Executive Summary : | Establishing Recurrent Neural network model for identifying the Recurrence Cervical Cancer Genes: Long Non-Coding RNA(lnRNA) gene signatures are identified in the CC patients implementing HSIC model. Identifying the risk factors in Recurrence CC Hub genes relevant to Recurrence cervical cancer are rectified using RNN model Establishing the model for prognosis of Recurrence cervical cancer : Determining gene-gene connectivity using a RNN model Estimating percentage of CC spread deploying Long short Term Memory (LSTM) model. Discovery of immune cells in by Artificial swarm intelligence Algorithm The cervical cancer RNA samples are given as input to the recurrent neural network where the history of the patients are already stored with gene signatures of the cervical cancer. The recurrence cervical cancer is tested with that of the previous gene RNA sample. The RNN explores the recent history of the CC patients and provides the output RNA samples with gene signature. Steps Diagnosing the recurrence CC by identifying lnRNA gene signatures. Monitoring the Recurrence CC with RNN model analyzing with risk factors. Integrating LSTM model for the prognosis of Recurrence CC with biological outcomes. Decision making therapy after post Recurrence CC. |