Literature DB >> 27102331

Computer-based coding of free-text job descriptions to efficiently identify occupations in epidemiological studies.

Daniel E Russ1, Kwan-Yuet Ho1, Joanne S Colt2, Karla R Armenti3, Dalsu Baris2, Wong-Ho Chow4, Faith Davis5, Alison Johnson6, Mark P Purdue2, Margaret R Karagas7, Kendra Schwartz8, Molly Schwenn9, Debra T Silverman2, Calvin A Johnson1, Melissa C Friesen2.   

Abstract

BACKGROUND: Mapping job titles to standardised occupation classification (SOC) codes is an important step in identifying occupational risk factors in epidemiological studies. Because manual coding is time-consuming and has moderate reliability, we developed an algorithm called SOCcer (Standardized Occupation Coding for Computer-assisted Epidemiologic Research) to assign SOC-2010 codes based on free-text job description components.
METHODS: Job title and task-based classifiers were developed by comparing job descriptions to multiple sources linking job and task descriptions to SOC codes. An industry-based classifier was developed based on the SOC prevalence within an industry. These classifiers were used in a logistic model trained using 14 983 jobs with expert-assigned SOC codes to obtain empirical weights for an algorithm that scored each SOC/job description. We assigned the highest scoring SOC code to each job. SOCcer was validated in 2 occupational data sources by comparing SOC codes obtained from SOCcer to expert assigned SOC codes and lead exposure estimates obtained by linking SOC codes to a job-exposure matrix.
RESULTS: For 11 991 case-control study jobs, SOCcer-assigned codes agreed with 44.5% and 76.3% of manually assigned codes at the 6-digit and 2-digit level, respectively. Agreement increased with the score, providing a mechanism to identify assignments needing review. Good agreement was observed between lead estimates based on SOCcer and manual SOC assignments (κ 0.6-0.8). Poorer performance was observed for inspection job descriptions, which included abbreviations and worksite-specific terminology.
CONCLUSIONS: Although some manual coding will remain necessary, using SOCcer may improve the efficiency of incorporating occupation into large-scale epidemiological studies. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://www.bmj.com/company/products-services/rights-and-licensing/

Entities:  

Keywords:  Computers and information technology < Methodology; speciality

Mesh:

Year:  2016        PMID: 27102331      PMCID: PMC4871757          DOI: 10.1136/oemed-2015-103152

Source DB:  PubMed          Journal:  Occup Environ Med        ISSN: 1351-0711            Impact factor:   4.402


  16 in total

1.  The use of occupation and industry classifications in general population studies.

Authors:  A 't Mannetje; H Kromhout
Journal:  Int J Epidemiol       Date:  2003-06       Impact factor: 7.196

Review 2.  Occupational exposure assessment in case-control studies: opportunities for improvement.

Authors:  K Teschke; A F Olshan; J L Daniels; A J De Roos; C G Parks; M Schulz; T L Vaughan
Journal:  Occup Environ Med       Date:  2002-09       Impact factor: 4.402

3.  Occupation and bladder cancer in a population-based case-control study in Northern New England.

Authors:  Joanne S Colt; Margaret R Karagas; Molly Schwenn; Dalsu Baris; Alison Johnson; Patricia Stewart; Castine Verrill; Lee E Moore; Jay Lubin; Mary H Ward; Claudine Samanic; Nathaniel Rothman; Kenneth P Cantor; Laura E Beane Freeman; Alan Schned; Sai Cherala; Debra T Silverman
Journal:  Occup Environ Med       Date:  2010-09-23       Impact factor: 4.402

4.  A computer system for coding occupation.

Authors:  Eric M Ossiander; Samuel Milham
Journal:  Am J Ind Med       Date:  2006-10       Impact factor: 2.214

5.  Performance of automated and manual coding systems for occupational data: a case study of historical records.

Authors:  Mehul D Patel; Kathryn M Rose; Cindy R Owens; Heejung Bang; Jay S Kaufman
Journal:  Am J Ind Med       Date:  2012-03       Impact factor: 2.214

6.  JEMs and incompatible occupational coding systems: effect of manual and automatic recoding of job codes on exposure assignment.

Authors:  Tom Koeman; Nadine S M Offermans; Yvette Christopher-de Vries; Pauline Slottje; Piet A Van Den Brandt; R Alexandra Goldbohm; Hans Kromhout; Roel Vermeulen
Journal:  Ann Occup Hyg       Date:  2012-07-17

7.  Beyond crosswalks: reliability of exposure assessment following automated coding of free-text job descriptions for occupational epidemiology.

Authors:  Igor Burstyn; Anton Slutsky; Derrick G Lee; Alison B Singer; Yuan An; Yvonne L Michael
Journal:  Ann Occup Hyg       Date:  2014-02-06

8.  Occupational risk factors for cancer of the central nervous system (CNS) among US women.

Authors:  P Cocco; E F Heineman; M Dosemeci
Journal:  Am J Ind Med       Date:  1999-07       Impact factor: 2.214

9.  Computer-Based Coding of Occupation Codes for Epidemiological Analyses.

Authors:  Daniel E Russ; Kwan-Yuet Ho; Calvin A Johnson; Melissa C Friesen
Journal:  Proc IEEE Int Symp Comput Based Med Syst       Date:  2014-05

10.  Methods and feasibility of collecting occupational data for a large population-based cohort study in the United States: the reasons for geographic and racial differences in stroke study.

Authors:  Leslie A MacDonald; LeaVonne Pulley; Misty J Hein; Virginia J Howard
Journal:  BMC Public Health       Date:  2014-02-10       Impact factor: 3.295

View more
  10 in total

1.  What Should We Do with Short-Term Jobs in Studies of Chronic Diseases?

Authors:  Melissa C Friesen
Journal:  Ann Work Expo Health       Date:  2019-07-24       Impact factor: 2.179

2.  Development of a Coding and Crosswalk Tool for Occupations and Industries.

Authors:  Thomas Rémen; Lesley Richardson; Corinne Pilorget; Gilles Palmer; Jack Siemiatycki; Jérôme Lavoué
Journal:  Ann Work Expo Health       Date:  2018-08-13       Impact factor: 2.179

3.  Capture and coding of industry and occupation measures: Findings from eight National Program of Cancer Registries states.

Authors:  MaryBeth B Freeman; Lori A Pollack; Judy R Rees; Christopher J Johnson; Randi K Rycroft; David L Rousseau; Mei-Chin Hsieh
Journal:  Am J Ind Med       Date:  2017-08       Impact factor: 2.214

4.  Efficiency of autocoding programs for converting job descriptors into standard occupational classification (SOC) codes.

Authors:  Skye Buckner-Petty; Ann Marie Dale; Bradley A Evanoff
Journal:  Am J Ind Med       Date:  2018-12-05       Impact factor: 2.214

5.  Smoking status, usual adult occupation, and risk of recurrent urothelial bladder carcinoma: data from The Cancer Genome Atlas (TCGA) Project.

Authors:  Amber N Wilcox; Debra T Silverman; Melissa C Friesen; Sarah J Locke; Daniel E Russ; Noorie Hyun; Joanne S Colt; Jonine D Figueroa; Nathaniel Rothman; Lee E Moore; Stella Koutros
Journal:  Cancer Causes Control       Date:  2016-11-01       Impact factor: 2.506

6.  Determining occupation for National Violent Death Reporting System records: An evaluation of autocoding programs.

Authors:  Jonathan Davis; Corinne Peek-Asa; Ann Marie Dale; Ling Zhang; Carri Casteel; Cara Hamann; Bradley A Evanoff
Journal:  Am J Ind Med       Date:  2021-09-07       Impact factor: 3.079

7.  Harmonizing work history data in epidemiologic studies with overlapping employment records.

Authors:  Jo Steinson Stenehjem; Ronnie Babigumira; Melissa C Friesen; Tom Kristian Grimsrud
Journal:  Am J Ind Med       Date:  2019-03-28       Impact factor: 3.079

Review 8.  A Narrative Literature Review of Natural Language Processing Applied to the Occupational Exposome.

Authors:  Annika M Schoene; Ioannis Basinas; Martie van Tongeren; Sophia Ananiadou
Journal:  Int J Environ Res Public Health       Date:  2022-07-13       Impact factor: 4.614

9.  Associations of self-reported occupational exposures and settings to ALS: a case-control study.

Authors:  Stephen A Goutman; Jonathan Boss; Christopher Godwin; Bhramar Mukherjee; Eva L Feldman; Stuart A Batterman
Journal:  Int Arch Occup Environ Health       Date:  2022-05-20       Impact factor: 2.851

10.  Labour market competition for public health graduates in the United States: A comparison of workforce taxonomies with job postings before and during the COVID-19 pandemic.

Authors:  Heather Krasna; Katarzyna Czabanowska; Angela Beck; Linda F Cushman; Jonathon P Leider
Journal:  Int J Health Plann Manage       Date:  2021-02-24
  10 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.