There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Talel GHOBBER |
| Institution: | esprit |
| Department: | IT |
| Country: | |
| Proposed Analysis: | As part of my university internship, I intend to employ Machine Learning algorithms for the detection and prediction of Alzheimer's disease using clinical data and biomarkers available in the ADNI datasets. The proposed analyses are as follows: Alzheimer's disease detection: Utilize a classification algorithm, such as logistic regression, to develop a model for detecting the presence of Alzheimer's disease in patients based on clinical data, brain imaging (MRI) results, and biomarkers. Evaluate the model's performance using metrics like sensitivity, specificity, and accuracy to assess its effectiveness in early detection of Alzheimer's disease. Alzheimer's disease progression prediction: Employ regression algorithms, such as linear regression or support vector machines, to build a model for predicting the progression of Alzheimer's disease in patients with mild cognitive impairment (MCI) using the available data. Assess the model's performance using evaluation measures like root mean squared error (RMSE) to evaluate the accuracy of disease progression predictions. Identification of predictive biomarkers: Employ variable selection methods like Lasso regression or feature importance-based feature selection to identify the most predictive biomarkers for Alzheimer's disease within the ADNI datasets. Analyze the correlation between the selected biomarkers and cognitive measures to gain insights into the factors associated with disease progression. Comparison of algorithm performance: Compare the performance of different Machine Learning algorithms, such as neural networks, support vector machines, and random forests, for Alzheimer's disease detection and prediction. Evaluate performance metrics (sensitivity, specificity, precision) to determine the algorithm that provides the best detection and prediction outcomes. |
| Additional Investigators |
