Combining knowledge- and data-driven methods for de-identification of clinical narratives

Abstract

A recent promise to access unstructured clinical data from electronic health records on large-scale has revitalized the interest in automated de-identification of clinical notes, which includes the identification of mentions of Protected Health Information (PHI). We describe the methods developed and evaluated as part of the i2b2/UTHealth 2014 challenge to identify PHI defined by 25 entity types in longitudinal clinical narratives. Our approach combines knowledge-driven (dictionaries and rules) and data-driven (machine learning) methods with a large range of features to address de-identification of specific named entities. In addition, we have devised a two-pass recognition approach that creates a patient-specific run-time dictionary from the PHI entities identified in the first step with high confidence, which is then used in the second pass to identify mentions that lack specific clues. The proposed method achieved the overall micro F1-measures of 91% on strict and 95% on token-level evaluation on the test dataset (514 narratives). Whilst most PHI entites can be reliably identified, particularly challenging were mentions of Organisations and Professions. Still, the overall results suggest that automated text mining methods can be used to reliably process clinical notes to identify personal information and thus providing a crucial step in large-scale de-identification of unstructured data for further clinical and epidemiological studies.

The UAB Informatics Institute and 2016 CEGS N-GRID de-identification shared task challenge

“…Prior de-id studies used multi-pass architectures at the macro level. For instance, Dehghan et al used a two-pass approach, where the second pass was a post-processing phase to filter low-quality annotations from the first pass(16). Our system applied a multi-pass framework at a micro level: by methodology and PHI type.…”

Learning to identify Protected Health Information by integrating knowledge- and data-driven algorithms: A case study on psychiatric evaluation notes

“…The approaches we designed are built using two previously published methods [22], which include a knowledge-driven open source algorithm (mDEID) and a data-driven method (CliDEID) built using linear chain CRF. We used default (CRF++) parameters: L2-regularization with C=1.00, ETA=0.001.…”

“…Submission 2 is built on top of mDEID, which was initially modeled on the i2b2/UTHealth 2014 Track I [22, 23]. The rules already available in mDEID were updated based on the new training data.…”

“…In this paper we describe two methods developed and evaluated as part of that task, as well as the outcome of their integration. Our methods rely on previous work [22]. mDEID is a knowledge-driven approach that relies on dictionaries to identify relatively closed PHI types (e.g.…”

DataSHIELD – New Directions and Dimensions

“…This extra metadata would help reduce any ambiguity the DataSHIELD end users may encounter with short 15 The BioPortal -https://bioportal.bioontology.org/. (Dehghan, 2015;Meystre et al 2010;Zhou et al 2015). The successful import of structured text and clinical ontology data into DataSHIELD as presented here, combined with the modular nature of the infrastructure, would make it possible to integrate and utilise existing open source text mining tools to give DataSHIELD users increasing functionality.…”