ADNI data is made available to researchers around the world. As such, there are many active research projects accessing and applying the shared ADNI data. To further encourage Alzheimer’s disease research collaboration, and to help prevent duplicate efforts, the list below shows the specific research focus of the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Sei Lee |
| Institution: | UCSF/SFVA |
| Department: | Medicine-Geriatrics |
| Country: | |
| Proposed Analysis: | Our objective is to improve the targeting of Alzheimers disease screening by improving the accuracy of predicting which patients will develop Alzheimers related cognitive impairment before death. Guided by previously published models of step-wise progression of Alzheimer’s pathology (Amyloid β accumulation, synaptic dysfunction, τ-mediated neuronal injury and brain volume loss), we will integrate MRI, PET and CSF biomarkers using hidden markov models (HMM) to predict future cognitive impairment. By incorporating risk factors for all cause mortality such as age, gender, physical function and comorbidities (AIBL), our HMM will predict the risk of developing clinical symptoms of cognitive impairment before death. Hidden Markov Models focus on transition probabilities between disease states, allowing us to fully leverage the slightly different strengths of ADNI and AIBL data. For example, if specific data elements are only available in AIBL (e.g. comorbidities), we will rely on AIBL data for this aspect of our prediction models. Conversely, if other data elements are only available in ADNI (e.g. processed image results), we will rely on ADNI data for this aspect of our prediction models. |
| Additional Investigators | |
| Investigator's Name: | deborah barnes |
| Proposed Analysis: | Our objective is to improve the targeting of Alzheimers disease screening by improving the accuracy of predicting which patients will develop Alzheimers related cognitive impairment before death. Guided by previously published models of step-wise progression of Alzheimer’s pathology (Amyloid β accumulation, synaptic dysfunction, τ-mediated neuronal injury and brain volume loss), we will integrate MRI, PET and CSF biomarkers using hidden markov models (HMM) to predict future cognitive impairment. By incorporating risk factors for all cause mortality such as age, gender, physical function and comorbidities (AIBL), our HMM will predict the risk of developing clinical symptoms of cognitive impairment before death. Hidden Markov Models focus on transition probabilities between disease states, allowing us to fully leverage the slightly different strengths of ADNI and AIBL data. For example, if specific data elements are only available in AIBL (e.g. comorbidities), we will rely on AIBL data for this aspect of our prediction models. Conversely, if other data elements are only available in ADNI (e.g. processed image results), we will rely on ADNI data for this aspect of our prediction models. |
| Investigator's Name: | john boscardin |
| Proposed Analysis: | Our objective is to improve the targeting of Alzheimers disease screening by improving the accuracy of predicting which patients will develop Alzheimers related cognitive impairment before death. Guided by previously published models of step-wise progression of Alzheimer’s pathology (Amyloid β accumulation, synaptic dysfunction, τ-mediated neuronal injury and brain volume loss), we will integrate MRI, PET and CSF biomarkers using hidden markov models (HMM) to predict future cognitive impairment. By incorporating risk factors for all cause mortality such as age, gender, physical function and comorbidities (AIBL), our HMM will predict the risk of developing clinical symptoms of cognitive impairment before death. Hidden Markov Models focus on transition probabilities between disease states, allowing us to fully leverage the slightly different strengths of ADNI and AIBL data. For example, if specific data elements are only available in AIBL (e.g. comorbidities), we will rely on AIBL data for this aspect of our prediction models. Conversely, if other data elements are only available in ADNI (e.g. processed image results), we will rely on ADNI data for this aspect of our prediction models. |
| Investigator's Name: | Irena Stijacic Cenzer |
| Proposed Analysis: | Ms Cenzer will support Drs Lee, Barnes and Boscardin in predicting which patients will develop symptoms of cognitive impairment in the ADNI/AIBL cohorts. |