An ensemble classifier approach for disease diagnosis using Random Forest

Massive amount of diagnostic data is generated everyday as a part of daily diagnosis, related to various types of diseases and disorders. For knowledge discovery from this diagnostic data, efficient data mining techniques play a very important role. Ensemble classifier is one of the data classification techniques related to data mining, in which decision of multiple base classifiers is combined for accurate prediction of the presence or absence of abnormality. Here, we have considered retinal images of diabetic patients, PET scan of brain of Alzheimer and MRI of brain cancer and classification is performed irrespective of whether normality or abnormality is present. The ensemble method proves to be very efficient in classification of records from available patient database, as it involves the process of considering opinion from multiple base classifiers, as opposed to the single classifier method. This leads to very accurate and precise inference, as uncorrelated errors are removed because of multiple base classifiers.