Safety and Health at Work

Occupational Safety and Health Research Institute, Korea Occupational Safety and Health Agency (산업안전보건연구원)
권호 표지
DOI QR코드

DOI QR Code

Decision Tree of Occupational Lung Cancer Using Classification and Regression Analysis

  • Kim, Tae-Woo (Occupational Safety and Health Research Institute, Korea Occupational Safety and Health Agency) ;
  • Koh, Dong-Hee (Occupational Safety and Health Research Institute, Korea Occupational Safety and Health Agency) ;
  • Park, Chung-Yill (Department of Preventive Medicine, College of Medicine, The Catholic University of Korea)
  • Received : 2010.04.29
  • Accepted : 2010.09.16
  • Published : 2010.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

Objectives: Determining the work-relatedness of lung cancer developed through occupational exposures is very difficult. Aims of the present study are to develop a decision tree of occupational lung cancer. Methods: 153 cases of lung cancer surveyed by the Occupational Safety and Health Research Institute (OSHRI) from 1992-2007 were included. The target variable was whether the case was approved as work-related lung cancer, and independent variables were age, sex, pack-years of smoking, histological type, type of industry, latency, working period and exposure material in the workplace. The Classification and Regression Test (CART) model was used in searching for predictors of occupational lung cancer. Results: In the CART model, the best predictor was exposure to known lung carcinogens. The second best predictor was 8.6 years or higher latency and the third best predictor was smoking history of less than 11.25 pack-years. The CART model must be used sparingly in deciding the work-relatedness of lung cancer because it is not absolute. Conclusion: We found that exposure to lung carcinogens, latency and smoking history were predictive factors of approval for occupational lung cancer. Further studies for work-relatedness of occupational disease are needed.

Keywords

References

  1. Alberg AJ, Ford JG, Samet JM. American College of Chest Physicians. Epidemiology of lung cancer: ACCP evidencebased clinical practice guidelines. 2nd ed. Chest 2007;132:29S-55S. https://doi.org/10.1378/chest.07-1347
  2. Ferlay J, Autier P, Boniol M, Heanue M, Colombet M, Boyle P.Estimates of the cancer incidence and mortality in Europe in2006. Ann Oncol 2007;18:581-92.
  3. Doll R, Peto R. The causes of cancer: quantitative estimatesof avoidable risks of cancer in the United States today. J NatlCancer Inst 1981;66:1191-308.
  4. Driscoll T, Nelson DI, Steenland K, Leigh J, Concha-BarrientosM, Fingerhut M, Pruss-Ustun A. The global burdenof disease due to occupational carcinogens. Am J Ind Med2005;48:419-31. https://doi.org/10.1002/ajim.20209
  5. Steenland K, Burnett C, Lalich N, Ward E, Hurrell J. Dyingfor work: the magnitude of US mortality from selectedcauses of death associated with occupation. Am J Ind Med2003;43:461-82. https://doi.org/10.1002/ajim.10216
  6. Peto R, Lopez AD, Boreham J, Thun M, Heath C Jr. Mortalityfrom smoking in developed countries 1950-2000: indirectestimates from national vital statistics. Oxford (UK): OxfordUniversity Press; 1994.
  7. Boffetta P, Kogevinas M. Introduction: epidemiologic researchand prevention of occupational cancer in Europe. EnvironHealth Perspect 1999;107:229-31. https://doi.org/10.1289/ehp.99107s2229
  8. Fingerhut M, Nelson DI, Driscoll T, Concha-Barrientos M,Steenland K, Punnett L, Pruss-Ustun A, Leigh J, Corvalan C,Eijkemans G, Takala J. The contribution of occupational risksto the global burden of disease: summary and next steps. MedLav 2006;97:313-21.
  9. Kim JI, Kim JH, Kang D, Kim JW, Kim JE, Ahn JH, LeeCH, Lee HJ, Kang JU, Son JK, Sul JK, Kim YK, Jung KY,Kim JY. Epidemiologic characteristics of occupational lungcancer in the Busan area. Korean J Occup Environ Med2006;18:53-8.
  10. Rosenstock L, Cullen MR, Brodkin CA, Redlich CA. Textbookof clinical occupational and environmental medicine.2nd ed. Philadelphia (PA): Elsevier Saunders Pub; 2005. p.727-41.
  11. Steenland K, Sanderson W. Lung cancer among industrialsand workers exposed to crystalline silica. Am J Epidemiol2001;153:695-703. https://doi.org/10.1093/aje/153.7.695
  12. Grimsrud TK, Berge SR, Martinsen JI, Andersen A. Lungcancer incidence among Norwegian nickel-refinery workers1953-2000. J Environ Monit 2003;5:190-7. https://doi.org/10.1039/b211722n
  13. Verougstraete V, Lison D, Hotz P. Cadmium, lung and prostatecancer: a systematic review of recent epidemiologicaldata. J Toxicol Environ Health B Crit Rev 2003;6:227-55. https://doi.org/10.1080/10937400306465
  14. Jarup L, Pershagen G, Wall S. Cumulative arsenic exposureand lung cancer in smelter workers: a dose-response study.Am J Ind Med 1989;15:31-41. https://doi.org/10.1002/ajim.4700150105
  15. Bjor O, Damber L, Edstrom C, Nilsson T. Long-term follow-upstudy of mortality and the incidence of cancer in a cohortof workers at a primary aluminum smelter in Sweden. ScandJ Work Environ Health 2008;34:463-70. https://doi.org/10.5271/sjweh.1293
  16. Smith GH, Williams FL, Lloyd OL. Respiratory cancerand air pollution from iron foundries in a Scottish town:an epidemiological and environmental study. Br J Ind Med1987;44:795-802.
  17. Kogevinas M, Sala M, Boffetta P, Kazerouni N, KromhoutH, Hoar-Zahm S. Cancer risk in the rubber industry: a reviewof the recent epidemiological evidence. Occup Environ Med1998;55:1-12. https://doi.org/10.1136/oem.55.1.1
  18. Wichmann HE. Diesel exhaust particles. Inhal Toxicol2007;19:241-4. https://doi.org/10.1080/08958370701498075
  19. IARC Monograph on the evaluation of the carcinogenic risksto humans. Volume 46 diesel and gasoline engine exhaustsand some nitroarenes. Lyon (France): International Agencyfor Research on Cancer (IARC); 1989. 458 p.
  20. Lewis RJ. An introduction to classification and regression tree(CART) analysis [Internet]. 2000 [cited 2010 Apr 12]. Availablefrom: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.95.4103&rep=rep1&type=pdf.
  21. Timofeev R. Classification and regression trees (cart) theoryand applications: Master Thesis. Berlin (Germany): HumboldtUniversity; 2004. p. 7-8.
  22. Breiman L, Friedman J, Olshen RA, Stone CJ. Classificationand regression trees. 1st ed. New York: Chapman & Hall;1998. p. 18-22.
  23. Steinberg D, Colla P. CART--classification and regressiontrees. 1st ed. San Diego (CA): Salford Systems; 1997. p. 180-1.
  24. IARC Monograph on the evaluation of the carcinogenicrisks to humans. Volume 81 man-made vitreous fibres. Lyon(France): International Agency for Research on Cancer; 2002.418 p.
  25. Berman DW, Crump KS. A meta-analysis of asbestos-relatedcancer risk that addresses fiber size and mineral type. Crit RevToxicol 2008;38:49-73. https://doi.org/10.1080/10408440802273156
  26. IARC Monograph on the evaluation of the carcinogenicrisks to humans. Volume 92 some non-heterocyclic polycyclicaromatic hydrocarbons and some related exposures. Lyon(France): International Agency for Research on Cancer; 2010.853 p.
  27. Cole P, Rodu B. Epidemiologic studies of chrome and cancermortality: a series of meta-analyses. Regul Toxicol Pharmacol2005;43:225-31. https://doi.org/10.1016/j.yrtph.2005.06.009
  28. Costantino JP, Redmond CK, Bearden A. Occupationallyrelated cancer risk among coke oven workers: 30 years offollow-up. J Occup Environ Med 1995;37:597-604. https://doi.org/10.1097/00043764-199505000-00009
  29. Hengstler JG, Bolm-Audorff U, Faldum A, Janssen K, ReifenrathM, Gotte W, Jung D, Mayer-Popken O, Fuchs J, Gebhard S, Bienfait HG, Schlink K, Dietrich C, Faust D, Epe B,Oesch F. Occupational exposure to heavy metals: DNA damageinduction and DNA repair inhibition prove co-exposuresto cadmium, cobalt and lead as more dangerous than hithertoexpected. Carcinogenesis 2003;24:63-73. https://doi.org/10.1093/carcin/24.1.63
  30. LaDou J. Current occupational and environmental medicine.4th ed. New York: McGrawHill Pub; 2007. p. 224-61.
  31. Scalable classification and regression tree construction [Internet].2007 [cited 2010 Apr 10]. Available from: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.86.413&rep=rep1&type=pdf.
  32. Spitz MR, Hong WK, Amos CI, Wu X, Schabath MB, DongQ, Shete S, Etzel CJ. A risk model for prediction of lung cancer.J Natl Cancer Inst 2007;99:715-26. https://doi.org/10.1093/jnci/djk153
  33. Cassidy A, Myles JP, van Tongeren M, Page RD, Liloglou T,Duffy SW, Field JK. The LLP risk model: an individual riskprediction model for lung cancer. Br J Cancer 2008;98:270-6. https://doi.org/10.1038/sj.bjc.6604158
  34. Etzel CJ, Kachroo S, Liu M, D'Amelio A, Dong Q, Cote ML,Wenzlaff AS, Hong WK, Greisinger AJ, Schwartz AG, SpitzMR. Development and validation of a lung cancer risk predictionmodel for African-Americans. Cancer Prev Res (Phila)2008;1:255-65. https://doi.org/10.1158/1940-6207.CAPR-08-0082
  35. Subramanian J, Govindan R. Lung cancer in never smokers:a review. J Clin Oncol 2007;25:561-70. https://doi.org/10.1200/JCO.2006.06.8015
  36. Brown T. Silica exposure, smoking, silicosis and lung cancer--complex interactions. Occup Med (Lond) 2009;59:89-95. https://doi.org/10.1093/occmed/kqn171
  37. Liddell FDK. The interaction of asbestos and smoking inlung cancer. Ann Occup Hyg 2001;45:341-56. https://doi.org/10.1016/S0003-4878(00)00060-0
  38. Cassidy A, 't Mannetje A, van Tongeren M, Field JK, ZaridzeD, Szeszenia-Dabrowska N, Rudnai P, Lissowska J, FabianovaE, Mates D, Bencko V, Foretova L, Janout V, Fevotte J,Fletcher T, Brennan P, Boffetta P. Occupational exposure tocrystalline silica and risk of lung cancer: a multicenter casecontrolstudy in Europe. Epidemiology 2007;18:36-43. https://doi.org/10.1097/01.ede.0000248515.28903.3c
  39. Hertz-Picciotto I, Smith AH, Holtzman D, Lipsett M, AlexeeffG. Synergism between occupational arsenic exposureand smoking in the induction of lung cancer. Epidemiology1992;3:23-31. https://doi.org/10.1097/00001648-199201000-00006
  40. Case BW. Asbestos, smoking, and lung cancer: interactionand attribution. Occup Environ Med 2006;63:507-8. https://doi.org/10.1136/oem.2006.027631

Cited by

  1. A novel crossover operator based on variable importance for evolutionary multi-objective optimization with tree representation vol.21, pp.1, 2015, https://doi.org/10.1007/s10732-014-9269-7
  2. in Switzerland and their suitability for age estimation vol.2018, pp.1, 2018, https://doi.org/10.2981/wlb.00432