A Comprehensive Machine Learning Based Ensemble Model for Prediction of Possible Diseases and Recommending Medicines

Many instances remain untreated globally due to the lack and unavailability of medical services. In this regard, efficient monitoring and analysis of medical records will be helpful in timely identification and prediction of diseases. To enable a quicker and more precise diagnosis, a platform that keeps track of a patient's medical history and makes illness predictions based on the patient's present symptoms is needed. Early disease prediction allows users to determine the severity of a condition and take appropriate action timely. Thus, anticipation of illness in its early stage becomes essential but it's difficult for doctors to anticipate outcomes precisely and accurately based only on symptoms. Availability of medical data and its analysis with the help of machine learning techniques can help the healthcare system for appropriate predictions and recommendations of diseases. In this paper, based on the patient's symptoms and medical records, a general illness prediction system is proposed. Using the input image for disease prediction, we applied an ensemble model exploiting the KNN, SVM, Naïve bayes and deep learning techniques to accurately predict diseases. The proposed model superseded the existing techniques with 98% accuracy on experimental study performed using benchmark datasets.