There is an urgent need amongst healthcare researchers to introduce creative solutions to address the challenges of caring for our growing aging population in diverse healthcare settings, including the need to predict disease development and treatment outcomes.

The availability of genetic, imaging and behavioural data allow the leveraging of machine learning to predict and distinguish different disease processes and phenotypes. The powerful and multi-faceted manner in which Artificial Intelligence (AI) enhances our knowledge of the human brain will help us develop better tools for detecting neurodegeneration in a cost-effective manner.

However, challenges exist in the acceleration of the impact of AI in clinical settings. One barrier is a lack of multidisciplinary integration for AI design, implementation, refinement and decision making for maximum impact. For example, a data scientist who is an expert in AI algorithms will likely not have the clinical expertise or sufficient knowledge of the clinical workflows to design the most feasible tools for existing healthcare models. Furthermore, hospital leadership teams need to consult with both scientists and clinicians to make the best decisions regarding AI. The importance of involving key stakeholders cannot be understated in turning the dial in the application of AI in healthcare.

Advancing Aging and Neurodegeneration Research through Data Science, a Data Sciences Institute Emergent Data Science Program, aims to provide a suite of training opportunities which address such challenges and cater to diverse audiences. The training program will provide a diverse set of learning and collaborative opportunities to bring together data scientists, clinicians, educators, to discuss the development of new areas of research which can ultimately benefit the treatment, care, and healthcare service delivery for older adults.

The following topics will be addressed:

• The use of data science and machine learning in aging neuroscience and neurology, e.g. the use of AI to uncover new disease mechanisms and disease-modifying solutions;
• The use of deep learning AI applications in aging and healthcare, e.g. the application natural language processing and optimization of early disease detection and hospital care;
• Promoting open-science best practices for data science
• Addressing the challenges of applying AI to answer scientific questions related to aging, e.g. explainability and generalization;
• The ethics of AI in research and care, e.g. data privacy and safety, legal considerations and bias mitigation.