De-identification is the first step to use these records for data processing or further medical investigations in electronic medical records. Consequently, a reliable automated de-identification system would be of high value. In this paper, a method of combining text skeleton and recurrent neural network is proposed to solve the problem of de-identification. Text skeleton is the general structure of a medical record, which can help neural networks to learn better. We evaluated our method on three datasets involving two English datasets from i2b2 de-identification challenge and a Chinese dataset we annotated. Empirical results show that the text skeleton based method we proposed can help the network to recognize protected health information. The comparison between our method and state-of-the-art frameworks indicates that our method achieves high performance on the problem of medical record de-identification.

Background: Data-driven medical health information processing has become a new development trend in obstetrics. Electronic medical records (EMRs) are the basis of evidence-based medicine and an important information source for intelligent diagnosis. To obtain diagnostic results, doctors combine clinical experience and medical knowledge in their diagnosis process. External medical knowledge provides strong support for diagnosis. Therefore, it is worth studying how to make full use of EMRs and medical knowledge in intelligent diagnosis. Objective: This study aims to improve the performance of intelligent diagnosis in EMRs by combining medical knowledge. Methods: As an EMR usually contains multiple types of diagnostic results, the intelligent diagnosis can be treated as a multilabel classification task. We propose a novel neural network knowledge-aware hierarchical diagnosis model (KHDM) in which Chinese obstetric EMRs and external medical knowledge can be synchronously and effectively used for intelligent diagnostics. In KHDM, EMRs and external knowledge documents are integrated by the attention mechanism contained in the hierarchical deep learning framework. In this way, we enrich the language model with curated knowledge documents, combining the advantages of both to make a knowledge-aware diagnosis. Results: We evaluate our model on a real-world Chinese obstetric EMR dataset and showed that KHDM achieves an accuracy of 0.8929, which exceeds that of the most advanced classification benchmark methods. We also verified the model’s interpretability advantage. Conclusions: In this paper, an improved model combining medical knowledge and an attention mechanism is proposed, based on the problem of diversity of diagnostic results in Chinese EMRs. KHDM can effectively integrate domain knowledge to greatly improve the accuracy of diagnosis.