{
  "id": "1905.12916",
  "version": "v1",
  "published": "2019-05-30T09:06:58.000Z",
  "updated": "2019-05-30T09:06:58.000Z",
  "title": "Effective Medical Test Suggestions Using Deep Reinforcement Learning",
  "authors": [
    "Yang-En Chen",
    "Kai-Fu Tang",
    "Yu-Shao Peng",
    "Edward Y. Chang"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Effective medical test suggestions benefit both patients and physicians to conserve time and improve diagnosis accuracy. In this work, we show that an agent can learn to suggest effective medical tests. We formulate the problem as a stage-wise Markov decision process and propose a reinforcement learning method to train the agent. We introduce a new representation of multiple action policy along with the training method of the proposed representation. Furthermore, a new exploration scheme is proposed to accelerate the learning of disease distributions. Our experimental results demonstrate that the accuracy of disease diagnosis can be significantly improved with good medical test suggestions.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-05-30T09:06:58.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep reinforcement learning",
      "experimental results demonstrate",
      "multiple action policy",
      "effective medical test suggestions benefit",
      "stage-wise markov decision process"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}