Desensitizing EHR/Biomedical Data and Synthetic Digital-Twins (DSLO)

UMSN, SOCR and GrayRain released a new app: DSLO - Data Simulator and Statistical Obfuscator. The privacy-enhancing technology of the DataSifter Longitudinal Obfuscator (DSLO) balances data-value (utility) and privacy protection (sensitivity). It is designed specifically for desensitization of real EHR/human data and synthetic generation of digital-twin data including time-series, cross-sectional, phenotypic, categorical, and other types.


 

Comments

Post a Comment

Popular posts from this blog

AI-supported Clinical Imaging Decision Support System

Image
In November 2025, a team of students, researchers, and faculty at  UMSN  and SOCR  developed, tested, and deployed a new sophisticated Clinical Imaging Decision Support System composed of two parts: A generation-3 Augmented Intelligent Agent (AIA-gen-3) , which supports RAG AI-responses via custom-training and tuning pre-trained GAIMs and LLMs , and A generation-4 CLNQ , which facilitates highly accurate AI autonomous responses contextualized according to specific transfer-learning knowledge-bases.  Driven by prompts from patients, clinicians, trainees, and other stakeholders, both AI systems are tested in describing, diagnosing, predicting treatment outcomes of simple ophthalmological images. These AI Clinical Decision Support Systems ( AIA-gen-3  and  CLNQ-gen-4 ) can be invoked in any modern browser. The AIA-3 sessions are virtual, confined to the browser tab, and no information is exposed to external AI API services. The CLNQ-4 also optionally ...
Read more

SPA: The First GAIM-supported Augmented Intelligence Scientific Writing & Reviewing Assistant, SOCR Proposal & Manuscript Assistant (PMA)

Image
At the start of 2026, SOCR and the AI in Health Initiative released the first GAIM-supported augmented intelligence agent supporting creative writing, manuscript preparation/review, and grant proposal writing and reviewing , the SOCR Proposal & Manuscript Assistant (PMA) . The Manuscript/Proposal Assistant is a comprehensive AI-aided web application designed to transform the traditionally arduous and unstructured processes of paper, grant, and report writing or reviewing into a streamlined, intelligent, and systematic workflow. PMA serves as a strategic partner for researchers and institutions, guiding academic scholars and clinicians from the initial analysis of a funding call through to the final polished proposal/manuscript submissions. By integrating advanced language models in a structured pipeline, the tool moves beyond simple text generation to provide deep strategic analysis, creative solutions, and rigorous compliance checking, effectively acting as both a project man...
Read more

Interactive Learning Platform (ILP)

Image
The UMSN AI in Health Initiative released a new Interactive Learning Platform (ILP) , which revolutionizes health, nursing, and inter-professional education through AI and Cloud technologies bringing active learners and innovative educators together in an engaging and effective environment.   The ILP democratizes access to high-quality, interactive education by providing educators with powerful tools to create engaging learning experiences and students with platforms that make learning collaborative, fun, and effective. It connects learners and educators across the world, breaking down geographical barriers to quality education. The main ILP features include: Student-Centered : Every feature is designed with learners in mind, prioritizing engagement, accessibility, and educational outcomes. Privacy First : We maintain the highest standards of data protection and privacy, ensuring a safe learning environment for all. What Makes Us Different : Our platform combines cutting-edge tec...
Read more