An Enhanced Machine Learning Framework for Type 2 Diabetes Classification Using Imbalanced Data with Missing Values

Table 2

Classification machine learning algorithms.

Algorithm	Short description
Logistic regression (LR)	It uses a logistic function to model the probability of a specific class
K-nearest neighbor (KNN)	It uses similarity of features/attributes to predict new data points based on how closely it resembles the points in the training set
Decision tree (DT)	It uses a tree structure in which each internal node represents an attribute, each branch represents the outcome of a condition set on the feature, and each leaf node represents a class label
Random forest (RF)	It uses multiple decision trees to train and output the class that is the mode of the classes from decision trees
Support vector machine (SVM)	It uses the kernel to transform data and identify an optimal boundary between the possible outputs
Gradient boosting (GB)	It uses a combination of many weak learning models together to create a robust predictive model
Light gradient boosting machine (LGBM)	It uses tree-based learning algorithms as a GB framework