SBIR - TOPIC 009 - AI/ML TOOL FOR VISUALIZING BEHAVIORAL AND SOCIAL SCIENCE RESEARCH

The purpose of this project is to develop an AI-based tool for Behavioral and Social Science Research (BSR) - specific literature visualization and hypothesis discovery that might be marketed ultimately to various institutions that consume scientific research, with an emphasis on Alzheimer's disease. Such a tool would likely reduce the time for understanding the conceptual structure of the literature from hours to seconds, accelerating scientific discovery. The tool will be particularly relevant for novice Alzheimer's disease researchers, who can use it to educate themselves on existing BSR research and uncover ways to leverage this research towards improving care outcomes for persons with Alzheimer's disease (PwD) and their caregivers. The Contractor will develop a patented, generative AI-based literature search and visualization tool and ensure that all content, graphics, and visuals are in compliance with the Section 508 Standards. The tool will automatically mine scientific papers and research grants and generates aggregate, interactive causal maps of the literature that combine a schematic overview of all the causation/correlation relationships examined on a given topic with a detailed representation of each relationship - including the relationship's sign and strength (for meta-analyses papers), moderating and mediating factors, and corresponding research papers/grants. In the Phase I, the AI-based literature search and visualization tool will be populated primarily with findings extracted from meta-analyses related to AD/ADRD, which will be ontologically classified, thus helping users easily discern the impact of different risk/prevention factors and treatments on AD/ADRD and the associations between AD/ADRD and various health and social outcomes.