Optimal vocabulary selection approaches for privacy-preserving deep NLP model training for information extraction and cancer epidemiology

Hong Jun Yoon, Christopher Stanley, J. Blair Christian, Hilda B. Klasky, Andrew E. Blanchard, Eric B. Durbin, Xiao Cheng Wu, Antoinette Stroup, Jennifer Doherty, Stephen M. Schwartz, Charles Wiggins, Mark Damesyn, Linda Coyle, Georgia D. Tourassi

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

Background: With the use of artificial intelligence and machine learning techniques for biomedical informatics, security and privacy concerns over the data and subject identities have also become an important issue and essential research topic. Without intentional safeguards, machine learning models may find patterns and features to improve task performance that are associated with private personal information. Objective: The privacy vulnerability of deep learning models for information extraction from medical textural contents needs to be quantified since the models are exposed to private health information and personally identifiable information. The Objective of the study is to quantify the privacy vulnerability of the deep learning models for natural language processing and explore a proper way of securing patients' information to mitigate confidentiality breaches. METHODS: The target model is the multitask convolutional neural network for information extraction from cancer pathology reports, where the data for training the model are from multiple state population-based cancer registries. This study proposes the following schemes to collect vocabularies from the cancer pathology reports; (a) words appearing in multiple registries, and (b) words that have higher mutual information. We performed membership inference attacks on the models in high-performance computing environments. Results: The comparison outcomes suggest that the proposed vocabulary selection methods resulted in lower privacy vulnerability while maintaining the same level of clinical task performance.

Original languageEnglish
Pages (from-to)185-198
Number of pages14
JournalCancer Biomarkers
Volume33
Issue number2
DOIs
StatePublished - 2022

Bibliographical note

Publisher Copyright:
© 2022 - IOS Press. All rights reserved.

Keywords

  • Privacy
  • artificial intelligence
  • cancer epidemiology
  • deep learning
  • natural language processing
  • privacy-preserving training

ASJC Scopus subject areas

  • Oncology
  • Genetics
  • Cancer Research

Fingerprint

Dive into the research topics of 'Optimal vocabulary selection approaches for privacy-preserving deep NLP model training for information extraction and cancer epidemiology'. Together they form a unique fingerprint.

Cite this