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

Using natural language processing and machine learning to identify breast cancer local recurrence.

Using natural language processing and machine learning to identify breast cancer local recurrence.

Read the original article.

Zeng Z1Espino S2Roy A2Li X3Khan SA2Clare SE2Jiang X4Neapolitan R1Luo Y5.

Author information

  1. Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA.
  2. Department of Surgery, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA.
  3. Department of Social and Behavioral Sciences, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
  4. Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA, USA.
  5. Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA. yuan.luo@northwestern.edu.

Abstract

BACKGROUND:
Identifying local recurrences in breast cancer from patient data sets is important for clinical research and practice. Developing a model using natural language processing and machine learning to identify local recurrences in breast cancer patients can reduce the time-consuming work of a manual chart review.

METHODS:
We design a novel concept-based filter and a prediction model to detect local recurrences using EHRs. In the training dataset, we manually review a development corpus of 50 progress notes and extract partial sentences that indicate breast cancer local recurrence. We process these partial sentences to obtain a set of Unified Medical Language System (UMLS) concepts using MetaMap, and we call it positive concept set. We apply MetaMap on patients’ progress notes and retain only the concepts that fall within the positive concept set. These features combined with the number of pathology reports recorded for each patient are used to train a support vector machine to identify local recurrences.

RESULTS:
We compared our model with three baseline classifiers using either full MetaMap concepts, filtered MetaMap concepts, or bag of words. Our model achieved the best AUC (0.93 in cross-validation, 0.87 in held-out testing).

CONCLUSIONS:
Compared to a labor-intensive chart review, our model provides an automated way to identify breast cancer local recurrences. We expect that by minimally adapting the positive concept set, this study has the potential to be replicated at other institutions with a moderately sized training dataset.

KEYWORDS:
Breast cancer local recurrence; EHR; NLP; SVM

PMID: 30591037
PMCID: PMC6309052
DOI: 10.1186/s12859-018-2466-x