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: | Gabriel Owusu |
| Institution: | University of Texas Rio Grande Valley |
| Department: | Information Systems |
| Country: | |
| Proposed Analysis: | Data Preprocessing: Preprocess the dataset by performing tasks such as data cleaning, missing value imputation, feature selection, and normalization to ensure data quality and compatibility with deep learning algorithms. CNN Model Development: Design and implement a convolutional neural network (CNN) architecture suitable for Alzheimer's disease prediction. This will involve configuring appropriate layers, filters, activation functions, and optimization algorithms to achieve optimal performance. Model Training and Validation: Split the dataset into training and validation sets and train the CNN model using the training data. Optimize the model's hyperparameters, evaluate its performance using appropriate metrics, and validate its robustness through techniques like cross-validation. Performance Evaluation: Assess the predictive performance of the developed model using various evaluation metrics such as accuracy, precision, recall, F1-score, and receiver operating characteristic (ROC) curve analysis. Conduct comparative analyses with existing methods or benchmarks, if available, to validate the effectiveness of the proposed approach. Interpretation and Feature Importance: Investigate the learned representations and feature importance in the CNN model to gain insights into the underlying biomarkers and image features contributing to Alzheimer's disease prediction. This analysis can provide valuable insights for further research and understanding of the disease. Reporting and Dissemination: Upon completion of the proposed analysis, I intend to prepare a comprehensive report summarizing the research findings, methodology, and results obtained from the predictive model. Additionally, I plan to present the findings at relevant conferences and submit the research for publication in reputable scientific journals to contribute to the field of Alzheimer's disease research and healthcare information systems. |
| Additional Investigators | |
| Investigator's Name: | Xuan Wang |
| Proposed Analysis: | Dr. Xuan happens to be my advisor, and she already got approval for this dataset, and hence we will be doing the same research. The proposed analysis is similar to what I reported earlier in my submission. Thus: Data Preprocessing: Preprocess the dataset by performing tasks such as data cleaning, missing value imputation, feature selection, and normalization to ensure data quality and compatibility with deep learning algorithms. CNN Model Development: Design and implement a convolutional neural network (CNN) architecture suitable for Alzheimer's disease prediction. This will involve configuring appropriate layers, filters, activation functions, and optimization algorithms to achieve optimal performance. Model Training and Validation: Split the dataset into training and validation sets and train the CNN model using the training data. Optimize the model's hyperparameters, evaluate its performance using appropriate metrics, and validate its robustness through techniques like cross-validation. Performance Evaluation: Assess the predictive performance of the developed model using various evaluation metrics such as accuracy, precision, recall, F1-score, and receiver operating characteristic (ROC) curve analysis. Conduct comparative analyses with existing methods or benchmarks, if available, to validate the effectiveness of the proposed approach. Interpretation and Feature Importance: Investigate the learned representations and feature importance in the CNN model to gain insights into the underlying biomarkers and image features contributing to Alzheimer's disease prediction. This analysis can provide valuable insights for further research and understanding of the disease. Reporting and Dissemination: Upon completion of the proposed analysis, I intend to prepare a comprehensive report summarizing the research findings, methodology, and results obtained from the predictive model. Additionally, I plan to present the findings at relevant conferences and submit the research for publication in reputable scientific journals to contribute to the field of Alzheimer's disease research and healthcare information systems. |
