Development and evaluation of a Naïve Bayesian model for coding causation of workers' compensation claims

Journal of Safety Research

Volumn 43, Issue 5-6, 2012, Pages 327-332

  Bertke, S J ^a   Meyers, A R ^a   Wurzelbacher, S J ^a   Bell, J ^a   Lampl, M L ^b   Robins, D ^b  

^a NATIONAL INSTITUTE FOR OCCUPATIONAL SAFETY AND HEALTH   (United States)

^b Ohio Bureau of Workers' Compensation   (United States)

Author keywords

Accident narratives; Bayes; Data mining; Text classification; Text mining

Indexed keywords

BAYES; BAYESIAN MODEL; FREEFORMS; INDUSTRY SECTORS; LARGE DATABASE; LARGE DATASETS; MANUAL CODING; MUSCULOSKELETAL DISORDERS; REPETITIVE MOTIONS; RISK FACTORS; TEXT CLASSIFICATION; TEXT-MINING; WORKERS' COMPENSATION;

ACCIDENT PREVENTION; ACCIDENTS; BAYESIAN NETWORKS; CLASSIFICATION (OF INFORMATION); DISEASES; HEALTH RISKS; PROGRAM DIAGNOSTICS;

OCCUPATIONAL RISKS;

ALGORITHM; ARTICLE; BAYES THEOREM; CLASSIFICATION; CODING; DATA MINING; EVALUATION; HUMAN; METHODOLOGY; MUSCULOSKELETAL DISEASE; OCCUPATIONAL ACCIDENT; QUALITY CONTROL; RISK FACTOR; SAMPLE SIZE; STANDARD; STATISTICS; THEORETICAL MODEL; WORKMAN COMPENSATION;

ACCIDENTS, OCCUPATIONAL; ALGORITHMS; BAYES THEOREM; CLINICAL CODING; DATA MINING; HUMANS; MODELS, THEORETICAL; MUSCULOSKELETAL DISEASES; QUALITY CONTROL; RISK FACTORS; SAMPLE SIZE; WORKERS' COMPENSATION;

EID: 84870725370     PISSN: 00224375     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jsr.2012.10.012     Document Type: Article

References (11)

1. Bureau of Labor Statistics [BLS] Nonfatal occupational injuries and illnesses requiring days away from work, 2010 Bureau of Labor Statistics News Release 2011 U.S. Department of Labor, Bureau of Labor Statistics Washington, DC
2. Bureau of Labor Statistics [BLS] http://www.bls.gov/iif/oiics-manual- 2010.pdf 2012 (accessed on February 16, 2012)
3. P. Domingos, and M. Pazzani On the optimality of the simple Bayesian classifier under zero-one loss Machine Learning 29 1997 103 130
4. D. Koller, and M. Sahami Hierarchically classifying documents using very few words In Proceedings of ICML-97 14th International Conference on Machine Learning 1997 (pp. 170-178). Nashville, US
5. M. Lehto, H. Marucci-Wellman, and H. Corns Bayesian method6s: a useful tool for classifying injury narratives into cause groups Injury Prevention 15 2009 259 265
6. Liberty Mutual Research Institute for Safety 2011 Liberty Mutual Workplace Safety Index 2011 Author Hopkinton, MA 2
7. H. Marucci-Wellman, M. Lehto, and H. Corns A combined Fuzzy and Naïve Bayesian strategy can be used to assign event codes to injury narratives Injury Prevention 17 2011 407 414
8. National Institute for Occupational Safety and Health (NIOSH) Office of the Director Centers for Disease Control and Prevention (CDC) The National Occupational Research Agenda (NORA) February 8, 2012 2012 (http://www.cdc.gov/ niosh/nora/ accessed on February 16, 2012)
9. F. Sebastiani Machine Learning in Automated Text Categorization ACM Computing Surveys 34 2002 1 47
10. C. van Rijsbergen A theoretical basis for the use of co-occurrence data in information retrieval Journal of Documentation 33 1977 106 119
11. H.M. Wellman, M.R. Lehto, and G.S. Sorock Computerized coding of injury narrative data from the National Health Interview Survey Accident; Analysis and Prevention 36 2004 165 171