Development and evaluation of a de-identification procedure for a case register sourced from mental health electronic records

Abstract

BackgroundElectronic health records (EHRs) provide enormous potential for health research but also present data governance challenges. Ensuring de-identification is a pre-requisite for use of EHR data without prior consent. The South London and Maudsley NHS Trust (SLaM), one of the largest secondary mental healthcare providers in Europe, has developed, from its EHRs, a de-identified psychiatric case register, the Clinical Record Interactive Search (CRIS), for secondary research.MethodsWe describe development, implementation and evaluation of a bespoke de-identification algorithm used to create the register. It is designed to create dictionaries using patient identifiers (PIs) entered into dedicated source fields and then identify, match and mask them (with ZZZZZ) when they appear in medical texts. We deemed this approach would be effective, given high coverage of PI in the dedicated fields and the effectiveness of the masking combined with elements of a security model. We conducted two separate performance tests i) to test performance of the algorithm in masking individual true PIs entered in dedicated fields and then found in text (using 500 patient notes) and ii) to compare the performance of the CRIS pattern matching algorithm with a machine learning algorithm, called the MITRE Identification Scrubber Toolkit – MIST (using 70 patient notes – 50 notes to train, 20 notes to test on). We also report any incidences of potential breaches, defined by occurrences of 3 or more true or apparent PIs in the same patient’s notes (and in an additional set of longitudinal notes for 50 patients); and we consider the possibility of inferring information despite de-identification.ResultsTrue PIs were masked with 98.8% precision and 97.6% recall. As anticipated, potential PIs did appear, owing to misspellings entered within the EHRs. We found one potential breach. In a separate performance test, with a different set of notes, CRIS yielded 100% precision and 88.5% recall, while MIST yielded a 95.1% and 78.1%, respectively. We discuss how we overcome the realistic possibility – albeit of low probability – of potential breaches through implementation of the security model.ConclusionCRIS is a de-identified psychiatric database sourced from EHRs, which protects patient anonymity and maximises data available for research. CRIS demonstrates the advantage of combining an effective de-identification algorithm with a carefully designed security model. The paper advances much needed discussion of EHR de-identification – particularly in relation to criteria to assess de-identification, and considering the contexts of de-identified research databases when assessing the risk of breaches of confidential patient information.

Seclusion and Psychiatric Intensive Care Evaluation Study (SPICES): combined qualitative and quantitative approaches to the uses and outcomes of coercive practices in mental health services

“…18 In the first, patient-identifiable information is stripped from the structured data in CRIS; dates of birth are truncated to month and year of birth, ethnicity is grouped into broad categories, addresses are converted to the corresponding Office for National Statistics output area, and the names of the service user and contacts are removed. A pseudonymous identifier is created, replacing local and national identifying numbers.…”

What proportion of patients with psychosis is willing to take part in research? A mental health electronic case register analysis

“…26 The SLaM C4C model was reviewed and approved by the National Information Governance Board for Health and Social Care (NIGB) Ethics and Confidentiality committee (reference ECC 2-08/2010). 14 A patient-led oversight committee provides governance for all projects conducted using these data, including those that use the C4C programme.…”

Data science for mental health: a UK perspective on a global challenge

“…Key to the development include data structuring and de-identification pipelines and also a wider data security and governance model which has been patient-led from the outset 33 . Research applications have included searches to help identify and characterise rare scenarios for further investigation 34,35 , and data linkage projects to characterise physical health outcomes 36,37 .…”