| Title | Assertion Detection in Clinical Natural Language Processing: A Knowledge-Poor Machine Learning Approach |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Chen, Long |
| Conference Name | 2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT) |
| Keywords | assertion assignment, assertion detection, assertion modifiers, assertion status, attention mechanism, bidirectional long short-term memory networks, clinical assertion, clinical context, clinical entities, clinical information, clinical natural language processing, clinical NLP systems, Deep Learning, disease modeling, diseases, electronic health record, electronic health records, Human Behavior, Knowledge engineering, knowledge poor deep-learning system, knowledge-poor machine learning approach, learning (artificial intelligence), LSTM, machine learning, Measurement, Medical diagnostic imaging, natural language processing, Pain, patient diagnosis, pubcrawl, recurrent neural nets, Resiliency, RNN, Scalability, Task Analysis, Training, word embedding |
| Abstract | Natural language processing (NLP) have been recently used to extract clinical information from free text in Electronic Health Record (EHR). In clinical NLP one challenge is that the meaning of clinical entities is heavily affected by assertion modifiers such as negation, uncertain, hypothetical, experiencer and so on. Incorrect assertion assignment could cause inaccurate diagnosis of patients' condition or negatively influence following study like disease modeling. Thus, clinical NLP systems which can detect assertion status of given target medical findings (e.g. disease, symptom) in clinical context are highly demanded. Here in this work, we propose a deep-learning system based on word embedding, RNN and attention mechanism (more specifically: Attention-based Bidirectional Long Short-Term Memory networks) for assertion detection in clinical notes. Unlike previous state-of-art methods which require knowledge input or feature engineering, our system is a knowledge poor machine learning system and can be easily extended or transferred to other domains. The evaluation of our system on public benchmarking corpora demonstrates that a knowledge poor deep-learning system can also achieve high performance for detecting negation and assertions comparing to state-of-the-art systems. |
| DOI | 10.1109/INFOCT.2019.8710921 |
| Citation Key | chen_assertion_2019 |
Assertion Detection in Clinical Natural Language Processing: A Knowledge-Poor Machine Learning Approach