De-identification In practice

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.