Ontology for Healthcare AI Privacy in Brazil

Tiago Andres Vaz; Jose Miguel Dora; Luis da Cunha Lamb; Suzi Alves Camey

doi:10.22456/2175-2745.140570

Authors

Tiago Andres Vaz Hospital de Clinicas de Porto Alegre https://orcid.org/0000-0003-3125-0662
Jose Miguel Dora Hospital de Clinicas de Porto Alegre
Luis da Cunha Lamb Universidade Federal do Rio Grande do Sul
Suzi Alves Camey Hospital de Clinicas de Porto Alegre https://orcid.org/0000-0002-5564-081X

DOI:

https://doi.org/10.22456/2175-2745.140570

Keywords:

Artificial Intelligence, ontology, Healthcare, Machine Learning

Abstract

This article details the creation of a novel domain ontology at the intersection of epidemiology,

medicine, statistics, and computer science. It outlines a systematic approach to handling structured data

anonymously in preparation for its use in Artificial Intelligence (AI) applications in healthcare. The development

followed 7 steps, including defining scope, selecting knowledge, reviewing important terms, constructing classes

that describe designs used in epidemiological studies, machine learning paradigms, types of data and attributes,

risks that anonymized data may be exposed to, privacy attacks, techniques to mitigate re-identification, privacy

models, and metrics for measuring the effects of anonymization. It concludes with a practical implementation of

this ontology in hospital settings to develop and validate AI systems.

Downloads

Download data is not yet available.

References

ABHYANKAR, Swapna; DEMNER-FUSHMAN, Dina; MCDONALD, Clement J. Standardizing clinical laboratory data for secondary use. Journal of biomedical informatics, [s. l.], v. 45, n. 4, p. 642–650, 2012.

AGGARWAL, Charu C.; YU, Philip S. (org.). Privacy-Preserving Data Mining: Models and Algorithms. Boston, MA: Springer US, 2008. p. 11–52.

BATET, Montserrat; SANCHEZ, David; VALLS, Aida. An ontology-based measure to compute semantic similarity in biomedicine. Journal of biomedical informatics, [s. l.], v. 44, n. 1, p. 118–125, 2011.

BRAZIL. LAI. [S. l.], [s. d.]. Disponível em: http://www.planalto.gov.br/ccivil_03/_ato2011-2014/2011/lei/l12527.htm.

BRAZIL. LGPD: A Lei Geral de Proteção de Dados Pessoais. [S. l.], 2018. Disponível em: http://www.planalto.gov.br/ccivil_03/_ato2015-2018/2018/lei/L13709.htm.

CHEVRIER, Raphael et al. Use and Understanding of Anonymization and De-Identification in the Biomedical Literature: Scoping Review. Journal of medical Internet research, [s. l.], v. 21, n. 5, p. e13484, 2019.

DWORK, Cynthia. Differential Privacy: A Survey of Results. Em: 2008. Theory and Applications of Models of Computation. [S. l.]: Springer Berlin Heidelberg, 2008. p. 1–19.

GENERAL DATA PROTECTION REGULATION (GDPR) – OFFICIAL LEGAL TEXT. [S. l.], 2016. Disponível em: https://gdpr-info.eu/. Acesso em: 20 abr. 2022.

GRUBER, Thomas R. A translation approach to portable ontology specifications. Knowledge Acquisition, [s. l.], v. 5, n. 2, p. 199–220, 1993.

IBM. IBM Dictionary of Computing. 10th. ed. USA: McGraw-Hill, Inc., 1993.

IYENGAR, Vijay S. Transforming data to satisfy privacy constraints. Em: 2002, Edmonton, Alberta, Canada. Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. New York, NY, USA: Association for Computing Machinery, 2002. p. 279–288. Disponível em: https://doi.org/10.1145/775047.775098. Acesso em: 21 abr. 2022.

KHAN, Muhammad; FOLEY, Simon; O’SULLIVAN, Barry. From k-anonymity to Differential Privacy: A Brief Introduction to Formal Privacy Models. [s. l.], 2021. Disponível em: https://hal.archives-ouvertes.fr/hal-03226881/.

KIMBALL, Ralph; CASERTA, Joe. The Data Warehouse ETL Toolkit: Practical Techniques for Extracting, Cleaning, Conforming, and Delivering Data. [S. l.], John Wiley and Sons, 2011.

LEFEVRE, K.; DEWITT, D. J.; RAMAKRISHNAN, R. Mondrian Multidimensional K-Anonymity. Em: 2006. 22nd International Conference on Data Engineering (ICDE’06). [S. l.: s. n.], 2006. p. 25–25.

LEFEVRE, Kristen; DEWITT, David J.; RAMAKRISHNAN, Raghu. Workload-aware anonymization techniques for large-scale datasets. ACM Trans. Database Syst., New York, NY, USA, v. 33, n. 3, p. 1–47, 2008.

LLUIS, Sergio; OTHERS. Ontology based semantic anonymisation of microdata. [s. d.]. - Universitat Rovira i Virgili, [s. l.], [s. d.]. Disponível em: https://www.tdx.cat/handle/10803/108961, 2011.

MACHANAVAJJHALA, Ashwin et al. L-diversity: Privacy beyond k-anonymity. ACM transactions on knowledge discovery from data, New York, NY, USA, v. 1, n. 1, p. 3–es, 2007.

MARK, Roger. The Story of MIMIC. Em: MIT CRITICAL DATA (org.). Secondary Analysis of Electronic Health Records. Cham: Springer International Publishing, 2016. p. 43–49.

NOY, Natalya F.; MCGUINNESS, Deborah L.; OTHERS. Ontology development 101: A guide to creating your first ontology. [S. l.]: Stanford knowledge systems laboratory technical report KSL-01-05 and..., 2001.

NUNES, L. N.; CAMEY, S. A.; GUIMARAES, L. S. P. Os principais delineamentos na Epidemiologia. Vol. 33, no. 2 (2013), p...., [s. l.], 2013. Disponível em: https://www.lume.ufrgs.br/handle/10183/158317.

OLIVEIRA, Erick de; MADEIRA, Humberto dos Santos; MONTEIRO, Pedro Augusto Migliari. A lei geral de proteção de dados pessoais e a anonimização de dados: uma aplicação da técnica em uma base de dados real. [s. l.], 2020.

PANOV, Pance; SOLDATOVA, Larisa N.; DŽEROSKI, Sašo. Generic ontology of datatypes. Information sciences, [s. l.], v. 329, p. 900–920, 2016.

PORTA, Miquel. A Dictionary of Epidemiology. [S. l.]: Oxford, 2014.

PRASSER, Fabian et al. Lightning: Utility-Driven Anonymization of High-Dimensional Data. Transactions on Data Privacy. Foundations and Technologies, [s. l.], v. 9, n. 2, p. 161–185, 2016.

PRASSER, Fabian; BILD, Raffael; KUHN, Klaus A. A Generic Method for Assessing the Quality of De-Identified Health Data. Studies in health technology and informatics, [s. l.], 2016.

QUEIROZ, Maria J.; LINO, Natasha C. Q.; GUSTAVO H M. Uma Ontologia de Domínio para Preservação de Privacidade em Dados Publicados pelo Governo BRAZILeiro. Em: 2016. Anais do XII Simposio Brasileiro de Sistemas de Informação. [S. l.]: SBC, 2016. p. 009–016. Disponível em: http://dx.doi.org/. Acesso em: 2 nov. 2020.

RAJENDRAN, Keerthana; JAYABALAN, Manoj; RANA, Muhammad Ehsan. A Study on k-anonymity, l-diversity, and t-closeness Techniques focusing Medical Data. [s. l.], v. 17, n. 12, 2017. Disponível em: http://dx.doi.org/. Acesso em: 6 dez. 2019.

REPS, Jenna M. et al. Design and implementation of a standardized framework to generate and evaluate patient-level prediction models using observational healthcare data. Journal of the American Medical Informatics Association: JAMIA, [s. l.], v. 25, n. 8, p. 969–975, 2018.

ROCHER, Luc; HENDRICKX, Julien M.; DE MONTJOYE, Yves-Alexandre. Estimating the success of re-identifications in incomplete datasets using generative models. Nature communications, [s. l.], v. 10, n. 1, p. 3069, 2019.

SAMARATI, Pierangela; SWEENEY, Latanya. Protecting privacy when disclosing information: K-anonymity and its enforcement through generalization and suppression. [S. l.], 2003.

SPENGLER, Helmut; PRASSER, Fabian. Protecting Biomedical Data Against Attribute Disclosure. Studies in health technology and informatics, [s. l.], v. 267, p. 207–214, 2019.

SULLIVAN, June M. HIPAA: A Practical Guide to the Privacy and Security of Health Data. [S. l.]: American Bar Association, 2004.

SWEENEY, Latanya. Achieving k-Anonymity Privacy Protection Using Generalization and Suppression. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, [s. l.], v. 10, n. 05, p. 571–588, 2002.

SWEENEY, Latanya. Only you, your doctor, and many others may know. Technology Science, [s. l.], v. 2015092903, n. 9, p. 29, 2015.

WILLENBORG, Leon; DE WAAL, Ton. Elements of Statistical Disclosure Control. [S. l.]: Springer Science and Business Media, 2012.

YADAV, S.K.; SINGH, S.; GUPTA, R. Data Types. In: Biomedical Statistics. Springer, Singapore. https://doi.org/10.1007/978-981-32-9294, 2019.