Identifying Breast Cancer Distant Recurrences from Electronic Health Records Using Machine Learning
- 8 April 2019
- journal article
- research article
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 3 (3) , 283-299
Abstract
Accurately identifying distant recurrences in breast cancer from the electronic health records (EHR) is important for both clinical care and secondary analysis. Although multiple applications have been developed for computational phenotyping in breast cancer, distant recurrence identification still relies heavily on manual chart review. In this study, we aim to develop a model that identifies distant recurrences in breast cancer using clinical narratives and structured data from EHR. We applied MetaMap to extract features from clinical narratives and also retrieved structured clinical data from EHR. Using these features, we trained a support vector machine model to identify distant recurrences in breast cancer patients. We trained the model using 1396 double-annotated subjects and validated the model using 599 double-annotated subjects. In addition, we validated the model on a set of 4904 single-annotated subjects as a generalization test. In the held-out test and generalization test, we obtained F-measure scores of 0.78 and 0.74, area under curve (AUC) scores of 0.95 and 0.93, respectively. To explore the representation learning utility of deep neural networks, we designed multiple convolutional neural networks and multilayer neural networks to identify distant recurrences. Using the same test set and generalizability test set, we obtained F-measure scores of 0.79 ± 0.02 and 0.74 ± 0.004, AUC scores of 0.95 ± 0.002 and 0.95 ± 0.01, respectively. Our model can accurately and efficiently identify distant recurrences in breast cancer by combining features extracted from unstructured clinical narratives and structured clinical data.Keywords
Funding Information
- NIH (R21LM012618-01)
This publication has 43 references indexed in Scilit:
- Semi-supervised clinical text classification with Laplacian SVMs: An application to cancer case managementJournal of Biomedical Informatics, 2013
- Using the Electronic Medical Record to Identify Community-Acquired Pneumonia: Toward a Replicable Automated StrategyPLOS ONE, 2013
- Pneumonia identification using statistical feature selectionJournal of the American Medical Informatics Association, 2012
- Electronic medical records for discovery research in rheumatoid arthritisArthritis Care & Research, 2010
- Declining recurrence among ductal carcinoma in situ patients treated with breast-conserving surgery in the community settingBreast Cancer Research, 2009
- Breast Cancer Recurrence in Older Women Five to Ten Years after DiagnosisCancer Epidemiology, Biomarkers & Prevention, 2009
- Collection of Cancer Stage Data by Classifying Free-text Medical ReportsJournal of the American Medical Informatics Association, 2007
- Measuring Diagnoses: ICD Code AccuracyHealth Services Research, 2005
- Accuracy of veterans administration databases for a diagnosis of rheumatoid arthritisArthritis Care & Research, 2004
- "Understanding" Medical School Curriculum Content Using KnowledgeMapJournal of the American Medical Informatics Association, 2003