activity
20202026
most citedHigh performance on-demand de-identification of a petabyte-scale medical imaging data lake

8 citations · 12 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification

Jose D. Posada, David Love, Somalee Datta +1

De-identification of clinical text is a prerequisite for the secondary use of electronic health records. Existing public benchmarks such as the i2b2 2006 and 2014 corpora are over…