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: | Hyewon Cho |
Institution: | UNIST |
Department: | Industrial Engineering |
Country: | |
Proposed Analysis: | This is Hyewon, from UNIST (Ulsan National Institute of Science and Technology). I am highly interested in applying AI (ML or DL) for healthcare industry. Currently, I am enrolled for PhD course in industrial engineering, and using multimodality for early disease prediction was one of my field of interest. Currently, I am also conducting research based on Korean National Health Insurance Database, for Korean-oriented disease prediction or other application. Meanwhile, I found this ADNI dataset through papers I've found interesting, and would be great if I can handle 'image, genomic, clinical dataset' for healthcare pespective. What I plan with the dataset is to figure out 'early detection of AD with various AI methods (ML, DL or ensemble methods)'. I am looking forward to having chance for exploring the dataset and building meaningful AI model with the given data. |
Additional Investigators | |
Investigator's Name: | Hyewon Kang |
Proposed Analysis: | My main research interest resides in 'disease-prediction by multiple data modalities. Since explosively increasing data, utilizing only a single data modality is a waste of resources to develop prediction models. A multi-modal fusion learning method is essential to integrate abundant data types to develop state-of-the-art prediction models. In particular, I am in charge of genomic data-based disease-prediction model development with multiple data modalities so that the ADNI data, which includes multiple types of data related to the healthcare domain, perfectly suits my main research interest. I look forward to using the ADNI data to successfully provide a high-quality disease-prediction model based on the multi-model fusion learning method. |
Investigator's Name: | Hansol Jang |
Proposed Analysis: | I have a interest in research to find the optimal embedding of data and to develop multimodal deep learning models. Now, I'm developing the prediction algorithms such as failure prediction based on customers' electronic device repair record data. It is being considered to collect additional data which is a different type from record data and develop it into a multi-modal deep learning model. While reading the paper in relation to this, I found the database. The database is likely to be helpful from the perspective of modeling that finds the optimal embedding of each different type of data and develops it into a multi-modal deep learning model. |