pISSN 1226-6051

eISSN 2508-786X

eISSN 2508-786X

Characteristics of non-cancer studies

Study name | Source of data | Number of patients | Prediction values | AI models | Performance metrics | |
---|---|---|---|---|---|---|

Churpek |
Hospital data | 5,075 | Mortality | XGBoost, RF, SVM, LR, neural net, self-developed model | AUC, sensitivity, specificity, PPV, NPV | |

Elghamrawy |
Public data | 10,248 | Mortality | self-developed model | AUC, accuracy, sensitivity, specificity, F1 score, FPR | |

Khadem |
Hospital data | 156 | Mortality | RF | AUC, accuracy, sensitivity, specificity | |

Kablan |
Hospital data | 247 | Mortality | Ensemble model (GLM, NB, SDA, RF, PLS, KNN, SVM, MLP) | AUC, accuracy, sensitivity, specificity, F1 | |

Ovcharenko |
Hospital data | 350 | Mortality | CatBoost, RF, MLP, LGBM, ET, XGBoost, LR, DT, KNN | AUC, sensitivity, specificity | |

Passarelli-Araujo et al. (2022) | Public data | 8,358 | Mortality | LR, SVM, RF, XGBoost | AUC, accuracy, precision, recall | |

Pournazari |
Hospital data | 724 | Mortality | LR | AUC | |

Pyrros |
Public data | 900 | Mortality | CNN, LR | AUC | |

Yazadani |
Hospital data | 1,572 | Mortality | MLP, NB, KNN, DT, RF | AUC, accuracy, precision, recall, F1 score | |

Wang |
Hospital data | 3,740 | Mortality, mechanical ventilation | XGBoost, LR, lasso, MLP, RNN, GRU, LSTM | AUC, sensitivity, specificity | |

Woo |
Hospital data | 415 | Mortality, severity | LR, self-developed model | AUC, sensitivity, specificity | |

Ageno |
Hospital data | 610 | Severity | Lasso, RF | AUC, sensitivity, specificity, PPV, NPV | |

Carr |
Hospital data | 7,513 | Severity | Lasso, KNN | AUC, sensitivity, specificity | |

Min |
Hospital data | 3,145 | Severity | CatBoost, CART | AUC, accuracy, precision, recall, F1 score | |

Sun |
Hospital data | 336 | Severity | SVM | AUC | |

Liprak |
Hospital data | 680 | Hospitalization | RF | AUC | |

Nakamichi |
Hospital data | 190 | Hospitalization | AdaBoost, Extra Trees, Gradient boosting, RF | AUC | |

Tariq |
Hospital data | 2,844 | Hospitalization | Fusion model (LR, RF, neural network, XGboost) | AUC, precision, recall, F1 score |

RF: random forest; RNN: recurrent neural network; XGBoost: extreme gradient boosting; LR: logistic regression; Lasso: least absolute shrinkage and selection operator; SDA: shrinkage discriminant analysis; SVM: support vector machine; GLM: generalized linear model; GRU: gated recurrent unit; NB: naive bayes; KNN: k-nearest neighbors; MLP: multi-layer perceptron; PLS: partial least squares; CART: classification and regression trees; CNN: convolutional neural network; ET: extra trees; LGBM: light gradient boosting machine; LSTM: long short-term memory; DT: decision tree; AUC: area under the curve; AI: artificial intelligence; PPV: positive predictive value; NPV: negative predictive value.

Korean J Clin Pharm 2024;34:141-54 https://doi.org/10.24304/kjcp.2024.34.3.141

© 2024 Korean J Clin Pharm