Contact us at (866) 265-5575 or sales@realhealthdata.com

Finding Needles in the Haystack: Identifying Patients with Rare Subtype of Multiple Myeloma Supported by a Data Warehouse and Information Extraction.

Finding Needles in the Haystack: Identifying Patients with Rare Subtype of Multiple Myeloma Supported by a Data Warehouse and Information Extraction.

Read the original article.

Krebs J1,┬ Bittrich M2,┬ Dietrich G1,┬ Ertl M3,┬ Fette G4,┬ Kaspar M4,┬ Liman L1,┬ Einsele H2,┬ Puppe F1,┬ Knop S2.

Author information

  1. Chair for Artificial Intelligence and Applied Informatics, University of W├╝rzburg.
  2. Department of Medicine II, University Hospital W├╝rzburg.
  3. Service-center Medical Informatics, University Hospital W├╝rzburg.
  4. Comprehensive Heart Failure Center, University Hospital W├╝rzburg.

Abstract

Finding patient cases with extremely rare pathologies is a laborious task. To decrease time spent on manually searching through thousands of discharge letters and reports, a data warehouse with a fast fulltext search index was queried. Our use case is to find “macrofocal myeloma”, i.e. Multiple Myeloma patients with few large lesions. We guessed the number of those patients in the University Hospital W├╝rzburg at about 20. Most criteria were available in the data warehouse in an unstructured form requiring information extraction. 8 patient cases were found by searching for different spellings of “macrofocal myeloma” in discharge letters directly. With an indirect search combining several criteria, we found additional 23 candidate patient cases, from which 10 were classified by a domain expert as correct. The most difficult criteria were determining the degree of bone marrow infiltration. We achieved an F1 score of 93.2 % for this task. The number of patient cases to be screened manually for this disease decreased from about 25000 to 23.

KEYWORDS:

Macrofocal myeloma; NLP; data warehouse; information extraction

PMID: 30147064
[Indexed for MEDLINE]