Survival Prediction Model for Patients with Esophageal Squamous Cell Carcinoma Based on the Parameter-Optimized Deep Belief Network Using the Improved Archimedes Optimization Algorithm

Abstract

Esophageal squamous cell carcinoma (ESCC) is one of the highest incidence and mortality cancers in the world. An effective survival prediction model can improve the quality of patients’ survival. Therefore, a parameter-optimized deep belief network based on the improved Archimedes optimization algorithm is proposed in this paper for the survival prediction of patients with ESCC. Firstly, a combination of features significantly associated with the survival of patients is found by the minimum redundancy and maximum relevancy (MRMR) algorithm. Secondly, a DBN network is introduced to make predictions for survival of patients. Aiming at the problem that the deep belief network model is affected by parameters in the construction process, this paper uses the Archimedes optimization algorithm to optimize the learning rate α and batch size β of DBN. In order to overcome the problem that AOA is prone to fall into local optimum and low search accuracy, an improved Archimedes optimization algorithm (IAOA) is proposed. On this basis, a survival prediction model for patients with ESCC is constructed. Finally, accuracy comparison tests are carried out on IAOA-DBN, AOA-DBN, SSA-DBN, PSO-DBN, BES-DBN, IAOA-SVM, and IAOA-BPNN models. The results show that the IAOA-DBN model can effectively predict the five-year survival rate of patients and provide a reference for the clinical judgment of patients with ESCC.

A Study of Optimization in Deep Neural Networks for Regression

“…Parameter adjustments aim to achieve the best accuracy and reduce the time and cost of model training. As shown in Figure 5, this study statistically analyzed hyperparameter optimization, and the results were consistent with the conclusion of Wang et al [44], who found that the learning rate and batch size were the two most essential hyperparameters. Parameter adjustments aim to achieve the best accuracy and reduce the time and cost of model training.…”

“…Supplementing average value [16,17], linear interpolation [17,18], KNN [19,20] Dimensionality reduction PCA [8], pooling layer [21], t-SNE [22], SPCA [23] Removing outliers Pauta criterion [18], EWMA [24] Feature selection PSO [1], LASSO [8,25], ASO [26], GA [27], MI [28], GRA [29], PCC [30], CCA [31] Decomposition EMD [32], EEMD [33], CEEMDAN [19,27,[34][35][36][37][38], ICEEMDAN [39], SSA [40,41], VMD [42], SVMD [43] Normalization [6,17,20,27,30,31,34,42,[44][45][46][47][48][49]…”

“…If the learning rate is too low, the modeling time will be longer; if the learning rate is too high, the model will fail to converge [63]. Wang et al [44] used DBN to predict the survival of cancer patients, and the results showed that the learning rate had a high impact on the model's accuracy. Yalçın et al [62] mentioned that setting a suitable learning rate can avoid overfitting.…”

“…The batch size is used in gradient descent to control the number of training samples used to update the internal parameters of a network model. Wang et al [44] showed that the batch size significantly impacts the accuracy in the DBN model. Iteration and epoch are parameters related to batch size optimization.…”

Application of Deep Learning in Cancer Prognosis Prediction Model

“…The predicted AUCs for 1-year, 3-year, and 5-year survivals were 0.851, 0.806, and 0.793, respectively. Wang et al 25 proposed a novel DL network IAOA-DBN combining DBN and Archimedean optimization algorithm for predicting the 5-year survival of patients with esophageal squamous cell carcinoma. First, a minimum redundancy maximum correlation algorithm was used to screen statistically significant features.…”