De-identification In practice
This work addresses de-identification for healthcare data privacy, but it is incremental as it applies existing methods like Word2Vec and LSTM to a specific domain.
The authors tackled the problem of identifying sensitive HIPAA-listed information in medical text using NLP and ML techniques, achieving promising results without manual feature extraction on a small dataset.
We report our effort to identify the sensitive information, subset of data items listed by HIPAA (Health Insurance Portability and Accountability), from medical text using the recent advances in natural language processing and machine learning techniques. We represent the words with high dimensional continuous vectors learned by a variant of Word2Vec called Continous Bag Of Words (CBOW). We feed the word vectors into a simple neural network with a Long Short-Term Memory (LSTM) architecture. Without any attempts to extract manually crafted features and considering that our medical dataset is too small to be fed into neural network, we obtained promising results. The results thrilled us to think about the larger scale of the project with precise parameter tuning and other possible improvements.