PHI Scrubber: A Deep Learning Approach

TL;DR

The paper introduces PHI Scrubber, a deep learning system combining neural networks and regex to identify and remove personally identifiable information from medical notes, enhancing patient privacy.

Contribution

It presents a novel deep learning-based approach integrating neural networks and regex for effective PHI removal from clinical texts.

Findings

High accuracy in identifying PHI in medical notes

Effective removal of sensitive information while preserving data utility

Improved privacy protection in electronic health records

Abstract

Confidentiality of patient information is an essential part of Electronic Health Record System. Patient information, if exposed, can cause a serious damage to the privacy of individuals receiving healthcare. Hence it is important to remove such details from physician notes. A system is proposed which consists of a deep learning model where a de-convolutional neural network and bi-directional LSTM-CNN is used along with regular expressions to recognize and eliminate the individually identifiable information. This information is then removed from a medical practitioner's data which further allows the fair usage of such information among researchers and in clinical trials.