Causal diagrams in systems epidemiology

Emerging Themes in Epidemiology

Paolo Vineis²  Marc Chadeau-Hyam²  Manoj Gambhir¹  Michael Joffe² 

[1] Department of Infectious Disease Epidemiology, Imperial College London, London, UK;Department of Epidemiology and Biostatistics, Imperial College London, London, UK

关键词: Feedback;    Change models;    Instrumental variables;    Web of causation;    Infectious disease epidemiology models;    Diagrammatic methods;    DAGs;    Causation;    Epidemiological methodology;   

Others  :  804010
DOI  :  10.1186/1742-7622-9-1

 received in 2011-08-06, accepted in 2012-03-19,  发布年份 2012

【 摘 要 】

Methods of diagrammatic modelling have been greatly developed in the past two decades. Outside the context of infectious diseases, systematic use of diagrams in epidemiology has been mainly confined to the analysis of a single link: that between a disease outcome and its proximal determinant(s). Transmitted causes ("causes of causes") tend not to be systematically analysed.

The infectious disease epidemiology modelling tradition models the human population in its environment, typically with the exposure-health relationship and the determinants of exposure being considered at individual and group/ecological levels, respectively. Some properties of the resulting systems are quite general, and are seen in unrelated contexts such as biochemical pathways. Confining analysis to a single link misses the opportunity to discover such properties.

The structure of a causal diagram is derived from knowledge about how the world works, as well as from statistical evidence. A single diagram can be used to characterise a whole research area, not just a single analysis - although this depends on the degree of consistency of the causal relationships between different populations - and can therefore be used to integrate multiple datasets.

Additional advantages of system-wide models include: the use of instrumental variables - now emerging as an important technique in epidemiology in the context of mendelian randomisation, but under-used in the exploitation of "natural experiments"; the explicit use of change models, which have advantages with respect to inferring causation; and in the detection and elucidation of feedback.

【 授权许可】

   
2012 Joffe et al; licensee BioMed Central Ltd.

【 图 表 】

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 1.

Figure 9.

Figure 10.

Figure 11.

Figure 2.

Figure 13.

Figure 14.

【 参考文献 】

• [1]Breslow NE: Are statistical contributions to medicine undervalued? Biometrics 2003, 59:1-8.
• [2]Epstein P: Changing planet, changing health. University of California Press; 2011.
• [3]Pearl J: Causality: models, reasoning and inference. New York: Cambridge University Press; 2000.
• [4]Pearl J: Causal inference in the health sciences: a conceptual introduction. Health services and outcomes research methodology 2002, 2:189-220.
• [5]Joffe M: Causality and evidence discovery in epidemiology. In Explanation, Prediction, and Confirmation. New Trends and Old Ones Reconsidered. Edited by Dieks D, Wenceslao JG, Hartmann S, Uebel T, Weber M. Springer; 2011.
• [6]Joffe M: The gap between evidence discovery and actual causal relationships. Preventive Medicine 2011, 53:246-49.
• [7]Greenland S, Pearl J, Robins JM: Causal diagrams for epidemiologic research. Epidemiol 1999, 10:37-48.
• [8]Robins JM: Data, design, and background knowledge in etiologic inference. Epidemiology 2001, 11:313-20.
• [9]Lauritzen SL, Richardson TS: Chain graph models and their causal interpretations. J R Statist Soc B 2002, 64:321-61.
• [10]Maldonado G, Greenland S: Estimating causal effects. Int J Epidemiol 2002, 31:422-29.
• [11]Hernán MA, Hernández-Díaz S, Werler MM, Mitchell AA: Causal knowledge as a prerequisite for confounding evaluation: an application to birth defects epidemiology. Am J Epidemiol 2002, 155:176-84.
• [12]Hernán MA, Hernández-Díaz S, Robins JM: A structural approach to selection bias. Epidemiol 2004, 15:615-25.
• [13]Howards PP, Schisterman EF, Heagerty PJ: Potential confounding by exposure history and prior outcomes - an example from perinatal epidemiology. Epidemiology 2007, 18:544-51.
• [14]Glymour MM, Greenland S: Causal diagrams. In Modern epidemiology. Edited by Rothman KJ, Greenland S, Lash TL. Philadelphia: Wolters Kluwer/Lippincott Williams & Wilkins; 2008.
• [15]VanderWeele TJ, Hernán MA, Robins JM: Causal directed acyclic graphs and the direction of unmeasured confounding bias. Epidemiol 2008, 19:720-28.
• [16]Hogan JW: Bringing causal models into the mainstream. Epidemiology 2009, 20:431-32.
• [17]Dawid AP: Beware of the DAG. JMLR: workshop and conference proceedings 2009, 6:59-86. http://jmlr.csail.mit.edu/proceedings/papers/v6/dawid10a/dawid10a.pdf webcite [accessed 1 February 2012]
• [18]Spirtes P, Glymour C, Scheines R: Causation, prediction and search. 2nd edition. New York: Springer-Verlag;
• [19]Wright S: The method of path coefficients. Annals of Mathematical Statistics 1934, 5:161-215.
• [20]Kennedy P: A guide to econometrics. 4th edition. Oxford: Blackwell Publishers Ltd; 1998.
• [21]Anderson RM, May RM: Infectious diseases of humans: dynamics and control. Oxford: Oxford University Press; 1992.
• [22]Sterman JD: Business dynamics. Boston: Irwin McGraw-Hill; 2000.
• [23]von Bertallanfy L: General system theory. New York: George Braziller; 1968.
• [24]Ross R: The prevention of malaria. New York: E.P. Dutton & company; 1910.
• [25]Isham V: Stochastic Models for Epidemics with Special Reference to AIDS. Ann Appl Probab 1993, 3:1-27.
• [26]Garnett GP, Anderson RM: Balancing sexual partnerships in an age and activity stratified model of HIV transmission in heterosexual populations. IMA J Math Appl Med Biol 1994, 11:161-92.
• [27]Baussano I, Garnett G, Segnan N, Ronco G, Vineis P: Modelling patterns of clearance of HPV-16 infection and vaccination efficacy. Vaccine 2011, 29:1270-77.
• [28]Chadeau-Hyam M, Guihenneuc-Jouyaux C, Cousens SN, et al.: An application of hidden Markov models to the French variant Creutzfeldt-Jakob disease epidemic. J Roy Stat Soc C (App Stat) 2010, 59:839-53.
• [29]Vineis P, Chadeau-Hyam M: Integrating biomarkers into molecular epidemiological studies. Current Opinion in Oncology 2011, 23:100-05.
• [30]Wild CP: Complementing the genome with an 'exposome': The outstanding challenge of environmental exposure measurement in molecular epidemiology. Cancer Epidemiol Biomarkers Prev 2005, 14:1847-50.
• [31]Rappaport SM, Smith MT: Environment and disease risks. Science 2010, 330:460-41.
• [32]Briggs DJ: A framework for integrated environmental health impact assessment of systemic risks. Environ Health 2008, 7:61. BioMed Central Full Text
• [33]Rose G: The strategy of preventive medicine. Oxford: Oxford University Press; 1992.
• [34]VanderWeele TJ, Robins JM: Four types of effect modification: a classification based on directed acyclic graphs. Epidemiol 2007, 18:561-68.
• [35]Weinberg CR: Can DAGs clarify effect modification? Epidemiol 2007, 18:569-72.
• [36]VanderWeele TJ: On the distinction between interaction and effect modification. Epidemiol 2009, 20:863-71.
• [37]Case A, Paxson C: The long reach of childhood health and circumstance: evidence from the Whitehall II Study. Economic Journal 2011, 121:F183-F204.
• [38]MacMahon B, Pugh TF: Epidemiology principles and methods. Boston: Little Brown and Co; 1970.
• [39]Krieger N: Epidemiology and the web of causation: has anyone seen the spider? Soc Sci Med 1994, 39:887-903.
• [40]Joffe M, Mindell J: Complex causal process diagrams for analyzing the health impacts of policy interventions. Am J Public Health 2006, 96:473-79.
• [41]Joffe M: The need for strategic health assessment. Eur J Public Health 2008, 18:439-40.
• [42]Joffe M: The role of strategic health impact assessment in sustainable development and green economics. International Journal of Green Economics 2010, 4:1-16.
• [43]Sacerdote C, Ricceri F, Rolandsson O, Baldi I, Chirlaque MD, Feskens E, et al.: Education level is a strong predictor of the risk of type 2 diabetes. The EPIC-InterAct Study. Int J Epidemiol, in revision
• [44]Rehfuess EA, Best N, Briggs DJ, Joffe M: Use of causal diagrams in systems epidemiology: elucidating the inter-relationships between determinants of acute lower respiratory infections among children in sub-Saharan Africa. Submitted to Emerging Themes in Epidmiology
• [45]de Nazelle A, Nieuwenhuijsen MJ, Antó JM, Brauer M, Briggs DJ, Braun-Fahrlander C, et al.: Improving health through policies that promote active travel: a review of evidence to support integrated health impact assessment. Environment Internationaldoi: 10.1016/j.envint.2011.02.003
• [46]Best N, Joffe M, Key J, Keiding N, Jensen TK: Social variation in biological fertility. (manuscript in preparation).
• [47]Guihenneuc-Jouyaux C, Richardson S, Longini IM Jr: Modeling markers of disease progression by a hidden Markov process: application to characterizing CD4 cell decline. Biometrics 2000, 56:733-41.
• [48]Best N, Jackson C, Richardson S: Modelling complexity in health and social sciences: Bayesian graphical models as a tool for combining multiple sources of information. In Proceedings of the 3 rd ASC International Conference on Survey Research Methods Edited by Banks R, Cornelius R, Evans S, Manners T. 2005.
• [49]Smith R: Assessment and validation of exposure to disinfection by-products during pregnancy, in an epidemiological study examining associated risk of adverse fetal growth outcomes. PhD thesis. Imperial College London, Department of Epidemiology and Biostatistics; 2011.
• [50]Greenland S: An introduction to instrumental variables for epidemiologists. Int J Epidemiol 2000, 29:722-29.
• [51]Davey Smith G, Ebrahim S: What can mendelian randomisation tell us about modifiable behavioural and environmental exposures? BMJ 2005, 330:1076-79.
• [52]Chen L, Davey Smith G, Harbord RM, Lewis SJ: Alcohol intake and blood pressure: a systematic review implementing a Mendelian randomization approach. PLoS Medicine 2008, 5:e52:0461-71. http://www.plosmedicine.org/article/info:doi/10.1371/journal.pmed.0050052 webcite [accessed 1 February 2012]
• [53]Allin KH, Nordestgaard BG, Zacho J, Tybjaerg-Hansen A, Bojesen SE: C-reactive protein and the risk of cancer: a mendelian randomization study. J Natl Cancer Inst 2010, 102:202-06.
• [54]Marott SC, Nordestgaard BG, Zacho J, Friberg J, Jensen GB, Tybjaerg-Hansen A, Benn M: Does elevated C-reactive protein increase atrial fibrillation risk? A Mendelian randomization of 47,000 individuals from the general population. J Am Coll Cardiol 2010, 56:789-95.
• [55]Angrist J, Evans W: Children and their parents' labor supply: Evidence from exogenous variation in family size. American Economic Review 1998, 88:450-77.
• [56]Clancy L, Goodman P, Sinclair H, Dockery DW: Effect of air-pollution control on death rates in Dublin, Ireland: an intervention study. Lancet 2002, 360:1210-14.
• [57]Wilkinson R, Pickett K: The Spirit Level: why equality is better for everyone. London: Penguin; 2010.
• [58]Hill AB: The environment and disease: association or causation? Proc Royal Soc Med 1965, 58:295-300.
• [59]Joffe M, Mindell J: A framework for the evidence base to support Health Impact Assessment. J Epidemiol Community Health 2002, 56:132-38.
• [60]Adams J: Risk. London: UCL Press; 1995.
• [61]Galea S, Riddle M, Kaplan GA: Causal thinking and complex system approaches in epidemiology. Int J Epidemiol 2010, 39:97-106.
• [62]Vensim. Ventana Systems, Inc [http://www.vensim.com/] webcite [accessed 1 February 2012]
• [63]Forrester JW: Counterintuitive behaviour of social systems. In Collected papers of Jay W Forrester: collectio. Volume 1970. Cambridge, MA: Wright-Allen Press; 1975::211-44.
• [64]Lane DC: The power of the bond between cause and effect. System Dynamics Review 2007, 23:95-118.
• [65]Joffe M: Health, livelihoods, and nutrition in low-income rural systems. Food Nut Bull 2007, 28 (suppl.):S227-36.
• [66]Elgar G, Vavouri T: Tuning in to the signals: noncoding sequence conservation in vertebrate genomes. Trends Genet 2008, 24:344-52.
• [67]di Bernardo D, Thompson MJ, Gardner TS, Chobot SE, Eastwood EI, Wojtovich AP, Elliott SJ, Schaus SE, Collins JJ: Chemogenomic profiling on a genome-wide scale using reverse-engineered gene networks. Nature Biotechnology 2005, 23:377-83.