Assessing the Effectiveness and Scalability of Fast Healthcare Interoperability Resource-Based Granular Data Segmentation Technology
January 1, 2026·
·
0 min read
Soroush Dianaty
Abstract
Evaluates SHARES, a FHIR-based granular data segmentation platform for protecting sensitive substance-use health information. Tested against 11,519 synthetic patient records, the system achieved a throughput of 10.36 bundles per second at a cost of under one cent per segmentation.
Type
Publication
Applied Clinical Informatics
Authors
PhD Student, Biomedical Informatics & Data Science
Physician-scientist and PhD student, focused on the evaluation and real-world implementation of clinical AI systems. My research centers on trustworthy clinical LLMs, including hallucination detection, evidence grounding, contextual reliability, and AI safety in healthcare settings. I develop evaluation frameworks and computational methods to determine whether clinical AI systems are scientifically grounded, clinically reliable, and suitable for deployment in real-world practice.