{
  "id": "1603.09381",
  "version": "v1",
  "published": "2016-03-30T20:57:07.000Z",
  "updated": "2016-03-30T20:57:07.000Z",
  "title": "Clinical Information Extraction via Convolutional Neural Network",
  "authors": [
    "Peng Li",
    "Heng Huang"
  ],
  "comment": "arXiv admin note: text overlap with arXiv:1408.5882 by other authors",
  "categories": [
    "cs.LG",
    "cs.CL",
    "cs.NE"
  ],
  "abstract": "We report an implementation of a clinical information extraction tool that leverages deep neural network to annotate event spans and their attributes from raw clinical notes and pathology reports. Our approach uses context words and their part-of-speech tags and shape information as features. Then we hire temporal (1D) convolutional neural network to learn hidden feature representations. Finally, we use Multilayer Perceptron (MLP) to predict event spans. The empirical evaluation demonstrates that our approach significantly outperforms baselines.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-03-30T20:57:07.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "convolutional neural network",
      "leverages deep neural network",
      "learn hidden feature representations",
      "clinical information extraction tool",
      "annotate event spans"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2016arXiv160309381L"
    }
  }
}