{
  "id": "2211.07549",
  "version": "v1",
  "published": "2022-11-14T17:14:39.000Z",
  "updated": "2022-11-14T17:14:39.000Z",
  "title": "Phenotype Detection in Real World Data via Online MixEHR Algorithm",
  "authors": [
    "Ying Xu",
    "Anna Decker",
    "Jacob Oppenheim",
    "Romane Gauriau"
  ],
  "comment": "Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2022, November 28th, 2022, New Orleans, United States & Virtual, http://www.ml4h.cc, 6 pages",
  "categories": [
    "cs.LG"
  ],
  "abstract": "Understanding patterns of diagnoses, medications, procedures, and laboratory tests from electronic health records (EHRs) and health insurer claims is important for understanding disease risk and for efficient clinical development, which often require rules-based curation in collaboration with clinicians. We extended an unsupervised phenotyping algorithm, mixEHR, to an online version allowing us to use it on order of magnitude larger datasets including a large, US-based claims dataset and a rich regional EHR dataset. In addition to recapitulating previously observed disease groups, we discovered clinically meaningful disease subtypes and comorbidities. This work scaled up an effective unsupervised learning method, reinforced existing clinical knowledge, and is a promising approach for efficient collaboration with clinicians.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-11-14T17:14:39.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "real world data",
      "online mixehr algorithm",
      "phenotype detection",
      "rich regional ehr dataset",
      "electronic health records"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 6,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}