Google Scholar
Visit for peer-reviewed publications, indexing, citation updates, and the most complete research profile.
View ProfileResearch
My research focuses on developing trustworthy, privacy-preserving, and generalizable AI systems for healthcare and other high-impact data environments.
Research profiles
Google Scholar is the authoritative profile for publication records and citation indexing. The other profiles help collaborators review identity, code, professional background, and research networking context.
Visit for peer-reviewed publications, indexing, citation updates, and the most complete research profile.
View ProfileUse ORCID to verify persistent researcher identity and connect scholarly work across platforms.
View ProfileVisit for research networking, academic visibility, and publication-discovery context.
View ProfileReview technical projects, code-oriented prototypes, analytics workflows, and implementation habits.
View ProfileReview professional background, experience, network context, and recruiter-facing career updates.
View ProfileResearch statement
My research focuses on developing trustworthy, privacy-preserving, and generalizable AI systems for healthcare. I am interested in combining deep learning, federated learning, multimodal clinical data, agentic and LLM-based systems, and reliable data infrastructure to create models that are accurate, explainable, safe, and practical. My work examines how AI can support clinical decision-making and data collaboration while preserving privacy, reducing bias, and maintaining data integrity.
Long-term research vision: My long-term goal is to develop trustworthy artificial intelligence systems that improve healthcare decision-making through privacy-preserving machine learning, multimodal clinical analytics, and scalable data infrastructure.
Research themes
Privacy-preserving, multi-source data management using AI-based access control, federated learning, homomorphic encryption, differential privacy, and predictive analytics. Co-developed / co-authored.
A proactive AI framework for anticipating anomalies in cloud databases using techniques such as LSTM and autoencoder-based detection. Co-developed / co-authored.
Research on the integration of ctDNA, microbiome, imaging, and related signals for cancer monitoring.
Research interest in retrieval-augmented and tool-using systems for clinical documentation, EHR interaction, and multimodal reasoning.
Academic service
Web of Science reviewer recognition shows 6 peer review records across 6 manuscripts for 2025-2026, based on the reviewer-recognition summary supplied August 4, 2026.
Reviewer recognition
Reviewed manuscripts across Data Science Journal, International Journal on Data Science and Technology, Journal of Disease and Global Health, and Academia Environmental Sciences and Sustainability.
Selected records
Presentation
Resilient Dataflow Intelligence: A Proactive AI Framework for Cloud Anomaly Detection - Bay Atlantic University, Washington, D.C. - 2024.
Service
Conference volunteer: IEEE CIC / TPS / CogMI 2024-2025; IEEE PES Energy & Policy Forum 2025; Coleridge Initiative 5th National Convening 2025; DevFest DC 2025.
Awards
Bay Atlantic University
Bay Atlantic University
IEEE CIC / CogMI / TPS