Utilizing AI for Alzheimer's Diagnosis

This research assesses the potential of AI to improve early Alzheimer’s diagnosis by evaluating various classifier models, with results showing that while MLP classifier achieved only 32% accuracy, the Random Forest classifier excelled at 91.5%, highlighting the importance of factors like the mini mental state evaluation over others, as revealed in the Logistic Regression Feature Importance analysis.

Alzheimer’s is a serious disease and its early diagnosis is essential to properly understand the disease, access information, and provide sufficient care and support. This study hopes to assess the potential of AI to help early diagnoses. When properly used, AI could potentially diagnose Alzheimer’s with more efficiency and accuracy. Many classifier models were used: the MLP classifier had the least accuracy of 32%, the K Nearest Neighbors classifier had an accuracy of 60%, the Decision Tree Model had an accuracy of 72%, the Logistic Regression model had an accuracy of 83%, and the Random Forest classifier did the best with a 91.5% accuracy. There are many factors that the AI algorithm takes into consideration when making the diagnosis, and each factor is weighed differently. Factors like hand dominance had a smaller weight in the diagnosis than the mini mental state evaluation, and all of the analysis is covered in the Logistic Regression Feature Importance to shed light on the factor importance.

Explore More!

Research Paper

Project Webpage