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: | Zhiqiang Lao |
| Institution: | University of Pennsylvania |
| Department: | Radiology |
| Country: | |
| Proposed Analysis: | Predictive Modeling of Alzheimer's Disease Progression Using Multi-modal ADNI Data The objective of this analysis is to develop a predictive model that can estimate the progression of Alzheimer's disease using multi-modal data from the ADNI dataset. Planned analysis steps are as follows: 1. Data Collection: Access the ADNI database and gather relevant multi-modal data, including clinical, imaging (MRI, PET), and cognitive assessment measures. 2. Data Preprocessing: Preprocess the collected data by handling missing values, normalizing imaging data, and applying appropriate feature selection techniques. 3. Feature Engineering: Extract relevant features from the multi-modal data, such as volumetric measures from MRI, standardized uptake values from PET, and cognitive scores from assessments. 4. Model Development: Utilize machine learning or statistical modeling techniques to develop a predictive model. Examples include logistic regression, support vector machines, random forests, or deep learning algorithms. 5. Cross-validation: Perform cross-validation to evaluate the model's performance and generalizability. Split the data into training and testing sets, and iteratively train and evaluate the model on different subsets of the data. 6. Performance Evaluation: Assess the model's performance using appropriate evaluation metrics such as accuracy, precision, recall, and area under the receiver operating characteristic curve (AUC-ROC). 7. Interpretation and Analysis: Interpret the model's results to gain insights into the important features and their contributions to Alzheimer's disease progression. Perform additional subgroup analyses if applicable (e.g., different disease stages, demographic factors). 8. Validation: If possible, validate the developed model on an external dataset or compare the results with other existing models or clinical measures. Expected Outcomes: The proposed analysis aims to create a predictive model that can estimate the progression of Alzheimer's disease based on multi-modal data from the ADNI dataset. The results can contribute to better understanding the disease progression patterns, identifying potential biomarkers, and aiding in early diagnosis and personalized treatment strategies. |
| Additional Investigators |
