For the evaluation of several disorders, an electrocardiogram (ECG) is a crucial diagnostic tool. We use a machine learning-based Random Forest framework in this procedure to carry out automatic ECG diagnoses by categorising patient ECGs into relevant cardiac diseases. The Random Forest framework was previously trained on a broad signal data set. Implementing a straightforward, trustworthy, and simply used machine learning approach for the categorization of the chosen signals from the dataset is the main goal of this procedure. The outcomes showed that a standard back propagation neural network in cascade with transplanted deep learning classification was able to achieve very high performance rates.The major goal of this research is to forecast the ECG signal employing an effective classification algorithm in order to increase classification accuracy and decrease miss classes

Neurological Disorder, Electrocardiogram (ECG), Atrial Fibrillation, Random Forest framework, Machine Learning