Breathing new life into death certificates: Extracting handwritten cause of death in the LIFE-M project

Martha J. Bailey; Susan H. Leonard; Joseph Price; Evan Roberts; Logan Spector; Mengying Zhang

doi:10.1016/j.eeh.2022.101474

Breathing new life into death certificates: Extracting handwritten cause of death in the LIFE-M project

Martha J. Bailey
, Susan H. Leonard
, Joseph Price
, Evan Roberts
, Logan Spector
, Mengying Zhang

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

The demographic and epidemiological transitions of the past 200 years are well documented at an aggregate level. Understanding differences in individual and group risks for mortality during these transitions requires linkage between demographic data and detailed individual cause of death information. This paper describes the digitization of almost 185,000 causes of death for Ohio to supplement demographic information in the Longitudinal, Intergenerational Family Electronic Micro-database (LIFE-M). To extract causes of death, our methodology combines handwriting recognition, extensive data cleaning algorithms, and the semi-automated classification of causes of death into International Classification of Diseases (ICD) codes. Our procedures are adaptable to other collections of handwritten data, which require both handwriting recognition and semi-automated coding of the information extracted.

Original language	English (US)
Article number	101474
Journal	Explorations in Economic History
Volume	87
DOIs	https://doi.org/10.1016/j.eeh.2022.101474
State	Published - Jan 2023

Bibliographical note

Funding Information:
This project is generously supported by the National Science Foundation (SMA-1,539,228), the National Institute on Aging (R21 AG056912), and the University of California, Los Angeles. Supplemental funding from the National Institute on Aging (R01 AG057704) allowed us to add cause of death for records in Ohio. Pilot work on this project was generously supported by the University of Michigan ’s Department of Economics Michigan Institute for Teaching and Research in Economics (MITER) grant, the University of Michigan's Population Studies Center Small Grant (R24 HD041028), and the Michigan Center for the Demography of Aging (MiCDA) grant (P30 AG012846–21). We gratefully acknowledge the use of the services and facilities of the Population Studies Center at the University of Michigan (R24 HD041028 and P2C HD041028), the California Center for Population Research at UCLA (P2C HD041022), and the Minnesota Population Center (P2C HD041023).

Funding Information:
This project is generously supported by the National Science Foundation (SMA-1,539,228), the National Institute on Aging (R21 AG056912), and the University of California, Los Angeles. Supplemental funding from the National Institute on Aging (R01 AG057704) allowed us to add cause of death for records in Ohio. Pilot work on this project was generously supported by the University of Michigan's Department of Economics Michigan Institute for Teaching and Research in Economics (MITER) grant, the University of Michigan's Population Studies Center Small Grant (R24 HD041028), and the Michigan Center for the Demography of Aging (MiCDA) grant (P30 AG012846–21). We gratefully acknowledge the use of the services and facilities of the Population Studies Center at the University of Michigan (R24 HD041028 and P2C HD041028), the California Center for Population Research at UCLA (P2C HD041022), and the Minnesota Population Center (P2C HD041023).

Publisher Copyright:
© 2022

Keywords

Cause of death
Death certificate
Semi-automated classification

Publisher link

10.1016/j.eeh.2022.101474

Find It

Find It at U of M Libraries

Cite this

@article{8de6ebf4d2f44c75a944501d95b3bfe6,

title = "Breathing new life into death certificates: Extracting handwritten cause of death in the LIFE-M project",

abstract = "The demographic and epidemiological transitions of the past 200 years are well documented at an aggregate level. Understanding differences in individual and group risks for mortality during these transitions requires linkage between demographic data and detailed individual cause of death information. This paper describes the digitization of almost 185,000 causes of death for Ohio to supplement demographic information in the Longitudinal, Intergenerational Family Electronic Micro-database (LIFE-M). To extract causes of death, our methodology combines handwriting recognition, extensive data cleaning algorithms, and the semi-automated classification of causes of death into International Classification of Diseases (ICD) codes. Our procedures are adaptable to other collections of handwritten data, which require both handwriting recognition and semi-automated coding of the information extracted.",

keywords = "Cause of death, Death certificate, Semi-automated classification",

author = "Bailey, \{Martha J.\} and Leonard, \{Susan H.\} and Joseph Price and Evan Roberts and Logan Spector and Mengying Zhang",

note = "Funding Information: This project is generously supported by the National Science Foundation (SMA-1,539,228), the National Institute on Aging (R21 AG056912), and the University of California, Los Angeles. Supplemental funding from the National Institute on Aging (R01 AG057704) allowed us to add cause of death for records in Ohio. Pilot work on this project was generously supported by the University of Michigan {\textquoteright}s Department of Economics Michigan Institute for Teaching and Research in Economics (MITER) grant, the University of Michigan's Population Studies Center Small Grant (R24 HD041028), and the Michigan Center for the Demography of Aging (MiCDA) grant (P30 AG012846{\textendash}21). We gratefully acknowledge the use of the services and facilities of the Population Studies Center at the University of Michigan (R24 HD041028 and P2C HD041028), the California Center for Population Research at UCLA (P2C HD041022), and the Minnesota Population Center (P2C HD041023). Funding Information: This project is generously supported by the National Science Foundation (SMA-1,539,228), the National Institute on Aging (R21 AG056912), and the University of California, Los Angeles. Supplemental funding from the National Institute on Aging (R01 AG057704) allowed us to add cause of death for records in Ohio. Pilot work on this project was generously supported by the University of Michigan's Department of Economics Michigan Institute for Teaching and Research in Economics (MITER) grant, the University of Michigan's Population Studies Center Small Grant (R24 HD041028), and the Michigan Center for the Demography of Aging (MiCDA) grant (P30 AG012846{\textendash}21). We gratefully acknowledge the use of the services and facilities of the Population Studies Center at the University of Michigan (R24 HD041028 and P2C HD041028), the California Center for Population Research at UCLA (P2C HD041022), and the Minnesota Population Center (P2C HD041023). Publisher Copyright: {\textcopyright} 2022",

year = "2023",

month = jan,

doi = "10.1016/j.eeh.2022.101474",

language = "English (US)",

volume = "87",

journal = "Explorations in Economic History",

issn = "0014-4983",

publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Breathing new life into death certificates

T2 - Extracting handwritten cause of death in the LIFE-M project

AU - Bailey, Martha J.

AU - Leonard, Susan H.

AU - Price, Joseph

AU - Roberts, Evan

AU - Spector, Logan

AU - Zhang, Mengying

N1 - Funding Information: This project is generously supported by the National Science Foundation (SMA-1,539,228), the National Institute on Aging (R21 AG056912), and the University of California, Los Angeles. Supplemental funding from the National Institute on Aging (R01 AG057704) allowed us to add cause of death for records in Ohio. Pilot work on this project was generously supported by the University of Michigan ’s Department of Economics Michigan Institute for Teaching and Research in Economics (MITER) grant, the University of Michigan's Population Studies Center Small Grant (R24 HD041028), and the Michigan Center for the Demography of Aging (MiCDA) grant (P30 AG012846–21). We gratefully acknowledge the use of the services and facilities of the Population Studies Center at the University of Michigan (R24 HD041028 and P2C HD041028), the California Center for Population Research at UCLA (P2C HD041022), and the Minnesota Population Center (P2C HD041023). Funding Information: This project is generously supported by the National Science Foundation (SMA-1,539,228), the National Institute on Aging (R21 AG056912), and the University of California, Los Angeles. Supplemental funding from the National Institute on Aging (R01 AG057704) allowed us to add cause of death for records in Ohio. Pilot work on this project was generously supported by the University of Michigan's Department of Economics Michigan Institute for Teaching and Research in Economics (MITER) grant, the University of Michigan's Population Studies Center Small Grant (R24 HD041028), and the Michigan Center for the Demography of Aging (MiCDA) grant (P30 AG012846–21). We gratefully acknowledge the use of the services and facilities of the Population Studies Center at the University of Michigan (R24 HD041028 and P2C HD041028), the California Center for Population Research at UCLA (P2C HD041022), and the Minnesota Population Center (P2C HD041023). Publisher Copyright: © 2022

PY - 2023/1

Y1 - 2023/1

N2 - The demographic and epidemiological transitions of the past 200 years are well documented at an aggregate level. Understanding differences in individual and group risks for mortality during these transitions requires linkage between demographic data and detailed individual cause of death information. This paper describes the digitization of almost 185,000 causes of death for Ohio to supplement demographic information in the Longitudinal, Intergenerational Family Electronic Micro-database (LIFE-M). To extract causes of death, our methodology combines handwriting recognition, extensive data cleaning algorithms, and the semi-automated classification of causes of death into International Classification of Diseases (ICD) codes. Our procedures are adaptable to other collections of handwritten data, which require both handwriting recognition and semi-automated coding of the information extracted.

AB - The demographic and epidemiological transitions of the past 200 years are well documented at an aggregate level. Understanding differences in individual and group risks for mortality during these transitions requires linkage between demographic data and detailed individual cause of death information. This paper describes the digitization of almost 185,000 causes of death for Ohio to supplement demographic information in the Longitudinal, Intergenerational Family Electronic Micro-database (LIFE-M). To extract causes of death, our methodology combines handwriting recognition, extensive data cleaning algorithms, and the semi-automated classification of causes of death into International Classification of Diseases (ICD) codes. Our procedures are adaptable to other collections of handwritten data, which require both handwriting recognition and semi-automated coding of the information extracted.

KW - Cause of death

KW - Death certificate

KW - Semi-automated classification

UR - https://www.scopus.com/pages/publications/85138792012

UR - https://www.scopus.com/pages/publications/85138792012#tab=citedBy

U2 - 10.1016/j.eeh.2022.101474

DO - 10.1016/j.eeh.2022.101474

M3 - Article

C2 - 36778518

AN - SCOPUS:85138792012

SN - 0014-4983

VL - 87

JO - Explorations in Economic History

JF - Explorations in Economic History

M1 - 101474

ER -

Breathing new life into death certificates: Extracting handwritten cause of death in the LIFE-M project

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this