Squirrel Search Deer Hunting-Based Deep Recurrent Neural Network for Survival Prediction Using PAN-Cancer Gene Expression Data

Abstract

This paper devises a novel technique, namely Squirrel Search Deer Hunting-based deep recurrent neural network (SSDH-based DRNN) for cancer-survival rate prediction using gene expression (GE) data. Initially, the input GE data are transformed using the polynomial kernel data transformation. Then entropy-based Bayesian fuzzy clustering is employed for gene selection. Then, the selected features are strengthened through survival indicators based on time series data features, like simple moving average (SMA) and rate of change. Finally, the survival rate prediction is performed using a deep recurrent neural network (DRNN), in which the training is carried out with squirrel search deer hunting (SSDH). The proposed SSDH algorithm is devised by combining Squirrel Search Algorithm (SSA) and deer hunting optimization algorithm (DHOA). The performance of the proposed methodology is analyzed using Pan-Cancer (PANCAN) dataset with a prediction error of 4.05%, RMSE of 7.58, the accuracy of 90.98%, precision of 90.80%, recall of 92.03% and F1-score of 91.41%. The devised method with higher prediction accuracy and the lower prediction error is employed for the cancer survival prediction of the patients for the cancer prognosis. Besides, it will be helpful for the clinical management of cancer patients.

Survival Prediction Landscape: An In-Depth Systematic Literature Review on Activities, Methods, Tools, Diseases, and Databases

“…Table 2 illustrates disease specific predictors distribution for both cancer and other diseases respectively. In the last 3 years, 60 predictors have been designed for different cancer subtypes related survival prediction 24,104,108 while only 14 predictors have been designed for other diseases such as cardiovascular diseases, COVID-19, and trauma 29,112,119,120 .…”

“…DL model DeepSurv, has been utilized in 5 studies related to gastrointestinal cancer 30 , ASCVD 111 , NSCLC 97 . On the other hand, in the analyzed survival predictive pipelines less frequently utilized methods are i.e., survival SVM 79,95,120 , partial logistic regression 70,75 , log hazard net 75,104 , boosting 41,112 , stepCox 86 , elastic net 95 , CNNcox 104 , DeepOmix 104 , ordinal Cox-PH 78 , DeepHit 112 , and linear multitask logistic regression (MTLR) 112 .…”

Survival prediction landscape: an in-depth systematic literature review on activities, methods, tools, diseases, and databases

“…Table 3 illustrates disease specific predictors distribution for both cancer and other diseases, respectively. In the last 3 years, 74 predictors have been designed for different cancer subtypes related survival prediction (Tan et al, 2020 ; Fan et al, 2023 ; Majji et al, 2023 ) while only 17 predictors have been designed for other diseases such as cardiovascular diseases, COVID-19, cardiomyopathy, esophagectomy and trauma (Kantidakis et al, 2020 ; Abdelhamid et al, 2022 ; Feng et al, 2022 ; Farahani et al, 2023 ; Qian et al, 2023 ; Rahman et al, 2023 ).…”

“…A. et al, 2021 ), NSCLC (Zhang Z.-S. et al, 2021 ). On the other hand, in the analyzed survival predictive pipelines less frequently utilized methods are i.e., survival SVM (Yu et al, 2020 ; Abdelhamid et al, 2022 ; Manganaro et al, 2023 ), partial logistic regression (Lin et al, 2022 ; Lee et al, 2023 ), log hazard net (Lee et al, 2023 ; Majji et al, 2023 ), boosting (Wang et al, 2020 ; Feng et al, 2022 ), stepCox (Wang X. et al, 2023 ), elastic net (Manganaro et al, 2023 ), CNN-cox (Majji et al, 2023 ), DeepOmix (Majji et al, 2023 ), ordinal Cox-PH (Bichindaritz and Liu, 2022 ), DeepHit (Feng et al, 2022 ), and linear multitask logistic regression (MTLR) (Feng et al, 2022 ).…”