Research on Disease Prediction Method Based on R-Lookahead-LSTM

Algorithm 2

R-Lookahead-LSTM algorithm.

	R-Lookahead-LSTM algorithm
Step 1: process the data, analyze the correlation of the data, and use the ensemble learning algorithm random forest algorithm to perform feature selection on the data, so as to further determine the feature vector required to build the model
Step 2: divide the above-processed data set into a training set and test set according to the ratio of 7:3
Step 3: determine the structure of the LSTM model for the data samples of the training set and determine the number of network layers and initialization parameters through experimental tests
Step 4: train the model and use the R-Lookahead optimization algorithm to optimize the loss function of the LSTM model
Step 5: use the test set data samples as the input data of the model to test the prediction effect of the R-Lookahead-LSTM disease risk prediction model
Step 6: use multiple indicators such as accuracy rate, recall rate, F1-score, specificity, and MCC value to evaluate the prediction effect of the model