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: | Hyunjung Shin |
| Institution: | Ajou University |
| Department: | Department of Industrial Engineering |
| Country: | |
| Proposed Analysis: | The study aims to develop an artificial intelligence model that diversifies medical diagnosis by using various information from multi-modal data of dementia patients and provides a precision medical solution that reflects racial and national characteristics. 1. Dementia-related gene discovery and candidate treatment selection In order to discover key genes and candidate drugs, biological information such as proteins and SNPs and chemical information such as drugs and compounds are used. We develop a network-based machine learning model for bio information learning characterized by a hierarchical connection structure. 2. Development of a diversified dementia diagnosis model The model to be developed is a diversified diagnostic model based on specific dementia diseases, namely, Alzheimer's disease, vascular dementia, Parkinson's disease, Huntington's disease, Lewy body dementia, frontotemporal dementia, and Lewy body dementia. For this purpose, deep learning models such as convolutional neural networks and generative adversarial networks are used. 3. Dementia precision medical solution development Based on domestic patient data in Korea, comparisons between ADNI patients by race and country are possible. Through this, the composition of the dementia diagnosis model, treatments, and side effect information of related drugs can be derived for each individual. |
| Additional Investigators | |
| Investigator's Name: | Dong-gi Lee |
| Proposed Analysis: | We intend to develop a method for refinement and diversification of a dementia diagnosis model using various patient information. The precise diagnosis process predicts the onset of dementia with a learning module for each data and leads to an integrated module. Genetic information diagnosis develops a semi-supervised regression model for hierarchical networks and propagates SNP and genetic information to higher-level disease networks. For brain image and clinical examination information, deep convolutional neural networks and deep neural networks are applied, respectively. The integrated module will utilize an ensemble learning-based optimization algorithm. The diversified precise diagnosis model gives comprehensive diagnosis based on degenerative brain diseases, such as Alzheimer's disease, vascular dementia, Parkinson's disease, Huntington's disease, or frontotemporal and Lewy body dementia. |
