Utility of inverse probability weighting in molecular pathological epidemiology
As one of causal inference methodologies, the inverse probability weighting (IPW) method has been utilized to address confounding and account for missing data when subjects with missing data cannot be included in a primary analysis. The transdisciplinary field of molecular pathological epidemiology (MPE) integrates molecular pathological and epidemiological methods, and takes advantages of improved understanding of pathogenesis to generate stronger biological evidence of causality and optimize strategies for precision medicine and prevention. Disease subtyping based on biomarker analysis of biospecimens is essential in MPE research. However, there are nearly always cases that lack subtype information due to the unavailability or insufficiency of biospecimens. To address this missing subtype data issue, we incorporated inverse probability weights into Cox proportional cause-specific hazards regression. The weight was inverse of the probability of biomarker data availability estimated based on a model for biomarker data availability status. The strategy was illustrated in two example studies; each assessed alcohol intake or family history of colorectal cancer in relation to the risk of developing colorectal carcinoma subtypes classified by tumor microsatellite instability (MSI) status, using a prospective cohort study, the Nurses’ Health Study. Logistic regression was used to estimate the probability of MSI data availability for each cancer case with covariates of clinical features and family history of colorectal cancer. This application of IPW can reduce selection bias caused by nonrandom variation in biospecimen data availability. The integration of causal inference methods into the MPE approach will likely have substantial potentials to advance the field of epidemiology.
KeywordsEtiologic heterogeneity Marginal structural model Missing at random Neoplasm Unique disease principle Selection bias
Area under receiver-operating characteristic curve
Complete case analysis
Directed acyclic graph
Inverse probability weighting
Missing at random
Mean metabolic equivalent task score
Missing completely at random
Molecular pathological epidemiology
Nurses’ Health Study
Receiver-operating characteristic curve
We would like to thank the participants and staff of the Nurses’ Health Study for their valuable contributions as well as the following state cancer registries for their help: AL, AZ, AR, CA, CO, CT, DE, FL, GA, ID, IL, IN, IA, KY, LA, ME, MD, MA, MI, NE, NH, NJ, NY, NC, ND, OH, OK, OR, PA, RI, SC, TN, TX, VA, WA, WY. The authors assume full responsibility for analyses and interpretation of these data.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflicts of interest.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed consent was obtained from all individual participants included in the study.
- 1.Ogino S, Lochhead P, Chan AT, Nishihara R, Cho E, Wolpin BM, Meyerhardt JA, Meissner A, Schernhammer ES, Fuchs CS, Giovannucci E. Molecular pathological epidemiology of epigenetics: emerging integrative science to analyze environment, host, and disease. Mod Pathol. 2013;26(4):465–84.CrossRefPubMedPubMedCentralGoogle Scholar
- 2.Ogino S, Nishihara R, VanderWeele TJ, Wang M, Nishi A, Lochhead P, Qian ZR, Zhang X, Wu K, Nan H, Yoshida K, Milner DA Jr, Chan AT, Field AE, Camargo CA Jr, Williams MA, Giovannucci EL. Review article: the role of molecular pathological epidemiology in the study of neoplastic and non-neoplastic diseases in the era of precision medicine. Epidemiology. 2016;27(4):602–11.CrossRefPubMedPubMedCentralGoogle Scholar
- 13.Liao X, Lochhead P, Nishihara R, Morikawa T, Kuchiba A, Yamauchi M, Imamura Y, Qian ZR, Baba Y, Shima K, Sun R, Nosho K, Meyerhardt JA, Giovannucci E, Fuchs CS, Chan AT, Ogino S. Aspirin use, tumor PIK3CA mutation, and colorectal-cancer survival. N Engl J Med. 2012;367(17):1596–606.CrossRefPubMedPubMedCentralGoogle Scholar
- 14.Nishihara R, Lochhead P, Kuchiba A, Jung S, Yamauchi M, Liao X, Imamura Y, Qian ZR, Morikawa T, Wang M, Spiegelman D, Cho E, Giovannucci E, Fuchs CS, Chan AT, Ogino S. Aspirin use and risk of colorectal cancer according to BRAF mutation status. JAMA. 2013;309(24):2563–71.CrossRefPubMedPubMedCentralGoogle Scholar
- 16.Cao Y, Nishihara R, Qian ZR, Song M, Mima K, Inamura K, Nowak JA, Drew DA, Lochhead P, Nosho K, Morikawa T, Zhang X, Wu K, Wang M, Garrett WS, Giovannucci EL, Fuchs CS, Chan AT, Ogino S. Regular aspirin use associates with lower risk of colorectal cancers with low numbers of tumor-infiltrating lymphocytes. Gastroenterology. 2016;151(5):879–92.CrossRefPubMedPubMedCentralGoogle Scholar
- 21.Graff RE, Pettersson A, Lis RT, Ahearn TU, Markt SC, Wilson KM, Rider JR, Fiorentino M, Finn S, Kenfield SA, Loda M, Giovannucci EL, Rosner B, Mucci LA. Dietary lycopene intake and risk of prostate cancer defined by ERG protein expression. Am J Clin Nutr. 2016;103(3):851–60.CrossRefPubMedPubMedCentralGoogle Scholar
- 22.Cox DR. Regression models and life-tables. J R Stat Soc Ser B (Methodological). 1972;34(2):187–220.Google Scholar
- 27.Lochhead P, Kuchiba A, Imamura Y, Liao X, Yamauchi M, Nishihara R, Qian ZR, Morikawa T, Shen J, Meyerhardt JA, Fuchs CS, Ogino S. Microsatellite instability and BRAF mutation testing in colorectal cancer prognostication. J Natl Cancer Inst. 2013;105(15):1151–6.CrossRefPubMedPubMedCentralGoogle Scholar
- 28.Hernán MA, Robins JM. Causal survival analysis. In: Causal inference. Boca Raton: Chapman & Hall/CRC, forthcoming; 2018. p. 69–78. https://www.hsph.harvard.edu/miguel-hernan/causal-inference-book/.
- 32.Ogino S, Nishihara R, Lochhead P, Imamura Y, Kuchiba A, Morikawa T, Yamauchi M, Liao X, Qian ZR, Sun R, Sato K, Kirkner GJ, Wang M, Spiegelman D, Meyerhardt JA, Schernhammer ES, Chan AT, Giovannucci E, Fuchs CS. Prospective study of family history and colorectal cancer risk by tumor LINE-1 methylation level. J Natl Cancer Inst. 2013;105(2):130–40.CrossRefPubMedGoogle Scholar
- 33.Song M, Nishihara R, Wu K, Qian ZR, Kim SA, Sukawa Y, Mima K, Inamura K, Masuda A, Yang J, Fuchs CS, Giovannucci EL, Ogino S, Chan AT. Marine omega-3 polyunsaturated fatty acids and risk of colorectal cancer according to microsatellite instability. J Natl Cancer Inst. 2015;107(4):djv007.CrossRefPubMedPubMedCentralGoogle Scholar
- 37.Ogino S, Campbell PT, Nishihara R, Phipps AI, Beck AH, Sherman ME, Chan AT, Troester MA, Bass AJ, Fitzgerald KC, Irizarry RA, Kelsey KT, Nan H, Peters U, Poole EM, Qian ZR, Tamimi RM, Tchetgen Tchetgen EJ, Tworoger SS, Zhang X, Giovannucci EL, van den Brandt PA, Rosner BA, Wang M, Chatterjee N, Begg CB. Proceedings of the second international molecular pathological epidemiology (MPE) meeting. Cancer Causes Control. 2015;26(7):959–72.CrossRefPubMedPubMedCentralGoogle Scholar
- 38.Campbell PT, Rebbeck TR, Nishihara R, Beck AH, Begg CB, Bogdanov AA, Cao Y, Coleman HG, Freeman GJ, Heng YJ, Huttenhower C, Irizarry RA, Kip NS, Michor F, Nevo D, Peters U, Phipps AI, Poole EM, Qian ZR, Quackenbush J, Robins H, Rogan PK, Slattery ML, Smith-Warner SA, Song M, VanderWeele TJ, Xia D, Zabor EC, Zhang X, Wang M, Ogino S. Proceedings of the third international molecular pathological epidemiology (MPE) meeting. Cancer Causes Control. 2017;28(2):167–76.CrossRefPubMedGoogle Scholar
- 42.Bishehsari F, Mahdavinia M, Vacca M, Malekzadeh R, Mariani-Costantini R. Epidemiological transition of colorectal cancer in developing countries: environmental factors, molecular pathways, and opportunities for prevention. World J Gastroenterol. 2014;20(20):6055–72.CrossRefPubMedPubMedCentralGoogle Scholar
- 47.Kuroiwa-Trzmielina J, Wang F, Rapkins RW, Rapkins RW, Ward RL, Buchanan DD, Win AK, Clendenning M, Rosty C, Southey MC, Winship IM, Hopper JL, Jenkins MA, Olivier J, Hawkins NJ, Hitchins MP. SNP rs16906252C > T is an expression and methylation quantitative trait locus associated with an increased risk of developing MGMT-methylated colorectal cancer. Clin Cancer Res. 2016;22(24):6266–77.CrossRefPubMedPubMedCentralGoogle Scholar
- 50.Campbell PT, Newton CC, Newcomb PA, Phipps AI, Ahnen DJ, Baron JA, Buchanan DD, Casey G, Cleary SP, Cotterchio M, Farris AB, Figueiredo JC, Gallinger S, Green RC, Haile RW, Hopper JL, Jenkins MA, Le Marchand L, Makar KW, McLaughlin JR, Potter JD, Renehan AG, Sinicrope FA, Thibodeau SN, Ulrich CM, Win AK, Lindor NM, Limburg PJ. Association between body mass index and mortality for colorectal cancer survivors: overall and by tumor molecular phenotype. Cancer Epidemiol Biomark Prev. 2015;24(8):1229–38.CrossRefGoogle Scholar
- 51.Gray RT, Loughrey MB, Bankhead P, Cardwell CR, McQuaid S, O’Neill RF, Arthur K, Bingham V, McGready C, Gavin AT, James JA, Hamilton PW, Salto-Tellez M, Murray LJ, Coleman HG. Statin use, candidate mevalonate pathway biomarkers, and colon cancer survival in a population-based cohort study. Br J Cancer. 2017;116(12):1652–9.CrossRefPubMedGoogle Scholar
- 53.Begg CB, Seshan VE, Zabor EC, Furberg H, Arora A, Shen R, Maranchie JK, Nielsen ME, Rathmell WK, Signoretti S, Tamboli P, Karam JA, Choueiri TK, Hakimi AA, Hsieh JJ. Genomic investigation of etiologic heterogeneity: methodologic challenges. BMC Med Res Methodol. 2014;14:138.CrossRefPubMedPubMedCentralGoogle Scholar
- 57.Inamura K, Song M, Jung S, Nishihara R, Yamauchi M, Lochhead P, Qian ZR, Kim SA, Mima K, Sukawa Y, Masuda A, Imamura Y, Zhang X, Pollak MN, Mantzoros CS, Harris CC, Giovannucci E, Fuchs CS, Cho E, Chan AT, Wu K, Ogino S. Prediagnosis plasma adiponectin in relation to colorectal cancer risk according to KRAS mutation status. J Natl Cancer Inst. 2016;108(4):djv363.CrossRefPubMedGoogle Scholar