Table 6.
ML applications in cesarean section research.
| Reference | ML application | Input | ML technique | Main output |
|---|---|---|---|---|
| (102) | Complication prediction | Cardiotocography traces | DNN | AUC = 99%, Se = 94%, Sp = 91%, F1 = 100% and MSE = 1% |
| (103) | Complication prediction | Cardiotocography traces | LDA, RF and SVM | AUC = 96%, Se = 87%, Sp = 90% and MSE = 9% |
| (104) | Complication prediction | Cardiotocography traces | RF | AUC = 96.7%, Ac = 91.1%, Se = 90.0%, Sp = 92.2% and Pr = 92.1% |
| (105) | Complication prediction | Cardiotocography traces | CNN | AUC = 0.95, Ac = 94.70%, Pr = 94.71% and Re = 94.68% |
| (106) | Complication prediction | Electronic health records | CART | AUC = 0.7 |
| (107) | Anesthesia dose prediction | Clinical parameters | LASSO | MSE = 0.0087 and R2 = 0.8070 |
| (108) | Surgical site infection prediction | Clinical parameters and mobile images | LR | AUC = 1.0, Ac = 100%, Se = 1.0 and Sp = 1.0 |
| (109) | Later vaginal birth prediction | Electronic health records | RF | AUC = 0.69, Ac = 70.0%, Se = 97.9% and Sp = 6.9% |
ML, machine learning; DNN, deep neural networks; LDA, linear discriminant analysis; RF, random forest; SVM, support vector machines; CNN, convolutional neural networks; CART, classification and regression tree; LASSO, least absolute shrinkage and selection operator; LR, logistic regression; AUC, area under the receiver operating characteristic curve; Se, sensitivity; Sp, specificity; MSE, mean squared error; Ac, accuracy; Pr, precision; Re, recall.