Privacy protected text analysis in DataSHIELD
ABSTRACT Objectives DataSHIELD (www.datashield.ac.uk) was born of the requirement in the biomedical and social sciences to co-analyse individual patient data (microdata) from different sources, without disclosing identity or sensitive information. Under DataSHIELD, raw data never leaves the data...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Swansea University
2017-04-01
|
Series: | International Journal of Population Data Science |
Online Access: | https://ijpds.org/article/view/289 |
_version_ | 1797430470874497024 |
---|---|
author | Rebecca Wilson Oliver Butters Demetris Avraam Andrew Turner Paul Burton |
author_facet | Rebecca Wilson Oliver Butters Demetris Avraam Andrew Turner Paul Burton |
author_sort | Rebecca Wilson |
collection | DOAJ |
description | ABSTRACT
Objectives
DataSHIELD (www.datashield.ac.uk) was born of the requirement in the biomedical and social sciences to co-analyse individual patient data (microdata) from different sources, without disclosing identity or sensitive information. Under DataSHIELD, raw data never leaves the data provider and no microdata or disclosive information can be seen by the researcher. The analysis is taken to the data - not the data to the analysis.
Text data can be very disclosive in the biomedical domain (patient records, GP letters etc). Similar, but different, issues are present in other domains - text could be copyrighted, or have a large IP value, making sharing impractical.
Approach
By treating text in an analogous way to individual patient data we assessed if DataSHIELD could be adapted and implemented for text analysis, and circumvent the key obstacles that currently prevent it.
Results
Using open digitised text data held by the British Library, a DataSHIELD proof-of-concept infrastructure and prototype DataSHIELD functions for free text analysis were developed.
Conclusions
Whilst it is possible to analyse free text within a DataSHIELD infrastructure, the challenge is creating generalised and resilient anti-disclosure methods for free text analysis. There are a range of biomedical and health sciences applications for DataSHIELD methods of privacy protected analysis of free text including analysis of electronic health records and analysis of qualitative data e.g. from social media. |
first_indexed | 2024-03-09T09:28:04Z |
format | Article |
id | doaj.art-7670295ffe8d4c058d7d066e42b3dd05 |
institution | Directory Open Access Journal |
issn | 2399-4908 |
language | English |
last_indexed | 2024-03-09T09:28:04Z |
publishDate | 2017-04-01 |
publisher | Swansea University |
record_format | Article |
series | International Journal of Population Data Science |
spelling | doaj.art-7670295ffe8d4c058d7d066e42b3dd052023-12-02T05:24:48ZengSwansea UniversityInternational Journal of Population Data Science2399-49082017-04-011110.23889/ijpds.v1i1.289289Privacy protected text analysis in DataSHIELDRebecca Wilson0Oliver Butters1Demetris Avraam2Andrew Turner3Paul Burton4University of BristolUniversity of BristolUniversity of BristolUniversity of BristolUniversity of BristolABSTRACT Objectives DataSHIELD (www.datashield.ac.uk) was born of the requirement in the biomedical and social sciences to co-analyse individual patient data (microdata) from different sources, without disclosing identity or sensitive information. Under DataSHIELD, raw data never leaves the data provider and no microdata or disclosive information can be seen by the researcher. The analysis is taken to the data - not the data to the analysis. Text data can be very disclosive in the biomedical domain (patient records, GP letters etc). Similar, but different, issues are present in other domains - text could be copyrighted, or have a large IP value, making sharing impractical. Approach By treating text in an analogous way to individual patient data we assessed if DataSHIELD could be adapted and implemented for text analysis, and circumvent the key obstacles that currently prevent it. Results Using open digitised text data held by the British Library, a DataSHIELD proof-of-concept infrastructure and prototype DataSHIELD functions for free text analysis were developed. Conclusions Whilst it is possible to analyse free text within a DataSHIELD infrastructure, the challenge is creating generalised and resilient anti-disclosure methods for free text analysis. There are a range of biomedical and health sciences applications for DataSHIELD methods of privacy protected analysis of free text including analysis of electronic health records and analysis of qualitative data e.g. from social media.https://ijpds.org/article/view/289 |
spellingShingle | Rebecca Wilson Oliver Butters Demetris Avraam Andrew Turner Paul Burton Privacy protected text analysis in DataSHIELD International Journal of Population Data Science |
title | Privacy protected text analysis in DataSHIELD |
title_full | Privacy protected text analysis in DataSHIELD |
title_fullStr | Privacy protected text analysis in DataSHIELD |
title_full_unstemmed | Privacy protected text analysis in DataSHIELD |
title_short | Privacy protected text analysis in DataSHIELD |
title_sort | privacy protected text analysis in datashield |
url | https://ijpds.org/article/view/289 |
work_keys_str_mv | AT rebeccawilson privacyprotectedtextanalysisindatashield AT oliverbutters privacyprotectedtextanalysisindatashield AT demetrisavraam privacyprotectedtextanalysisindatashield AT andrewturner privacyprotectedtextanalysisindatashield AT paulburton privacyprotectedtextanalysisindatashield |