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: | Yicheng Li |
| Institution: | Nanyang Technological University |
| Department: | School of Electrical and Electronic Engineering |
| Country: | |
| Proposed Analysis: | Purely data-driven methodologies in Machine Learning (ML) has been encountering their challenges in practice, such as requirement of huge amount of training data, inconsistency of the predictions with the physical world (e.g. a negative prediction of stock price). There is an increasing awareness of combining physics/domain knowledge into ML for better modelling performance. This project will be focusing on physics/domain knowledge incorporation into ML models for longitudinal data (a type of time series, e.g. medical records of a patient across time) modelling. In this project, the student will: 1) conduct a comprehensive survey on physics-constrained ML; 2) implement selected algorithms on selected use case with longitudinal data; 3) further research on the algorithm for performance improvement. |
| Additional Investigators | |
| Investigator's Name: | Feng Yang |
| Proposed Analysis: | Analytical methods have been established for the study of longitudinal data in medical treatments. This project will finally apply the model on a collection of real-world datasets to estimate the progression, e.g. eye disease progression with data retrieved from clinical measurements and testing. A common practice involves manipulating the individual data in time sequence, as a comprise to subject-specific disease progression with respect to age. |
| Investigator's Name: | Feng Yang |
| Proposed Analysis: | Analytical methods have been established for the study of longitudinal data in medical treatments. This project will finally apply the model on a collection of real-world datasets to estimate the progression, e.g. eye disease progression with data retrieved from clinical measurements and testing. A common practice involves manipulating the individual data in time sequence, as a comprise to subject-specific disease progression with respect to age. |
