Send to

Choose Destination
J Am Med Inform Assoc. 2015 Sep;22(5):1009-19. doi: 10.1093/jamia/ocv016. Epub 2015 Apr 9.

Subgraph augmented non-negative tensor factorization (SANTF) for modeling clinical narrative text.

Author information

Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology
Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology.
Center for Lymphoma, Massachusetts General Hospital and Department of Medicine, Harvard Medical School.
Department of Information Studies, State University of New York at Albany.



Extracting medical knowledge from electronic medical records requires automated approaches to combat scalability limitations and selection biases. However, existing machine learning approaches are often regarded by clinicians as black boxes. Moreover, training data for these automated approaches at often sparsely annotated at best. The authors target unsupervised learning for modeling clinical narrative text, aiming at improving both accuracy and interpretability.


The authors introduce a novel framework named subgraph augmented non-negative tensor factorization (SANTF). In addition to relying on atomic features (e.g., words in clinical narrative text), SANTF automatically mines higher-order features (e.g., relations of lymphoid cells expressing antigens) from clinical narrative text by converting sentences into a graph representation and identifying important subgraphs. The authors compose a tensor using patients, higher-order features, and atomic features as its respective modes. We then apply non-negative tensor factorization to cluster patients, and simultaneously identify latent groups of higher-order features that link to patient clusters, as in clinical guidelines where a panel of immunophenotypic features and laboratory results are used to specify diagnostic criteria.


SANTF demonstrated over 10% improvement in averaged F-measure on patient clustering compared to widely used non-negative matrix factorization (NMF) and k-means clustering methods. Multiple baselines were established by modeling patient data using patient-by-features matrices with different feature configurations and then performing NMF or k-means to cluster patients. Feature analysis identified latent groups of higher-order features that lead to medical insights. We also found that the latent groups of atomic features help to better correlate the latent groups of higher-order features.


natural language processing; non-negative tensor factorization; subgraph mining; unsupervised learning

[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Silverchair Information Systems Icon for PubMed Central
Loading ...
Support Center