Cohort-Level Protection and Individualized Inference in AI-Based Monitoring

Files

Cohortlevelprotectionandindividualizedinferenceposter.pdf (832.56 KB)

Links to Files

https://indico.bnl.gov/event/28538/contributions/112804/attachments/64680/111127/Cohort-level%20protection%20and%20individualized%20inference%20poster.pdf

Permanent Link

http://hdl.handle.net/11603/40511

Collections

UMBC Faculty Collection
UMBC Mathematics and Statistics Department

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0002-7986-0470

Date

Type of Work

posters
Text

Department

Program

Citation of Original Publication

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

Abstract

Artificial intelligence (AI) tools are increasingly used to monitor large groups of similar units (e.g., patients, credit cards), but critical decisions must often be made at the individual level.We propose a framework that:• Borrows strength across a cohort for better accuracy,• Enables automated, individualized inference, and• Supports early detection of system breaches (e.g., tumor growth, fraud).Applications include:• Cancer screening via image analysis• Credit card fraud detection• Cybersecurity and ecological monitoring Our work offers a scalable, mathematically grounded approach that blends cohort-level learning with personalized monitoring, forming a key step toward digital twins and precision healthcare.