Abstract
Ensemble approaches to statistical modelling combine multiple statistical methods to form a comprehensive analysis. They are of increasing interest for problems that involve diverse data sources, complex systems and subtle outcomes of interest. An example of such an ensemble approach is described in this chapter, in the context of a substantive case study that aimed to tease out factors affecting the age at onset of the neurodegenerative medical condition, Parkinsons Disease (PD), with a particular focus on the role of a particular potential risk factor, pesticide exposure.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
W. Dauer, S. Przedborski, Parkinson’s disease: mechanisms and models. Neuron 39, 889–909 (2003)
M.J. Farrer, Genetics of Parkinson disease: paradigm shifts and future prospects. Nat. Rev. Genet. 7, 306–318 (2006)
A.A. Hicks, H. Pétursson, T. Jonsson, H. Stefánsson, H.S. Johannsdottir, J. Sainz, M.L. Frigge, A. Kong, J.R. Gulcher, K. Stefansson, et al., A susceptibility gene for late-onset idiopathic Parkinson’s disease. Ann. Neurol. 52, 549–555 (2002)
E.R. Martin, W.K. Scott, M.A. Nance, et al., Association of single-nucleotide polymorphisms of the Tau gene with late-onset Parkinson’s disease. J. Am. Med. Assoc. 286, 2245–2250 (2001)
T.H. Hamza, et al., Common genetic variation in the HLA region is associated with late-onset sporadic Parkinson’s disease. Nat. Genet. 42, 781–785 (2010)
C.B. Lücking, A. Dürr, V. Bonifati, J. Vaughan, G. De Michele, T. Gasser, B.S. Harhangi, G. Meco, P. Denéfle, N.W. Wood, Association between early-onset Parkinson’s disease and mutations in the Parkin gene. New Engl. J. Med. 342, 1560–1567 (2000)
M. Periquet, M. Latouche, E. Lohmann, N. Rawal, G. De Michele, S. Ricard, H. Teive, V. Fraix, M. Vidailhet, D. Nicholl, Parkin mutations are frequent in patients with isolated early-onset Parkinsonism. Brain 126, 1271–1278 (2003)
S. Hague, E. Rogaeva, D. Hernandez, C. Gulick, A. Singleton, M. Hanson, J. Johnson, R. Weiser, M. Gallardo, B. Ravina, Early-onset Parkinson’s disease caused by a compound heterozygous DJ-1 mutation. Ann. Neurol. 54, 271–274 (2003)
V. Bonifati, P. Rizzu, M.J. van Baren, O. Schaap, G.J. Breedveld, E. Krieger, M.C. Dekker, F. Squitieri, P. Ibanez, M. Joosse, Mutations in the DJ-1 gene associated with autosomal recessive early-onset Parkinsonism. Science, 299, 256–259 (2003)
E.M. Valente, P.M. Abou-Sleiman, V. Caputo, M.M. Muqit, K. Harvey, S. Gispert, Z. Ali, D. Del Turco, A.R. Bentivoglio, D.G. Healy, Hereditary early-onset Parkinson’s disease caused by mutations in PINK1. Science 304, 1158–1160 (2004)
R.C. Duvoisin, R. Eldridge, A. Williams, J. Nutt, D. Calne, Twin study Of Parkinson disease. Neurology 31, 77–77 (1981)
C.D. Ward, R.C. Duvoisin, S.E. Ince, J.D. Nutt, R. Eldridge, D.B. Calne, Parkinson’s disease in 65 pairs of twins and in a set of quadruplets. Neurology 33, 815–815 (1983)
C. Marsden, Parkinson’s disease in twins. J. Neurol. Neurosurg. Psychiatry 50, 105–106 (1987)
R. Marttila, J. Kaprio, M. Koskenvuo, U. Rinne, Parkinson’s disease in a nationwide twin cohort. Neurology, 38, 1217–1217 (1988)
T. Zimmerman, M. Bhatt, D. Calne, R. Duvoisin, Parkinson’s disease in monozygotic twins: a follow-up. Neurology 41, 255 (1991)
P. Vieregge, K. Schiffke, H. Friedrich, B. Müller, H. Ludin, Parkinson’s disease in twins. Neurology 42, 1453–1453 (1992)
C. Tanner, R. Ottman, S. Goldman, et al., Parkinson disease in twins: an etiologic study. J. Am. Med. Assoc. 281, 341–346 (1999)
J.M. Gorell, E.L. Peterson, B.A. Rybicki, C.C. Johnson, Multiple risk factors for Parkinson’s disease. J. Neurol. Sci. 217, 169–174 (2004)
H. Checkoway, K. Powers, T. Smith-Weller, G.M. Franklin, W.T. Longstreth, P.D. Swanson, Parkinson’s disease risks associated with cigarette smoking, alcohol consumption, and caffeine intake. Am. J. Epidemiol. 155, 732–738 (2002)
H. Payami, K. Larsen, S. Bernard, J. Nutt, Increased risk of Parkinson’s disease in parents and siblings of patients. Ann. Neurol. 36, 659–661 (1994)
C.A. Taylor, M.H. Saint-Hilaire, L.A. Cupples, C.A. Thomas, A.E. Burchard, R.G. Feldman, R.H. Myers, Environmental, medical, and family history risk factors for Parkinson’s disease: a New England-based case control study. Am. J. Med. Genet. 88, 742–749 (1999)
J.A. Driver, G. Logroscino, J.M. Gaziano, T. Kurth, Incidence and remaining lifetime risk of Parkinson disease in advanced age. Neurology 72, 432–438 (2009)
M.A. Hernán, B. Takkouche, F. Caamaño Isorna, J.J. Gestal-Otero, A meta-analysis of coffee drinking, cigarette smoking, and the risk of Parkinson’s disease. Ann. Neurol. 52, 276–284 (2002)
A. Ascherio, S.M. Zhang, M.A. Hernán, I. Kawachi, G.A. Colditz, F.E. Speizer, W.C. Willett, Prospective study of caffeine consumption and risk of Parkinson’s disease in men and women. Ann. Neurol. 50, 56–63 (2001)
A.E. Lang, C.D. Marsden, J.A. Obeso, J.D. Parkes, Alcohol and Parkinson disease. Ann. Neurol. 12, 254–256 (1982)
M.A. Hernán, H. Chen, M.A. Schwarzschild, A. Ascherio, Alcohol consumption and the incidence of Parkinson’s disease. Ann. Neurol. 54, 170–175 (2003)
N. Palacios, X. Gao, E. O’Reilly, M. Schwarzschild, M.L. McCullough, T. Mayo, S.M. Gapstur, A.A. Ascherio, Alcohol and risk of Parkinson’s disease in a large, prospective cohort of men and women. Mov. Disord. 27, 980–987 (2012)
A. Ascherio, H. Chen, M.G. Weisskopf, E. O’Reilly, M.L. McCullough, E.E. Calle, M.A. Schwarzschild, M.J. Thun, Pesticide exposure and risk for Parkinson’s disease. Ann. Neurol. 60, 197–203 (2006)
J.R. Richardson, S.L. Shalat, B. Buckley, et al., Elevated serum pesticide levels and risk of Parkinson’s disease. Arch. Neurol. 66, 870–875 (2009)
A.F. Hernández, B. González-Alzaga, I. López-Flores, M. Lacasaña, Systematic reviews on neurodevelopmental and neurodegenerative disorders linked to pesticide exposure: methodological features and impact on risk assessment. Environ. Int. 92, 657–679 (2016)
M. Weisskopf, P. Knekt, E. O’Reilly, J. Lyytinen, A. Reunanen, F. Laden, L. Altshul, A. Ascherio, Persistent organochlorine pesticides in serum and risk of Parkinson disease. Neurology 74, 1055–1061 (2010)
S.M. Goldman, C.M. Tanner, D. Oakes, G.S. Bhudhikanok, A. Gupta, J.W. Langston, Head injury and Parkinson’s disease risk in twins. Ann. Neurol. 60, 65–72 (2006)
A. Hofman, H. Collette, A. Bartelds, Incidence and risk factors of Parkinson’s disease in The Netherlands. Neuroepidemiology 8, 296–299 (1989)
K. Rugbjerg, B. Ritz, L. Korbo, N. Martinussen, J.H. Olsen, Risk of Parkinson’s disease after hospital contact for head injury: population based case-control study. Br. Med. J. 337, a2494 (2008)
R.L. Levine, J.C. Jones, N. Bee, Stroke and Parkinson’s disease. Stroke 23, 839–842 (1992)
X. Gao, H. Chen, T.T. Fung, G. Logroscino, M.A. Schwarzschild, F.B. Hu, A. Ascherio, Prospective study of dietary pattern and risk of Parkinson disease. Am. J. Clin. Nutr. 86, 1486–1494 (2007)
A. Priyadarshi, S.A. Khuder, E.A. Schaub, S. Shrivastava, A meta-analysis of Parkinson’s disease and exposure to pesticides. Neurotoxicology 21, 435–440 (2000)
E.E. Ntzani, M. Chondrogiorgi, G. Ntritsos, E. Evangelou, I. Tzoulaki, Literature review on epidemiological studies linking exposure to pesticides and health effects. EFSA Supporting Publication (2013)
D.B. Hancock, E.R. Martin, J.M. Stajich, R. Jewett, M.A. Stacy, B.L. Scott, J.M. Vance, W.K. Scott, Smoking, caffeine, and nonsteroidal anti-inflammatory drugs in families with Parkinson disease. Arch. Neurol. 64, 576–580 (2007)
K.M. Powers, D.M. Kay, S.A. Factor, C.P. Zabetian, D.S. Higgins, A. Samii, J.G. Nutt, A. Griffith, B. Leis, J.W. Roberts, E.D. Martinez, J.S. Montimurro, H. Checkoway, H. Payami, Combined effects of smoking, coffee, and NSAIDs on Parkinson’s disease risk. Move. Disord. 23, 88–95 (2008)
A.J. Lees, J. Hardy, T. Revesz, Parkinson’s disease. Lancet 373, 2055–2066 (2009)
A.J. Noyce, A.J. Lees, A.-E. Schrag, The prediagnostic phase of Parkinson’s disease. J. Neurol. Neurosurg. Psychiatry 87, 871-878 (2016). jnnp–2015
A. Elbaz, J. Clavel, P.J. Rathouz, F. Moisan, J.-P. Galanaud, B. Delemotte, A. Alperovitch, C. Tzourio, Professional exposure to pesticides and Parkinson disease. Ann. Neurol. 66, 494–504 (2009)
M. Stern, E. Dulaney, S.B. Gruber, L. Golbe, M. Bergen, H. Hurtig, S. Gollomp, P. Stolley, The epidemiology of Parkinson’s disease: a case-control study of young-onset and old-onset patients. Arch. Neurol. 48, 903–907 (1991)
C. Tsai, S. Lo, L. See, H. Chen, R. Chen, Y. Weng, F. Chang, C. Lu, Environmental risk factors of young onset Parkinson’s disease: a case-control study. Clin. Neurol. Neurosurg. 104 (2002), 328–333
N.E. Maher, et al., Epidemiologic study of 203 sibling pairs with Parkinson’s disease: the GenePD study. Neurology 58, 79–84 (2002)
J.B. Wilk, T.L. Lash, Risk factor studies of age-at-onset in a sample ascertained for Parkinson disease affected sibling pairs: a cautionary tale. Emerg. Themes Epidemiol. 4, 1 (2007)
G. Pezzoli, M. Canesi, A. Antonini, A. Righini, L. Perbellini, M. Barichella, C. Mariani, F. Tenconi, S. Tesei, A. Zecchinelli, K. Leenders, Hydrocarbon exposure and Parkinson’s disease. Neurology 55, 667–673 (2000)
J. Molina, F.J. Jiménez-Jiménez, J. Navarro, E. Ruiz, J. Arenas, F. Cabrera-Valdivia, A. Vázquez, P. Fernández-Calle, L. Ayuso-Peralta, M. Rabasa, et al., Plasma levels of nitrates in patients with Parkinson’s disease. J. Neurol. Sci. 127, 87–89 (1994)
J. Sanyal, B.N. Sarkar, T.K. Banerjee, S.C. Mukherjee, B.C. Ray, V.R. Rao, Plasma level of nitrates in patients with Parkinson’s disease in West Bengal. Neurol. Asia 15, 55–59 (2010)
G. Bartzokis, T.A. Tishler, I.S. Shin, P.H. Lu, J.L. Cummings, Brain ferritin iron as a risk factor for age at onset in neurodegenerative diseases. Ann. N. Y. Acad. Sci. 1012, 224–36 (2004)
K. Marder, G. Levy, E.D. Louis, H. Mejia-Santana, L. Cote, H. Andrews, J. Harris, C. Waters, B. Ford, S. Frucht, et al., Familial aggregation of early- and late-onset Parkinson’s disease. Ann. Neurol. 54, 507–513 (2003)
B.A. Rybicki, C.C. Johnson, E.L. Peterson, G.X. Kortsha, J.M. Gorell, A family history of Parkinson’s disease and its effect on other PD risk factors. Neuroepidemiology 18, 270–278 (1999)
G.T. Sutherland, G.M. Halliday, P.A. Silburn, F.L. Mastaglia, D.B. Rowe, R.S. Boyle, J.D. O’Sullivan, T. Ly, S.D. Wilton, G.D. Mellick, Do polymorphisms in the familial Parkinsonism genes contribute to risk for sporadic Parkinson’s disease? Move. Disord. 24, 833–838 (2009)
A. Thomas, L.-M.L. Toms, F.A. Harden, P. Hobson, N.M. White, K.L. Mengersen, J.F. Mueller, Concentrations of organochlorine pesticides in pooled human serum by age and gender. Environ. Res. 154, 10–18 (2017)
M. Borenstein, L.V. Hedges, J. Higgins, H.R. Rothstein, Introduction To Meta-analysis (Wiley Online Library, Hoboken, 2009)
J. Pearl, Bayesian networks: a model of self-activated memory for evidential reasoning, in Proceedings of the 7th Conference of the Cognitive Science Society, University of California, Irvine, CA, USA, pp. 15–17 (1985)
M.J. Druzdzel, F.J. Díez, Combining knowledge from different sources in causal probabilistic models. J. Mach. Learn. Res. 4, 295–316 (2003)
M.J. Druzdzel, GeNIe: a development environment for graphical decision-analytic models, in Proceedings of the AMIA Symposium (1999), p. 1206
H.B. Ferraz, L.A. Andrade, V. Tumas, L.C. Calia, V. Borges, Rural or urban living and Parkinson’s disease. Arquivos de neuro-psiquiatria 54, 37–41 (1996)
J. De Reuck, M. De Weweire, G. Van Maele, P. Santens, Comparison of age of onset and development of motor complications between smokers and non-smokers in Parkinson’s disease. J. Neurol. Sci. 231, 35–39 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix: Supporting Information
Appendix: Supporting Information
Let Y represent early age at onset and X represent the presence of one or more risk factors, which include smoking, alcohol, head injury or family history. Let X c represent the absence of risk factors and define E as,
where E can be a lifestyle or medical history effect conducive to an early age at onset, such that when E represents lifestyle, X = {X 1 = smoking, X 2 = alcohol}. When E represents medical history, X = {X 1 = head injury, X 2 = family history}.
We wish to quantify the conditional probabilities P(E|X) and the data available is in the form of ORs and marginal probabilities as derived from the literature and from meta-analyses. These ORs take the following form,
Equation 11.10 can be rearranged to express OR(E|X) entirely in terms of P(E|X) and its marginal probabilities,
We solve Eq. 11.11 for P(E|X), which involves solving for the roots of the quadratic on P(E|X), to obtain the following expression for the CPT,
In the presence of more than one risk factor, due to the absence of data covering different combinations of risk factors, we assume conditional independence. For example, to estimate the lifestyle effects CPT P(E|X 1, X 2), assuming smoking (X 1) and alcohol (X 2) are conditionally independent, the CPT is quantified as,
where P(E|X 1) and P(E|X 2) can be evaluated as per Eq. 11.12. From Eq. 11.9 where we have the presence of atleast one risk factor, P(E) is,
In the QPP data source, we derived an OR for early onset given pesticide exposure using logistic regression. We assume this is approximately equal to the OR for early onset given OCP, OR(Y |OCP) where OCP represents exposure to OCPs. Thus, we apply Eq. 11.12 to estimate P(Y |E OCP) where E OCP represents the effect of OCP exposure conducive to an early age at onset.
To estimate the conditional probabilities of the terminal node P(Y |E L, E M, E OCP), we assume that E L, E M and E OCP are conditionally independent of each other due to the lack of existing studies on the combined effects of lifestyle, medical history and OCP exposure on an early age at PD onset. Here, E L represents lifestyle effect and E M represents medical history effect.
We can obtain P(Y |E L) and equivalently P(Y |E M) based on their relevant risk factors as informed by the QPP data source.
where S and A represent smoking and alcohol respectively and S c and A c represent the absence of smoking and alcohol respectively.
Rights and permissions
Copyright information
© 2020 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Thomas, A., Wu, P., White, N.M., Toms, L., Mellick, G., Mengersen, K.L. (2020). An Ensemble Approach to Modelling the Combined Effect of Risk Factors on Age at Parkinson’s Disease Onset. In: Mengersen, K., Pudlo, P., Robert, C. (eds) Case Studies in Applied Bayesian Data Science. Lecture Notes in Mathematics, vol 2259. Springer, Cham. https://doi.org/10.1007/978-3-030-42553-1_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-42553-1_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-42552-4
Online ISBN: 978-3-030-42553-1
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)