Dilated Convolutional Attention Network for Medical Code Assignment from Clinical Text

Shaoxiong Ji, Erik Cambria, Pekka Marttinen

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

Abstrakti

Medical code assignment, which predicts medical codes from clinical texts, is a fundamental task of intelligent medical information systems. The emergence of deep models in natural language processing has boosted the development of automatic assignment methods. However, recent advanced neural architectures with flat convolutions or multi-channel feature concatenation ignore the sequential causal constraint within a text sequence and may not learn meaningful clinical text representations, especially for lengthy clinical notes with long-term sequential dependency. This paper proposes a Dilated Convolutional Attention Network (DCAN), integrating dilated convolutions, residual connections, and label attention, for medical code assignment. It adopts dilated convolutions to capture complex medical patterns with a receptive field which increases exponentially with dilation size. Experiments on a real-world clinical dataset empirically show that our model improves the state of the art.
Alkuperäiskielienglanti
OtsikkoProceedings of the 3rd Clinical Natural Language Processing Workshop
ToimittajatAnna Rumshisky, et al.
Sivumäärä6
JulkaisupaikkaStroudsburg
KustantajaThe Association for Computational Linguistics
Julkaisupäivä1 marrask. 2020
Sivut73-78
ISBN (elektroninen)978-1-952148-74-3
DOI - pysyväislinkit
TilaJulkaistu - 1 marrask. 2020
Julkaistu ulkoisestiKyllä
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaClinical Natural Language Processing Workshop
- [Online event]
Kesto: 19 marrask. 202119 marrask. 2021
Konferenssinumero: 3

Tieteenalat

  • 6121 Kielitieteet
  • 113 Tietojenkäsittely- ja informaatiotieteet

Siteeraa tätä