Abstract | ||
---|---|---|
As more and more information is available in the Electronic Health Record in the form of free-text narrative, there is a need for automated tools, which can process and understand such texts. One first step towards the automated processing of clinical texts is to determine the document-level structure of a patient note, i.e., identifying the different sections and mapping them to known section types automatically. This paper considers section mapping as a sequence-labeling problem to 15 possible known section types. Our method relies on a Hidden Markov Model (HMM) trained on a corpus of 9,679 clinical notes from NewYork-Presbyterian Hospital. We compare our method to a state-of-the-art baseline, which ignores the sequential aspect of the sections and considers each section independently of the others in a note. Experiments show that our method outperforms the baseline significantly, yielding 93% accuracy in identifying sections individually and 70% accuracy in identifying all the sections in a note, compared to 70% and 19% for the baseline method respectively. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1145/1882992.1883105 | IHI |
Keywords | Field | DocType |
section classification,supervised hidden markov model,possible known section type,section mapping,automated processing,different section,clinical note,state-of-the-art baseline,patient note,known section type,automated tool,hidden markov model,natural language processing,discourse analysis | Computer science,Narrative,Discourse analysis,Natural language processing,Medical record,Artificial intelligence,Hidden Markov model,Patient Note,Machine learning | Conference |
Citations | PageRank | References |
15 | 0.80 | 20 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ying Li | 1 | 222 | 42.33 |
Sharon Lipsky Gorman | 2 | 15 | 3.17 |
Noémie Elhadad | 3 | 289 | 20.78 |