Cancer Prognosis & Stratification with Sentimental Analysis using Deep and Machine Techniques

For therapy and monitoring, it is crucial to provide prognostic information at the time of cancer characteristics, and clinical variables might offer helpful prognostic clues, risk stratification still has to be improved. All these data generate defined patterns and those patterns can be examined with the help of Machine Learning and Deep Learning. The most promising algorithm for this use case is artificial neural networks. Decision trees might be used to the best extent as they provide an adequate balance of speed and accuracy. An ideal approach would be through the effective combination of ANN and Random Forests. Ensembling models would also be able to boost the performance of the system. The metrics and scores for the project must be in-scope of the development and at the same time extendable.