Introduction: Alzheimer__ampersandsignrsquo;s is a degenerative neurological disease and is difficult to diagnose with early symptoms. Nowadays, the number of people diagnosed with Alzheimer__ampersandsignrsquo;s disease is increasing rapidly due to lifestyle changes. Alzheimer__ampersandsignrsquo;s disease can be diagnosed from MRI brain images. It requires medical expertise and the failure to identify the disease at an early stage will result in permanent disabilities. The automatic and accurate identification of Alzheimer__ampersandsignrsquo;s disease from MRI images helps to eliminate the above issues and dispense better results. Objectives: This work intends to develop an algorithm that could detect the presence of Alzheimer__ampersandsignrsquo;s disease at an early stage by extracting the brain features of MRI images using a point-based feature extraction method. Methods: Here, a new algorithm is proposed using combined point detection based feature extraction techniques like SURF, FAST, BRISK, Harris, Min Eigen and HOG methods and feature selection using Principal Component Analysis for early prediction of various stages of Alzheimer__ampersandsignrsquo;s disease. An analysis of the proposed method is done by combining it with different classifiers and the performance parameters are evaluated. The performance of the proposed method is evaluated and analyzed using parameters such as classification accuracy, sensitivity, specificity andF1 score. Results: From the analysis of the experimental results, the proposed algorithm was found to have a high accuracy rate of 98.62% for the detection and classification of Alzheimer__ampersandsignrsquo;s disease. Conclusion: The proposed method was found to be superior to the methods which use single feature extraction which is developed for the prediction and classification of Alzheimer__ampersandsignrsquo;s disease.