Applying Artificial Intelligence Techniques to Improve Clinical Diagnosis of Alzheimer’s disease

Proceedings of ‏The International Conference on Research in Science and Technology

Year: 2020


[Fulltex PDF]

Applying Artificial Intelligence Techniques to Improve Clinical Diagnosis of Alzheimer’s disease

Ahmed Abdullah Farid, Gamal Ibrahim Selim and Hatem Awad A. Khater



Alzheimer’s disease (AD) is a significant regular type of dementia that causes damage in brain cells. Early detection of AD acting as an ‎essential ‎role in global health care due to misdiagnosis and sharing many ‎clinical sets with other types of dementia, and costly monitoring ‎the progression of the disease over time by magnetic reasoning ‎imaging (MRI) with consideration of human error in manual reading. Our ‎proposed model in the first stage, apply the medical dataset to a composite hybrid feature selection (CHFS), to extract new features for select the best features to ‎improve the performance of the classification process due to ‎eliminating obscures features. In the second stage, we applied a dataset to a stacked ‎hybrid classification system to combine Jrip and random forest ‎classifiers with six model evaluations as meta-classifier individually ‎to improve the prediction of clinical diagnosis. All experiments conducted on a laptop with an Intel Core i7- 8750H CPU at 2.2 GHz and 16 G of ram running on windows 10 (64 bits). The dataset evaluated using an explorer ‎set of weka data mining software for the analysis purpose. The experimental show that the ‎proposed model ‎of ‏‎(‎CHFS‎) ‎feature extraction ‏performs better than ‎principal component analysis (PCA), and lead to ‎ effectively reduced the false-negative ‎rate with a ‎relatively ‎high overall accuracy with support vector machine (SVM) as meta-classifier of 96.50% compared to 68.83% which is considerably better than the previous state-of-the-art result. The receiver operating characteristic (ROC) curve was equal to 95.5%. Also, the experiment on MRI images Kaggle dataset of CNN classification process with 80.21% accuracy result. The results of the proposed model show an accurate classify ‎Alzheimer’s clinical samples against MRI neuroimaging for diagnoses AD at a low cost.‎

Keywords: Data Mining, Alzheimer’s Dementia, Composite Hybrid Feature Selection, Machine learning, Stack ‎Hybrid Classification, AI Techniques, Classification, AD Diagnose, Clinical AD Dataset.