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: | Jeanne Latourelle |
Institution: | GNS Healthcare |
Department: | Precision Medicine |
Country: | |
Proposed Analysis: | GNS will apply its data-driven REFS platform to build, in an unbiased manner, in silico AD models from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). These causal models will probabilistically characterize the network connections between the key parameters that drive cognitive decline, and identify the genetic drivers of AD and its progression. Using these REFS models, researchers will be able to project the risk of transition to AD for patient with mild cognitive impairment, and predict outcomes of AD patients (i.e. cognitive score). The early identification of AD and better understanding of the disease trajectory could enable optimization of clinical trial selection. In addition, the models could be used to target patients at risk of AD at an early stage and provide appropriate treatment. |
Additional Investigators | |
Investigator's Name: | Rahul Das |
Proposed Analysis: | GNS will apply its data-driven REFS platform to build, in an unbiased manner, in silico AD models from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). These causal models will probabilistically characterize the network connections between the key parameters that drive cognitive decline, and identify the genetic drivers of AD and its progression. Using these REFS models, researchers will be able to project the risk of transition to AD for patient with mild cognitive impairment, and predict outcomes of AD patients (i.e. cognitive score). The early identification of AD and better understanding of the disease trajectory could enable optimization of clinical trial selection. In addition, the models could be used to target patients at risk of AD at an early stage and provide appropriate treatment. UPDATED (2019-07-23) :GNS is continuing to evaluate the data for use in causal disease modeling efforts as described in the original analysis proposal. |
Investigator's Name: | So-Youn Shin |
Proposed Analysis: | GNS will apply its data-driven REFS platform to build, in an unbiased manner, in silico AD models from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). These causal models will probabilistically characterize the network connections between the key parameters that drive cognitive decline, and identify the genetic drivers of AD and its progression. Using these REFS models, researchers will be able to project the risk of transition to AD for patient with mild cognitive impairment, and predict outcomes of AD patients (i.e. cognitive score). The early identification of AD and better understanding of the disease trajectory could enable optimization of clinical trial selection. In addition, the models could be used to target patients at risk of AD at an early stage and provide appropriate treatment. UPDATED (2019-07-23) :GNS is continuing to evaluate the data for use in causal disease modeling efforts as described in the original analysis proposal. |
Investigator's Name: | Jing Tu |
Proposed Analysis: | GNS will apply its data-driven REFS platform to build, in an unbiased manner, in silico AD models from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). These causal models will probabilistically characterize the network connections between the key parameters that drive cognitive decline, and identify the genetic drivers of AD and its progression. Using these REFS models, researchers will be able to project the risk of transition to AD for patient with mild cognitive impairment, and predict outcomes of AD patients (i.e. cognitive score). The early identification of AD and better understanding of the disease trajectory could enable optimization of clinical trial selection. In addition, the models could be used to target patients at risk of AD at an early stage and provide appropriate treatment. UPDATED (2019-07-23) :GNS is continuing to evaluate the data for use in causal disease modeling efforts as described in the original analysis proposal. |
Investigator's Name: | Tanveer Talukdar |
Proposed Analysis: | GNS will apply its data-driven REFS platform to build, in an unbiased manner, in silico AD models from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). These causal models will probabilistically characterize the network connections between the key parameters that drive cognitive decline, and identify the genetic drivers of AD and its progression. Using these REFS models, researchers will be able to project the risk of transition to AD for patient with mild cognitive impairment, and predict outcomes of AD patients (i.e. cognitive score). The early identification of AD and better understanding of the disease trajectory could enable optimization of clinical trial selection. In addition, the models could be used to target patients at risk of AD at an early stage and provide appropriate treatment. UPDATED (2019-07-23) :GNS is continuing to evaluate the data for use in causal disease modeling efforts as described in the original analysis proposal. UPDATED (2020-08-12) :GNS is using the ADNI data for causal disease modeling efforts as described in the original analysis proposal. We are further using the causal models to explore mechanistic underpinnings of AD outcomes and novel target identification. |
Investigator's Name: | Deepanshi Shokeen |
Proposed Analysis: | In this project, GNS Healthcare will apply its data-driven REFS platform to build, in an unbiased manner, in silico causal models using the ADNI data. These causal models will probabilistically characterize directed causal relationships between genetic and molecular features driving disease state and cognitive decline and identify the mechanistic underpinnings of AD and its progression. Taken together the models will result in an in silico AD patient allowing for simulated interventions to be tested and assessed. By leveraging our causal AI approach, we will be able to provide insights, predictions and results of in silico experiments to enable R&D efforts for third party partners (but no data will be externally shared). |