Home

BSO-AD

Standardizing and Harmonizing Behavioral and Social Science Research Factors in Alzheimer's Disease through Ontology-Based Approaches

Award Number: U01AG088076

NIH RePORTER Project Details: https://reporter.nih.gov/search/bGo56Rz6q0Sdz98guPjnjw/project-details/11180321

Principal Investigators

Cui Tao and Jiang Bian

Overview

Behavioral and social science research (BSSR) is instrumental in comprehending Alzheimer's Disease and related dementia (ADRD) and their profound impact on individuals, families, and communities. However, absence of formal representations for BSSR data and limited tools to link comprehensive BSSR information to ADRD from diverse sources poses significant challenges.
This project pioneers ontology-driven approaches to standardize and formally represent ADRD-related BSSR factors. We will develop natural language processing (NLP) methods, including large language models (LLMs), to extract and normalize BSSR data from scientific literature and electronic health records (EHRs).
We will further build a comprehensive and normalized knowledge graph (KG) that unifies BSSR factors into ADRD by integrating structured and unstructured data across research silos.
Innovation of the project lies in four key aspects:

1.

Development of a formal ontological representation of BSSR elements related to ADRD that aligns with existing standards, involving iterative refinement;

2.

Development of advanced NLP systems to extract, normalize, and encode essential BSSR information pertaining to ADRD;

3.

LLMs-empowered ontology enrichment, semantic triple extraction, and KG generation;

4.

Systematic evaluation of the informatics solutions through conducting both EHRs-based observational demonstration studies and literature-drive knowledge validation.

Resources

GitHub will be shared after the first ontology paper is published.

Publications

Hou Z, Liu H, Bian J, He X, Zhuang Y. Enhancing medical coding efficiency through domain-specific fine-tuned large language models. Npj Health Syst. 2025;2(1):14. https://doi.org/10.1038/s44401-025-00018-3 Epub 2025 May 1. PMID: 40321467.

Amith M, Yu Y, Shi YH, et al. An ontology-based method for formalizing and encoding patient colonoscopy preparation using BPMN and OWL2 for automated tool development. Journal of Clinical Informatics, 2025. doi: 10.36922/jci.8599

Hasan WU, Zaman KT, Wang X, et al. Empowering Alzheimer's caregivers with conversational AI: a novel approach for enhanced communication and personalized support. npj Biomed. Innov. 1, 3 (2024) https://doi.org/10.1038/s44385-024-00004-8

Hao XB, Cui LC, Tao C, et al. Analyzing Llama 3-based approach for axiom translation from ontologies. KBC-LM'24: Knowledge Base Construction from Pre-trained Language Models workshop at ISWC 2024 https://ceur-ws.org/Vol-3853/paper5.pdf

Amith M, Yu Y, Shi YH, et al. BPMN and OWL2 ontology-based methods to formalize and encode colonoscopy preparation. Accepted by the Journal of Clinical Informatics.

Team

Cui Tao

Principal Investigator

Cui Tao, PhD, Department of Artificial Intelligence and Informatics, Mayo Clinic, tao.cui@mayo.edu

Cui Tao is the inaugural Enterprise Chair of the Department of Artificial Intelligence and Informatics at Mayo Clinic. She serves as Vice President of Mayo Clinic Platform and the Enterprise Deputy Co-director of Data Science and Artificial Intelligence at the Mayo Clinic Comprehensive Cancer Center.

She is a Professor of Biomedical Informatics and an elected fellow of the American College of Medical Informatics. Her background is in clinical informatics and computer science, and her research interests include ontologies, knowledge graphs, predictive modeling, deep learning, large language models, as well as applying these technologies to clinical and translational studies.

She is a recipient of the Presidential Early Career Awards for Scientists and Engineers (PECASE), the highest honor bestowed by the United States Government on science and engineering professionals in the early stages of their independent research careers. Her collective research funding surpasses $30 million. She has Ph.D. in computer science from Brigham Young University.

Jiang Bian

MPI

Jiang Bian, PhD, Regenstrief Institute, Indiana University, bianji@regenstrief.org

Fang Li

Co-Investigator

Fang Li, PhD, Department of Artificial Intelligence and Informatics, Mayo Clinic, li.fang@mayo.edu

Fang Li is an associate consultant and assistant professor at the Department of Artificial Intelligence and Informatics, Mayo Clinic. Her background is medical informatics. Her research interest includes ontology, knowledge graph, predictive modeling, and large language models.

She is the editorial board member of JAMIA and has over 40 journal and conference publications. She received her PhD degree in information and library science from the University of Chinese Academy of Sciences.

Lu Kang

Project Manager

Haifang Li

Researcher

Haifang Li, PhD, Department of Artificial Intelligence and Informatics, Mayo Clinic, Li.Haifang@mayo.edu

Haifang Li is a postdoctoral research fellow at Mayo Clinic. She earned her Ph.D. in Probability and Mathematical Statistics from the University of Chinese Academy of Sciences. Her research focuses on machine learning, natural language processing (NLP), and ontology-based knowledge representation, with applications in clinical and biomedical fields.

Yue Yu

Researcher/Working Group Lead

Yue Yu, PhD, Department of Artificial Intelligence and Informatics, Mayo Clinic, yu.yue1@mayo.edu

Yue Yu is an Assistant Professor of Biomedical Informatics and a Senior Data Science Analyst in the Department of Artificial Intelligence and Informatics at Mayo Clinic.

Dr. Yu's background is in biomedical informatics, and his research interests include medical data standardization, common data models, and machine learning, as well as the application of artificial intelligence technologies to support clinical and translational research. He earned his Ph.D. in Public Health from Jilin University.

Amit 'Tuan' Muhammad

Researcher

Weiguo Cao

Researcher

Weiguo Cao, PhD, Department of Artificial Intelligence and Informatics, Mayo Clinic, Cao.Weiguo@mayo.edu

Weiguo Cao is a postdoctoral research fellow in the Department of Artificial Intelligence and Informatics at Mayo Clinic. His background spans computer graphics, computer vision, medical image analysis, large language models, and machine learning.

Previously, he was a Postdoctoral Associate at Stony Brook University and a Senior Research Scientist at Alibaba Group. He holds a Ph.D. in computer science from the Institute of Computing Technology, Chinese Academy of Sciences.

Avanti Bhandarkar

Researcher

Avanti Bhandarkar, PhD, Department of Artificial Intelligence and Informatics, Mayo Clinic, Bhandarkar.Avanti@mayo.edu

Avanti Bhandarkar is a postdoctoral research fellow at Mayo Clinic. She received her PhD in Electrical and Computer Engineering from the University of Florida, where she specialized in natural language processing (NLP). She also holds an MS in Electrical and Computer Engineering from the University of Florida and a BE in Electronics and Telecommunication Engineering from G. H. Raisoni College of Engineering in India.

Dr. Bhandarkar's research focuses on NLP, applied artificial intelligence, and generative AI. Her work has led to over 10 publications in leading NLP, AI and interdisciplinary venues, including EACL, COLING, NAACL, IEEE, and the British Journal of Psychology.

Rakesh Kumar

Researcher

Rakesh Kumar, M.B.B.S., M.D., Department of Artificial Intelligence and Informatics, Mayo Clinic, Kumar.Rakesh@mayo.edu

Rakesh Kumar is a postdoctoral research fellow at Mayo Clinic. He holds an M.B.B.S. Goa medical college and an M.D. in Psychiatry from Guru Gobind Singh Medical College, where he also served as Chief Resident. Before joining Mayo Clinic, Dr. Kumar practiced psychiatry and served as a medical officer with the Government of India and State Government for nearly ten years.

His research focuses on the neurological mechanisms of mood disorders, development of objective biomarkers, and the application of artificial intelligence to advance psychiatric research and practice.