Dataset Information

Hiding in plain sight: use of realistic surrogates to reduce exposure of protected health information in clinical text.

ABSTRACT:

Objective

Secondary use of clinical text is impeded by a lack of highly effective, low-cost de-identification methods. Both, manual and automated methods for removing protected health information, are known to leave behind residual identifiers. The authors propose a novel approach for addressing the residual identifier problem based on the theory of Hiding In Plain Sight (HIPS).

Materials and methods

HIPS relies on obfuscation to conceal residual identifiers. According to this theory, replacing the detected identifiers with realistic but synthetic surrogates should collectively render the few 'leaked' identifiers difficult to distinguish from the synthetic surrogates. The authors conducted a pilot study to test this theory on clinical narrative, de-identified by an automated system. Test corpora included 31 oncology and 50 family practice progress notes read by two trained chart abstractors and an informaticist.

Results

Experimental results suggest approximately 90% of residual identifiers can be effectively concealed by the HIPS approach in text containing average and high densities of personal identifying information.

Discussion

This pilot test suggests HIPS is feasible, but requires further evaluation. The results need to be replicated on larger corpora of diverse origin under a range of detection scenarios. Error analyses also suggest areas where surrogate generation techniques can be refined to improve efficacy.

Conclusions

If these results generalize to existing high-performing de-identification systems with recall rates of 94-98%, HIPS could increase the effective de-identification rates of these systems to levels above 99% without further advancements in system recall. Additional and more rigorous assessment of the HIPS approach is warranted.

SUBMITTER: Carrell D

PROVIDER: S-EPMC3638183 | biostudies-literature | 2013 Mar-Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Hiding in plain sight: use of realistic surrogates to reduce exposure of protected health information in clinical text.

Carrell David D Malin Bradley B Aberdeen John J Bayer Samuel S Clark Cheryl C Wellner Ben B Hirschman Lynette L

Journal of the American Medical Informatics Association : JAMIA 20120706 2

<h4>Objective</h4>Secondary use of clinical text is impeded by a lack of highly effective, low-cost de-identification methods. Both, manual and automated methods for removing protected health information, are known to leave behind residual identifiers. The authors propose a novel approach for addressing the residual identifier problem based on the theory of Hiding In Plain Sight (HIPS).<h4>Materials and methods</h4>HIPS relies on obfuscation to conceal residual identifiers. According to this the ...[more]

PMID: 22771529

Similar Datasets

Project description:Cultivation in the laboratory is essential for understanding the phenotypic characteristics and environmental preferences of bacteria. However, basic phenotypic information is not readily accessible. Here, we compiled phenotypic and environmental tolerance information for >5,000 bacterial strains described in the International Journal of Systematic and Evolutionary Microbiology (IJSEM) with all information made publicly available in an updatable database. Although the data span 23 different bacterial phyla, most entries described aerobic, mesophilic, neutrophilic strains from Proteobacteria (mainly Alpha- and Gammaproteobacteria), Actinobacteria, Firmicutes, and Bacteroidetes isolated from soils, marine habitats, and plants. Most of the routinely measured traits tended to show a significant phylogenetic signal, although this signal was weak for environmental preferences. We demonstrated how this database could be used to link genomic attributes to differences in pH and salinity optima. We found that adaptations to high salinity or high-pH conditions are related to cell surface transporter genes, along with previously uncharacterized genes that might play a role in regulating environmental tolerances. Together, this work highlights the utility of this database for associating bacterial taxonomy, phylogeny, or specific genes to measured phenotypic traits and emphasizes the need for more comprehensive and consistent measurements of traits across a broader diversity of bacteria. IMPORTANCE Cultivation in the laboratory is key for understanding the phenotypic characteristics, growth requirements, metabolism, and environmental preferences of bacteria. However, oftentimes, phenotypic information is not easily accessible. Here, we compiled phenotypic and environmental tolerance information for >5,000 bacterial strains described in the International Journal of Systematic and Evolutionary Microbiology (IJSEM). We demonstrate how this database can be used to link bacterial taxonomy, phylogeny, or specific genes to measured phenotypic traits and environmental preferences. The phenotypic database can be freely accessed (https://doi.org/10.6084/m9.figshare.4272392), and we have included instructions for researchers interested in adding new entries or curating existing ones.

Dataset Information

Hiding in plain sight: use of realistic surrogates to reduce exposure of protected health information in clinical text.

Objective

Materials and methods

Results

Discussion

Conclusions

Publications

Hiding in plain sight: use of realistic surrogates to reduce exposure of protected health information in clinical text.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets