In medical filed, predicting the occurrence of heart diseases is a significant piece of work. Millions of healthcare-related complexities that have remained unsolved up until now can be greatly simplified with the help of machine learning. The proposed study is concerned with the cardiac disease diagnosis decision support system. An OpenML repository data stream with 1 million instances of heart disease and 14 features is used for this study. After applying to preprocess and feature engineering techniques, machine learning approaches like random forest, decision trees, gradient boosted trees, linear support vector classifier, logistic regression, one-vs-rest, and multilayer perceptron are used to perform binary and multiclassification on the data stream. When combined with the Max Abs Scaler technique, the multilayer perceptron performed satisfactorily in both binary (Accuracy 94.8%) and multiclassification (accuracy 88.2%). Compared to the other binary classification algorithms, the GBT delivered the right outcome (accuracy of 95.8%). Multilayer perceptrons, however, did well in multiple classifications. Techniques such as oversampling and undersampling have a negative impact on disease prediction. Machine learning methods like multilayer perceptrons and ensembles can be helpful for diagnosing cardiac conditions. For this kind of unbalanced data stream, sampling techniques like oversampling and undersampling are not practical.

Co-operative and competitive building blocks drive the evolution of GP. There exists useful schema which remains promising and persistent in terms of their occurrence over the generations. These schemas are majorly present at levels other than root level, and gradually this genetic material is pushed towards the root level by co-operation, where they compete with each other, few among those increase their occurrence at the root level and rest vanished. These schemas if extended to the deeper depths, still be useful and helps in achieving the goal of the problem. Lastly, some of these schemas are same even in different runs for the same problem. The experiment results show that the evolution is driven by co-operative rooted building blocks as well, along with the competitive building blocks. It shows the count of building blocks in different positions never reaches zero, which indicates the presence of the genetic material required for the construction of the building block at a particular position in the form of co-operation and competition with other schemas, which, at a later stage, may move to the correct position (root level). In our work, these behaviours are also demonstrated by injecting genetic material manually in the population and investigated their prominence throughout the evolution. This work contributes to many dimensions like; by combining these competitive building blocks appear at root level uncovers the problem solution over time. For that reason, by identifying, preserving and exchanging these building blocks explicitly, the system enactment can be improved severely. Additionally, the solutions of the developed versions of the same problem can also be handled through this.

No abstract