Collaborative Research: FDT-BioTech: Aspects of Digital Twin Studies for Neuroimages

Neurodegenerative diseases (for example, Alzheimer's disease, Parkinson's disease, multiple sclerosis) impact millions of people in the United States and result in hundreds of thousands of deaths. These disorders can affect people of all ages, although they are more common in older adults. Digital twin models, leveraging the exponential growth of biomedical data and artificial intelligence and data science techniques, are opening exciting avenues to obtain new insights into these diseases and revolutionize their treatment and prevention. The investigators will address multiple problems on this interface, and develop data science-driven theoretical foundations, methodological tools and algorithmic principles for several aspects of digital twin models towards better understanding of digital twins as a whole, and in particular in the context of their use in neuroscience and in prevention, treatment and better understanding of neurodegenerative diseases. They will also address the ethical, legal, and social implications of using digital twin models in the context of healthcare in general, and in studying neurodegenerative diseases using magnetic resonance-technology driven images (MRI) in particular. This research will greatly aid in the deployment of digital twins in medical and healthcare practice, and will significantly advance neuroscience and the study of neurodegenerative diseases. The investigators will address open problems in low-dimensional manifold learning, causal pathway searches and feature discoveries and selections, and develop multiple techniques for verification, validation and uncertainty quantification of digital twins using Bayesian techniques, data assimilation, resampling, empirical likelihood methods and topological data analysis. They will also develop dynamical system models, incorporating observational image data, for computational efficiency and synthetic data generation for ethical use of artificial intelligence and digital twin technology in studying neurodegenerative diseases. Additionally, they will develop knowledge graph driven systems for use by regulatory and other healthcare monitoring agencies for de-risking and easy implementation of data-driven modern technologies. The investigators will work in conjunction with regulatory and other healthcare governing agencies towards better understanding of neurodegenerative diseases and successful deployment of data-driven technologies to mitigate suffering from such diseases. The investigators will mentor, train and teach students on various aspects of digital twins, data science and neuroscience and their interconnections, and will help build a highly skilled workforce on these topics. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.