From: Artificial intelligence and machine learning for hemorrhagic trauma care
Study topic | Category | Method in search | References |
---|---|---|---|
Different outcomes in trauma | Regression | LR | |
Network | DNN, ANN, MLP, RBFN, Predictive Hierarchical Network, Polynomial NN, RSNNS | [27, 36, 37, 41, 63,64,65,66,67,68, 70, 71, 73,74,75,76,77,78,79,80] | |
Tree | CART, DT, RF, Recursive Partitioning Algorithm, OCT, Bayesian DT, unpruned C4.5 tree (J48), Archetypal DT | ||
Kernel | SVM, SMO, Polynomial Kernel, SVM Radial | ||
Ensemble | SuperLearner | [86] | |
Boosting | XGBoost, Gradient Boost | ||
Other | LDA, ER, FIS, Inference methodology | ||
Bayesian | GNB, NB, BBN | ||
Unmentioned/commercial ML algorithm, novel scoring systems | Deep-FLAIM, UKTRISS, TOP, 4TDS, EDI | ||
Classification | KNN, Maximum a Posteriori | ||
Risk assessment | Regression | LR, MLR | |
Network | ANN, MLP, DNN, Dirichlet DNN | ||
Tree | RF, DT, Boosted Tree | ||
Kernel | SVM, SVMR | ||
Bayesian | BBN, NB | ||
Boosting | XGBoost, Adaboost | ||
Ensemble | Bagging | [97] | |
Other | Generalized Linear Model, LDA | ||
Classification | KNN | [97] | |
Unmentioned/commercial ML algorithm, novel scoring systems | CRI, MGAP | ||
Transfusion | Network | NN | |
Kernel | SVM | [49] | |
Boosting | XGBoost | ||
Tree | Classification and regression tree, Recursive partitioning analysis | ||
Regression | Logistic regression | ||
Unmentioned ML algorithm, commercial ML software, novel scoring systems | CRI, MASH, BRI | ||
Hemorrhage detection | Network | Multi-scale attentional network | [59] |
Ensemble | Ensemble classifier | [109] | |
Regression | Poisson regression | [110] | |
Kernel | SVM | [56] | |
Unmentioned/commercial ML algorithm, novel scoring systems | BRI | [111] | |
Other | Linear/non-linear density model, NLP Linear Classifier | ||
Coagulopathy | Regression | LR | [113] |
Tree | DT, RF | ||
Bayesian | BN | [57] | |
Unmentioned/commercial ML algorithm, novel scoring systems | Caprini RAM | [113] |