pISSN 1226-6051

eISSN 2508-786X

eISSN 2508-786X

Characteristics of cancer studies

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

Aghakhani |
Hospital data | 44,112 | Mortality | DT, RF, GBM, XGBoost | AUC, accuracy, sensitivity, specificity, F1 score, recall, precision |

Ahamad |
Public data | 72,147 | Severity, mortality, hospitalization | RF, DT, XGBoost, GBM, SVM, GBM | AUC, accuracy, F1 score, precision, recall |

Upadhyay |
Public data | N/A | Mortality | NN | N/A |

Banoei |
Hospital data | 1,743 | Mortality | Bootstrap forest, Boosted tree, Neural boosted, Nominal logistic, lasso, svm, DT, KNN | AUC, sensitivity, specificity |

Carbonell |
Hospital data | 152 | Mortality, severity | Lasso | AUC |

An |
Public data | 10,237 | Mortality | LASSO, Linear SVM, RBF-SVM, RF, KNN | AUC, accuracy, sensitivity, specificity |

Gao |
Hospital data | 23,749 | Mortality, severity | LR, RF, NN, KNN, GBM, ensemble model (SVM, GBM, NN) | AUC, accuracy, sensitivity, specificity, F1 score, PPV, NPV |

Experton |
Public data | 1,030,893 | Mortality, hospitalization | RF | AUC, accuracy |

Heydar |
Hospital data | 505 | Mortality | RF | AUC, accuracy, sensitivity, specificity |

Heyl |
Public data | 215,831 | Mortality | RF, XGBoost, LR | AUC, accuracy |

Hilal |
Public data | 608,140 | Mortality, hospitalization | XGBoost | AUC, accuracy, F1 score, recall, precision |

Ikemura |
Hospital data | 4,313 | Mortality | GBM, XGBoost, GLM, RF, DL | AUC, sensitivity, specificity |

Jamshidi |
Hospital data | 797 | Mortality | RF, LR, GBM, SVM, NN | AUC, sensitivity, specificity |

Razjouyan |
Public data | 9,541 | Mortality | Lasso | N/A |

Edqvist |
Public data | 8,328,518 | Mortality, hospitalization | GBM, RF | Accuracy |

Karasneh |
Hospital data | 1,613 | Mortality | LR, RF, MARS, KNN, XGBoost, CART | AUC |

Lee |
Public data | 7,943 | Mortality, hospitalization | LR, RF | AUC, precision |

Modelli de Andrade |
Hospital data | 1,379 | Mortality | Lasso, XGBoost, Elastic Net | AUC |

Kivrak |
Public data | 1,603 | Mortality | XGBoost, RF, KNN, DL | accuracy, sensitivity, specificity, precision |

Rahman |
Hospital data | 250 | Mortality | self-developed model | AUC, accuracy, sensitivity, specificity |

Lorè |
Hospital data | 111 | Mortality | DT | AUC |

Rasmy |
Public data | CRWD: 247,960 OPTUM: 36,140 | Mortality, mechanical ventilation, hospitalization | LR, GBM, self-developed model | AUC |

Wollenstein-Betech |
Public data | 91,179 | Mortality, hospitalization | SVM, RF, XGBoost, LR | AUC, accuracy, F1 score, precision, recall |

Schmidt |
Hospital data | 4,643 | Mortality | XGBoost | AUC |

Alle |
Hospital data | 544 | Mortality | SVM, RF, XGBoost, LR | AUC, F1 score, precision, recall |

Nojiri |
Hospital data | 11,440 | Mortality, severity | XGBoost, Lasso | AUC |

Snider |
Hospital data | 127 | Mortality, severity | DT, RF, Lasso | AUC, recall, precision |

Subudhi |
Hospital data | 3,597 | Mortality | Boosting models, self-developed model | N/A |

Kar |
Hospital data | 2,370 | Mortality | XGBoost | AUC, accuracy, sensitivity, specificity, F1 score, precision |

Wu |
Hospital data | 2,144 | Mortality | DenseNet | AUC, accuracy, sensitivity, specificity, F1 score, precision, recall |

Guan |
Hospital data | 1,270 | Mortality | XGBoost, Lasso | AUC,F1 score, precision, recall |

Jung |
Hospital data | 1,076 | Severity | LR, XGBoost | AUC, accuracy |

Zhao |
Hospital data | 172 | Severity | LR, SVM | AUC, accuracy, sensitivity, specificity |

Jiao |
Hospital data | 2,309 | Severity | DL, self-developed model | AUC, sensitivity, specificity, F1 score |

Kang |
Hospital data | 151 | Severity | NN | AUC, sensitivity, specificity, F1 score |

Wong |
Public data | 502,524 | Severity | XGBoost | AUC |

Rojas-García |
Public data | 11,564 | Severity | SVM, RF, XGBoost, LR | AUC, accuracy, sensitivity, specificity, F1 score, PPV, NPV |

Burns |
Public data | 4,295 | Severity | LR, RF, SVM, XGBoost | AUC, accuracy, specificity, F1 score, precision, recall, NPV |

Wang |
Hospital data | 1,051 | Severity | self-developed model | AUC, accuracy, sensitivity, specificity |

Chen |
Hospital data | 362 | Severity | RF | AUC, accuracy, sensitivity, specificity, F1 score |

De Freitas |
Hospital data | 7,336 | Hospitalization | RF, XGBoost, GBM, Lasso | AUC, accuracy, F1 score, precision |

Jehi |
Hospital data | 4,536 | Hospitalization | Lasso | AUC |

Hao |
Hospital data | 2,566 | Hospitalization, Mechanical ventilation | SVM, RF, XGBoost, LR | AUC, accuracy, F1 score, precision, recall |

Aminu |
Public data, hospital data | 502 | Mechanical ventilation | LR, RF, SVM, GAM | AUC, accuracy, sensitivity, specificity |

Chen |
Public data | 6,485 | Hospitalization | Lasso, LR | AUC, sensitivity, specificity |

DenseNet: densely connected convolutional network; Lasso: least absolute shrinkage and selection operator; XGBoost: extreme gradient boosting; RF: random forest; LR: logistic regression; DT: decision tree; KNN: k-nearest neighbors; DL: deep learning model; SVM: support vector machine; NN: neural network; LGBM: light gradient boosting machine; GBM: gradient boosting model; GAM: generalized additive model; GLM: generalized linear model; MARS: multivariate adaptive regression splines; CART: classification and regression 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