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: | Yi-Ju Lee |
| Institution: | Academia Sinica |
| Department: | Institute of Statistical Science |
| Country: | |
| Proposed Analysis: | In this research, we aim to establish genetic and imaging markers of phenotyping Alzheimer’s diseases. In the recent decade, the flood of applications with Artificial Intelligence (AI) has led to a paradigm shift in medical research, reshaping the healthcare system overwhelmingly. The deep learning approach has challenged how the diseases were recognized. The digitalized big health-related data has increased the quality of medicine and supporting the boost of technique development. To possibly extracting the full value of data, national programs have been initiated worldwide to use such real-world data to conduct important clinical evidence, such as All of Us Program in the United States, UK Biobank and Taiwan Precision Medicine Initiative (TPMI). Taking the advantage of developing techniques, there are genomic data that are introduced in more details, the phenotype data can be extracted from the electronic medical records, and the multi-omics research allows us to understand the complex normal and pathological mechanisms holistically. The aim of this project is to make use of health big data to advance the current AI models and methods with statistical thinking. With the performance breakthrough of deep neural networks and GPU implementation, AI models have been created for diagnostic classification, lesion segmentation, pathological prediction in the clinics. Goal: Predicting neurodegenerative-brain structure change with genetic and clinical data. Data: ADNI dataset (genetic data, clinical data, brain structural MRI image) and domestic data. Methods: In addition to the methods developed, here we will further focus on identifying genetic and imaging markers as well as their interactions associated with the progression of Alzheimer’s diseases. We expect deep neural network models can be effective in characterizing and gaining insights into the genetic-imaging interactions and prediction of disease progression. Statistical thinking from model reduction, regularization, feature selection, etc. can be integrated into the deep model for better robust and more efficient statistical inferences. |
| Additional Investigators | |
| Investigator's Name: | Su-Yun Huang |
| Proposed Analysis: | In this research, we aim to establish genetic and imaging markers of phenotyping Alzheimer’s diseases. In the recent decade, the flood of applications with Artificial Intelligence (AI) has led to a paradigm shift in medical research, reshaping the healthcare system overwhelmingly. The deep learning approach has challenged how the diseases were recognized. The digitalized big health-related data has increased the quality of medicine and supporting the boost of technique development. To possibly extracting the full value of data, national programs have been initiated worldwide to use such real-world data to conduct important clinical evidence, such as All of Us Program in the United States, UK Biobank and Taiwan Precision Medicine Initiative (TPMI). Taking the advantage of developing techniques, there are genomic data that are introduced in more details, the phenotype data can be extracted from the electronic medical records, and the multi-omics research allows us to understand the complex normal and pathological mechanisms holistically. The aim of this project is to make use of health big data to advance the current AI models and methods with statistical thinking. With the performance breakthrough of deep neural networks and GPU implementation, AI models have been created for diagnostic classification, lesion segmentation, pathological prediction in the clinics. Goal: Predicting neurodegenerative-brain structure change with genetic and clinical data. Data: ADNI dataset (genetic data, clinical data, brain structural MRI image) and domestic data. Methods: In addition to the methods developed, here we will further focus on identifying genetic and imaging markers as well as their interactions associated with the progression of Alzheimer’s diseases. We expect deep neural network models can be effective in characterizing and gaining insights into the genetic-imaging interactions and prediction of disease progression. Statistical thinking from model reduction, regularization, feature selection, etc. can be integrated into the deep model for better robust and more efficient statistical inferences. |
| Investigator's Name: | Hsin-Chou Yang |
| Proposed Analysis: | In this research, we aim to establish genetic and imaging markers of phenotyping Alzheimer’s diseases. In the recent decade, the flood of applications with Artificial Intelligence (AI) has led to a paradigm shift in medical research, reshaping the healthcare system overwhelmingly. The deep learning approach has challenged how the diseases were recognized. The digitalized big health-related data has increased the quality of medicine and supporting the boost of technique development. To possibly extracting the full value of data, national programs have been initiated worldwide to use such real-world data to conduct important clinical evidence, such as All of Us Program in the United States, UK Biobank and Taiwan Precision Medicine Initiative (TPMI). Taking the advantage of developing techniques, there are genomic data that are introduced in more details, the phenotype data can be extracted from the electronic medical records, and the multi-omics research allows us to understand the complex normal and pathological mechanisms holistically. The aim of this project is to make use of health big data to advance the current AI models and methods with statistical thinking. With the performance breakthrough of deep neural networks and GPU implementation, AI models have been created for diagnostic classification, lesion segmentation, pathological prediction in the clinics. Goal: Predicting neurodegenerative-brain structure change with genetic and clinical data. Data: ADNI dataset (genetic data, clinical data, brain structural MRI image) and domestic data. Methods: In addition to the methods developed, here we will further focus on identifying genetic and imaging markers as well as their interactions associated with the progression of Alzheimer’s diseases. We expect deep neural network models can be effective in characterizing and gaining insights into the genetic-imaging interactions and prediction of disease progression. Statistical thinking from model reduction, regularization, feature selection, etc. can be integrated into the deep model for better robust and more efficient statistical inferences. |
