Background:
Alzheimer’s disease affects millions worldwide, yet early detection remains a challenge. These challenges are due to the complexity and diverse range of factors involved, and also the long progression period as the disease develops over a long period, decades in many cases.

Goal:
This project aims to evolve a predictive model for assessing the probability of having the disease based on various factors, including demographics, medical, lifestyle, and cognitive factors.

Data:
There are some datasets on Alzheimer's disease, including ones that are not open to the public and need certain authorizations. An example of a public dataset can be found here:
https://www.kaggle.com/competitions/alzheimers-disease-risk-prediction-eu-business/data
Another dataset which requires granting access can be found here:
https://adni.loni.usc.edu/data-samples/adni-data/#AccessData
Since the factors recorded in each dataset might be different, we might have to do data cleaning and implement different models according to each set of factors and devise a method to combine the models' predictive capabilities.

Method:
Performing EDA to identify the relevant and impacting factors, classification based on categorical factors such as lifestyle, education level, and ethnicity, linear regression, etc.