Application of machine learning in predicting survival outcomes involving real-world data: a scoping review

Table 1 ML algorithms used in the studies and featuring studies (N = 28 studies)

Type of ML Algorithms	Number of Studies^d	Featuring Studies
Tree-based Methods
Random survival forests	16	26–28,31–34,36,42,43,45–49,53
Boosted tree methods^a	7	31,34,42,43,45,51,53
Neural Networks
Artificial neural networks^b	11	30,31,37,39–41,43,44,46,47,49,50
Support Vector Machine	4	34,35,42,53
Regularization^c	4
Other algorithms
Naives bayes	3	29,35,53
K-Nearest Neighbors	1	35
Multi-layer Perceptron	1	34

ML Machine learning, LASSO Least absolute shrinkage and selection operator, NN Neural networks, CNN Convolutional neural network, RNN Recurrent neural network, DL Deep learning, KNN The k-nearest neighbors
^aincludes ada-boost, gradient boosting, gradient descent boosting, boosting, XGBoost
^bincludes CNN, RNN, DNN, deep stacking networks, and ensemble of DL methods
^cincludes LASSO (L1 regularization), Ridge Regression (L2 regularization), or Elastic-Net
^dSince most studies have applied more than 1 machine learning algorithms, therefore the sum of the number of studies by machine learning method is greater than included studies (N = 28)

ISSN: 1471-2288