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: | Xi Chen |
| Institution: | Sun Yat-sen University Cancer Center |
| Department: | Department of Nasopharyngeal Carcinoma |
| Country: | |
| Proposed Analysis: | We performed lipidomic analysis on plasma of a group of nasopharyngeal carcinoma patients before treatment, but due to the small sample size (n=150), we hope to apply metabolomics data for model pre-training. It remains challenging to build good predictive models especially when the sample size is limited and the number of features is high. By reading the literatures, we laerned a meta-learning approach for survival analysis. Meta-learning is a significantly more effective paradigm to leverage highdimensional data that is relevant but not directly related to the problem of interest. Specifically, meta-learning explicitly constructs a model, from abundant data of relevant tasks, to learn a new task with few samples effectively. Theerefore, we would like to apply here for ADNI data for meta-learning. |
| Additional Investigators | |
| Investigator's Name: | Yingxue Li |
| Proposed Analysis: | We performed lipidomic analysis on plasma of a group of nasopharyngeal carcinoma patients before treatment, but due to the small sample size (n=150), we hope to apply metabolomics data for model pre-training. It remains challenging to build good predictive models especially when the sample size is limited and the number of features is high. By reading the literatures, we laerned a meta-learning approach for survival analysis. Meta-learning is a significantly more effective paradigm to leverage highdimensional data that is relevant but not directly related to the problem of interest. Specifically, meta-learning explicitly constructs a model, from abundant data of relevant tasks, to learn a new task with few samples effectively. Theerefore, we would like to apply here for ADNI data for meta-learning. Yingxue Li will focus on the application of meta-learning and model pretraining. |
