Bootstrapping a de-identification system for narrative patient records: Cost-performance tradeoffs

Hanauer, David A.; Aberdeen, John S.; Bayer, Samuel; Wellner, Benjamin; Clark, Cheryl; Zheng, Kai; Hirschman, Lynette

doi:10.1016/j.ijmedinf.2013.03.005

Cited by 27 publications

(24 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neamatullah et al (2008) reported a recall ranging from 0.63 to 0.94 between 14 clinicians for manually identifying PHI in 130 clinical notes. Since human annotations for clinical data are costly (Douglass et al, 2004), researchers have investigated automated and semi-automated methods for de-identification (Gobbel et al, 2014;Hanauer et al, 2013). Automated methods range from rule-based systems (Morrison et al, 2009) to statistical methods such as support vector machines and conditional random fields (Stubbs et al, 2015), with more recent use of recurrent neural networks (Liu et al, 2017;Dernoncourt et al, 2017).…”

Section: De-identificationmentioning

confidence: 99%

Towards Automatic Generation of Shareable Synthetic Clinical Notes Using Neural Language Models

Melamud¹,

Shivade²

2019

Proceedings of the 2nd Clinical Natural Language Processing Workshop

View full text Add to dashboard Cite

Large-scale clinical data is invaluable to driving many computational scientific advances today. However, understandable concerns regarding patient privacy hinder the open dissemination of such data and give rise to suboptimal siloed research. De-identification methods attempt to address these concerns but were shown to be susceptible to adversarial attacks. In this work, we focus on the vast amounts of unstructured natural language data stored in clinical notes and propose to automatically generate synthetic clinical notes that are more amenable to sharing using generative models trained on real de-identified records. To evaluate the merit of such notes, we measure both their privacy preservation properties as well as utility in training clinical NLP models. Experiments using neural language models yield notes whose utility is close to that of the real ones in some clinical NLP tasks, yet leave ample room for future improvements.

show abstract

Section: De-identificationmentioning

confidence: 99%

Towards Automatic Generation of Shareable Synthetic Clinical Notes Using Neural Language Models

Melamud¹,

Shivade²

2019

Proceedings of the 2nd Clinical Natural Language Processing Workshop

View full text Add to dashboard Cite

show abstract

“…Hanauer et al [10] constructed statistical de-identification models by iteratively performing (i) annotation of a small EHRs sample; (ii) training of a CRF model;…”

Section: De-identificationmentioning

confidence: 99%

De-identification of health records using Anonym: Effectiveness and robustness across datasets

Zuccon¹,

Kotzur²,

Nguyen³

et al. 2014

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Results: Anonym identifies and removes up to 96.6% of personal health identifiers (recall) with a precision of up to 98.2% on the i2b2 dataset, outperforming the best system proposed in the i2b2 challenge. The effectiveness of Anonym across datasets is found to depend on the amount of information available for training.Conclusion: Findings show that Anonym compares to the best approach from the 2006 i2b2 shared task. It is easy to retrain Anonym with new datasets; if retrained, the system is robust to variations of training size, data type and quality in presence of sufficient training data.

show abstract

“…More recently, incremental approaches have been advocated for certain tasks (e.g. de-identification) [ 7 ]. These methods may be most appropriate where specific classes of mentions are being annotated [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

NOBLE – Flexible concept recognition for large-scale biomedical natural language processing

et al. 2016

View full text Add to dashboard Cite

BackgroundNatural language processing (NLP) applications are increasingly important in biomedical data analysis, knowledge engineering, and decision support. Concept recognition is an important component task for NLP pipelines, and can be either general-purpose or domain-specific. We describe a novel, flexible, and general-purpose concept recognition component for NLP pipelines, and compare its speed and accuracy against five commonly used alternatives on both a biological and clinical corpus.NOBLE Coder implements a general algorithm for matching terms to concepts from an arbitrary vocabulary set. The system’s matching options can be configured individually or in combination to yield specific system behavior for a variety of NLP tasks. The software is open source, freely available, and easily integrated into UIMA or GATE. We benchmarked speed and accuracy of the system against the CRAFT and ShARe corpora as reference standards and compared it to MMTx, MGrep, Concept Mapper, cTAKES Dictionary Lookup Annotator, and cTAKES Fast Dictionary Lookup Annotator.ResultsWe describe key advantages of the NOBLE Coder system and associated tools, including its greedy algorithm, configurable matching strategies, and multiple terminology input formats. These features provide unique functionality when compared with existing alternatives, including state-of-the-art systems. On two benchmarking tasks, NOBLE’s performance exceeded commonly used alternatives, performing almost as well as the most advanced systems. Error analysis revealed differences in error profiles among systems.ConclusionNOBLE Coder is comparable to other widely used concept recognition systems in terms of accuracy and speed. Advantages of NOBLE Coder include its interactive terminology builder tool, ease of configuration, and adaptability to various domains and tasks. NOBLE provides a term-to-concept matching system suitable for general concept recognition in biomedical NLP pipelines.

show abstract

Bootstrapping a de-identification system for narrative patient records: Cost-performance tradeoffs

Cited by 27 publications

References 20 publications

Towards Automatic Generation of Shareable Synthetic Clinical Notes Using Neural Language Models

Towards Automatic Generation of Shareable Synthetic Clinical Notes Using Neural Language Models

De-identification of health records using Anonym: Effectiveness and robustness across datasets

NOBLE – Flexible concept recognition for large-scale biomedical natural language processing

Contact Info

Product

Resources

About