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: | Hichem Sahli |
| Institution: | Vrije Universiteit Brussel (VUB) |
| Department: | Elctronics & Informatics (ETRO) |
| Country: | |
| Proposed Analysis: | At the Department of Electronics and Informatics (ETRO) of the Vrije Universiteit Brussel (VUB), in collaboration with the Cognition and Modelling lab (CIME, Department of Observational Clinical Sciences, faculty of Medicine and Pharmacy) and the University Hospital Brussels (Universitair Ziekenhuis Brussel, UZ), we are developing clinical prediction models of Alzheimer's disease. The team has a long record experience developing and applying statistical analysis and machine learning tools on different degenerative diseases, including Alzheimer's disease. We intend to use ADNI data to train complex models able to learn the interaction of different biomarkers along the course of the disease, and to explore the predictive power of models trained with different combinations of biomarkers. Our approach consists in extracting relevant features for each biomarker, for example: using Deep Learning or Tensor Based Morphometry tools to extract information from structural MRI images; bayesian Item Response Theory models for Neuropsychological Battery; etc., and later combine the extracted features to build multimodal prediction models. We are interested in early identification of people at high risk of developing Alzheimer among patients with memory complaints or mild cognitive impairment, therefore ADNI study is particularly suitable. |
| Additional Investigators | |
| Investigator's Name: | Matias Bossa |
| Proposed Analysis: | At the Department of Electronics and Informatics (ETRO) of the Vrije Universiteit Brussel (VUB), in collaboration with the Cognition and Modelling lab (CIME, Department of Observational Clinical Sciences, faculty of Medicine and Pharmacy) and the University Hospital Brussels (Universitair Ziekenhuis Brussel, UZ), we are developing clinical prediction models of Alzheimer's disease. The team has a long record experience developing and applying statistical analysis and machine learning tools on different degenerative diseases, including Alzheimer's disease. We intend to use ADNI data to train complex models able to learn the interaction of different biomarkers along the course of the disease, and to explore the predictive power of models trained with different combinations of biomarkers. Our approach consists in extracting relevant features for each biomarker, for example: using Deep Learning or Tensor Based Morphometry tools to extract information from structural MRI images; bayesian Item Response Theory models for Neuropsychological Battery; etc., and later combine the extracted features to build multimodal prediction models. We are interested in early identification of people at high risk of developing Alzheimer among patients with memory complaints or mild cognitive impairment, therefore ADNI study is particularly suitable. |
| Investigator's Name: | Jef Vandemeulebroucke |
| Proposed Analysis: | At the Department of Electronics and Informatics (ETRO) of the Vrije Universiteit Brussel (VUB), in collaboration with the Cognition and Modelling lab (CIME, Department of Observational Clinical Sciences, faculty of Medicine and Pharmacy) and the University Hospital Brussels (Universitair Ziekenhuis Brussel, UZ), we are developing clinical prediction models of Alzheimer's disease. The team has a long record experience developing and applying statistical analysis and machine learning tools on different degenerative diseases, including Alzheimer's disease. We intend to use ADNI data to train complex models able to learn the interaction of different biomarkers along the course of the disease, and to explore the predictive power of models trained with different combinations of biomarkers. Our approach consists in extracting relevant features for each biomarker, for example: using Deep Learning or Tensor Based Morphometry tools to extract information from structural MRI images; bayesian Item Response Theory models for Neuropsychological Battery; etc., and later combine the extracted features to build multimodal prediction models. We are interested in early identification of people at high risk of developing Alzheimer among patients with memory complaints or mild cognitive impairment, therefore ADNI study is particularly suitable. |
