Exploiting historical registers: Automatic methods for coding c19th and c20th cause of death descriptions to standard classifications

Jamie Kirk Carson, Graham Njal Cameron Kirby, Alan Dearle, Lee Williamson, Eilidh Garrett, Alice Reid, Christopher John Lloyd Dibben

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Downloads (Pure)

Abstract

The increasing availability of digitised registration records presents a significant opportunity for research. Returning to the original records allows researchers to classify descriptions, such as cause of death, to modern medical understandings of illness and disease, rather than relying on contemporary registrars’ classifications. Linkage of an individual’s records together also allows the production of sparse life-course micro-datasets. The further linkage of these into family units then presents the possibility of reconstructing family structures and producing multi-generational studies. We describe work to develop a method for automatically coding to standard classifications the causes of death from 8.3 million Scottish death certificates. We have evaluated a range of approaches using text processing and supervised machine learning, obtaining accuracy from 72%-96% on several test sets. We present results and speculate on further development that may be needed for classification of the full data set.
Original languageEnglish
Title of host publicationNew Techniques and Technologies for Statistics
Place of Publicationhttp://www.cros-portal.eu/content/ntts-2013-proceedings
PublisherEurostat
Pages598-607
Number of pages10
DOIs
Publication statusPublished - 5 Mar 2013
EventNew Techniques and Technologies for Statistics (NTTS 2013) - Brussels, Belgium
Duration: 5 Mar 20137 Mar 2013

Conference

ConferenceNew Techniques and Technologies for Statistics (NTTS 2013)
Country/TerritoryBelgium
CityBrussels
Period5/03/137/03/13

Fingerprint

Dive into the research topics of 'Exploiting historical registers: Automatic methods for coding c19th and c20th cause of death descriptions to standard classifications'. Together they form a unique fingerprint.

Cite this