Utilizing a Machine Learning Approach, Chronic Disease Identification and Prediction

Nowadays, people suffer from many diseases due to lifestyle choices and environment. Recognition and predicting these diseases in their early stages is crucial to preventing their extremes. Mostly time, identifying diseases manually poses a significant challenge for doctors. The purpose of this study to determine and forecast the patients who have greater prevalent long-term conditions. This might be accomplished by ensuring that this classification accurately identifies people with chronic illnesses by applying a machine learning technique. The disease prediction is also difficult a difficult challenge. Therefore, data mining is essential to the prediction of disease. The system provides a wide range of features depend on the patient's diagnostic by using machine learning algorithms like convolutional neural networks (CNN) for impulsive attribute extraction and disorder prediction and Knearest neighbour (KNN) for calculating distances to discover the accurate match in the dataset and the concluding disorder prediction. Prognosis of the disorder. The process of creating the data set included obtaining details on the patient's lifestyle, medical consultation history, and the symptoms of the illness. All of these factors were taken into account while making this general illness prediction. To sum up, this study compares the recommended system utilizing a variety of methods, such as logistic regression, decision trees, and Naïve Bayes.