonality | Principal‐Component Analysis, K‐means clustering, classification and regression trees | |
| Vaccine | Vaccine impact | SIS‐ (susceptible‐infectious‐susceptible), SIRS‐like compartmental models, ensemble models, dynamic, deterministic compartmental model, periodic regression models, age‐structured compartmental mode |
| Vaccine cost‐effectiveness | Dynamic model | |
| Vaccine hesitancy | Logistic regression, Random Forest, and Neural Networks | |
| Determinants of diarrheal disease burden | Classification and Regression Trees (CART) | |