Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
July 26, 2026J — Multidisciplinary Scientific JournalOpen Access

Clinical Text De-Identification Beyond PHI Detection: A Scoping Review

View Full Paper
Ask AI
Bookmark
Share

Authors

MSMurat Sariyar

Discussion

Loading...

Member takes

Overview

Scoping review identifies methods for clinical text de-identification, highlighting challenges beyond PHI detection.

Key Points

  • The aim is to explore clinical text de-identification, focusing on methods beyond just detecting protected health information (PHI).
  • Conducted a scoping review following PRISMA-ScR guidelines.
  • Combined searches from PubMed/MEDLINE, OpenAlex, Web of Science, and Scopus.
  • Screened records to identify core publications related to de-identification from 2018 to 2026.
  • Identified 275 records, resulting in 258 unique records after deduplication.
  • Assessments produced 110 core records and identified structural frameworks for method classification.
  • Found that named-entity recognition is insufficient on its own for effective de-identification.

Cite This Study

Murat Sariyar (2026) studied this question.

synapsesocial.com/papers/6a65a825d3aea3239cd78a75https://doi.org/10.3390/j9030022
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Development and Validation of a Natural Language Processing Algorithm to Pseudonymize Documents in the Context of a Clinical Data Warehouse2024 · 21 citations
  2. 2Leveraging text skeleton for de-identification of electronic medical records2018 · 35 citations
  3. 3Optimal database combinations for literature searches in systematic reviews: a prospective exploratory study2017 · 2,126 citations
  4. 4OpenDeID Pipeline for Unstructured Electronic Health Record Text Notes Based on Rules and Transformers: Deidentification Algorithm Development and Validation Study2023 · 35 citations
  5. 5Deidentification of free-text medical records using pre-trained bidirectional transformers2020 · 55 citations