Dr. Bukhari is a globally recognized expert in biomedical informatics and trustworthy artificial intelligence. His research focuses on developing AI-driven methods to integrate complex healthcare data, enable predictive modeling of clinical outcomes, and advance reproducibility and transparency in biomedical research. He bridges cutting-edge AI methodologies, including neuro-symbolic and explainable frameworks, with real-world healthcare applications, addressing critical challenges in data standardization, clinical decision support, and health information interoperability. He leads federally funded research on intelligent systems that enhance biomedical knowledge creation, clinical workflow efficiency, and healthcare decision-making. His lab develops transparent predictive models, extracts actionable insights from biomedical datasets, and fosters effective human-AI collaboration in healthcare settings. These efforts are shaping the future of health informatics and predictive analytics with a strong emphasis on practical impact and clinical relevance.
A sought-after keynote speaker and invited panelist, Dr. Bukhari regularly engages international audiences to share his vision for AI in healthcare. He serves on editorial boards of leading journals, edits special issues, and participates in global grant review panels, influencing research directions in AI, biomedical informatics, and health data science. His work has been recognized in international media for advancing trustworthy AI in healthcare and improving patient safety, clinical outcomes, and research reproducibility. He is a tenured Associate Professor and Director of Research at St. John’s University in New York, where he also leads the Healthcare Informatics program. Previously, he worked as a scientist at Yale School of Medicine, was a core team member at Stanford University’s CEDAR Metadata Center, and completed an NIH fellowship. He earned his Ph.D. in Artificial Intelligence from the University of New Brunswick, Canada.
Terminology and Standards: SNOMED CT, RxNorm, LOINC, ICD, CPT, CDISC, HL7 (FHIR), NCDPD, IHTSDO, CDISC, and more
Knowledge engineering: Ontologies, Linked Data, Visualization
Artificial Intelligence: Expertise in Machine learning and Deep learning platforms
Data integration: EHR, Lab and Research data, Clinical notes
Natural language processing, Natural language generation, Hardware with integrated AI
Programming Languages: Python, PHP, Java, Javascript, HTML5, Linux/Unix/Shell environments
Databases: NoSQL and SQL e.g., Cassandra, Relational (MySQL, PostgreSQL, SQLite), Graph (Neo4J)