Automatic ICD-10 classification of cancers from free-text death certificates.

Journal: International journal of medical informatics

PMID: 26323193

Abstract

OBJECTIVE: Death certificates provide an invaluable source for cancer mortality statistics; however, this value can only be realised if accurate, quantitative data can be extracted from certificates--an aim hampered by both the volume and variable nature of certificates written in natural language. This paper proposes an automatic classification system for identifying cancer related causes of death from death certificates.

Authors

Bevan Koopman

Australian e-Health Research Centre, CSIRO, Brisbane, QLD, Australia; Queensland University of Technology, Brisbane, QLD, Australia.
Guido Zuccon

Queensland University of Technology, Brisbane, QLD, Australia.
Anthony Nguyen

Australian e-Health Research Centre, CSIRO, Brisbane, QLD, Australia.
Anton Bergheim

Cancer Institute NSW, Sydney, Australia. Electronic address: anton.bergheim@cancerinstitute.org.au.
Narelle Grayson

Cancer Institute NSW, Sydney, Australia. Electronic address: Narelle.Grayson@cancerinstitute.org.au.

Keywords

Cause of Death Death Certificates Humans International Classification of Diseases Machine Learning Natural Language Processing Neoplasms New South Wales Program Evaluation Registries

External Resources

View on PubMed Access via DOI PubMed (26323193)

Automatic ICD-10 classification of cancers from free-text death certificates.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals