Gray wolf‐student psychology optimization‐based deep long short term memory for survival prediction using cancer gene‐expression data. (29th July 2022)

• Record Type: Journal Article
• Authors: Prabhakar, Telagarapu; Vairamuthu, Subbiah; Rani, Balasubramaniam Selva; Maram, Balajee
• Is Part Of: Concurrency and computation. Volume 34:Number 23(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-07-29
• Subjects: deep long short term memory -- gene expression data -- gray wolf optimizer -- student psychology based optimization -- survival prediction; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.7206
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: Oncology treatment accuracy relies on providing information from a variety of sources to have a accurate assessment of a patient's health status and prediction. With the advancement in medical field, accurate prediction allows prescription of more effective treatments and customized medical services to individual patient's. Next generation sequencing has put pressure on cancer researchers in recent years by giving doctors access to vast amounts of data from RNA‐seq high‐throughput fields. Effectual survival prediction can save patient's life from threatening at earlier stage. In addition, traditional techniques of gene expression datasets failed to trade off balance among huge genes and low number of samples available, thereby resulting low level of survival prediction rate. Therefore, this research proposes an efficient model for survival prediction of cancer patients using proposed gray wolf‐student psychology optimization‐based deep long short term memory (GW‐SPO based deep LSTM). The proposed GW‐SPO is derived by incorporating gray wolf optimization (GWO) and student psychology based optimization (SPBO). However, survival prediction is performed effectively using deep LSTM and network classifier is trained using proposed GW‐SPO. Nevertheless, proposed GW‐SPO has achieved superior results with minimum RMSE of 0.325, and minimum prediction error of 0.110 for analysis with cluster size of 5.