Abstract
The search for complex, nonlinear relationships and causality in data is hindered by the availability of techniques in many domains, including forensic science. Linear multivariable techniques are useful but present some shortcomings. In the past decade, Bayesian approaches have been introduced in forensic science. To date, authors have mainly focused on providing an alternative to classical techniques for quantifying effects and dealing with uncertainty. Causal networks, including Bayesian networks, can help detangle complex relationships in data. A Bayesian network estimates the joint probability distribution of data and graphically displays dependencies between variables and the circulation of information between these variables. In this study, we illustrate the interest in utilizing Bayesian networks for dealing with complex data through an application in clinical forensic science. Evaluating the functional impairment of assault survivors is a complex task for which few determinants are known. As routinely estimated in France, the duration of this impairment can be quantified by days of ‘Total Incapacity to Work’ (‘Incapacité totale de travail,’ ITT). In this study, we used a Bayesian network approach to identify the injury type, victim category and time to evaluation as the main determinants of the ‘Total Incapacity to Work’ (TIW). We computed the conditional probabilities associated with the TIW node and its parents. We compared this approach with a multivariable analysis, and the results of both techniques were converging. Thus, Bayesian networks should be considered a reliable means to detangle complex relationships in data.
Similar content being viewed by others
References
Brunel C, Fermanian C, Durigon M, de la Grandmaison GL (2010) Homicidal and suicidal sharp force fatalities: Autopsy parameters in relation to the manner of death. Forensic Sci Int 198:150–154
Lefèvre T, Briffa H, Thomas G, Chariot P (2012) Evaluating the functional impairment of assault survivors in a judicial context – A retrospective study. J Forensic Leg Med 19:215–218
Schmeling A, Reisinger W, Geserick G, Olze A (2006) Age estimation of unaccompanied minors. Part I. General considerations. Forensic Sci Int 159(Suppl 1):S61–S64
Karlsson T (1998) Multivariate analysis (‘forensiometrics’)–a new tool in forensic medicine. Differentiation between sharp force homicide and suicide. Forensic Sci Int 94:183–200
Biedermann A, Bozza S, Garbolino P, Taroni F (2012) Decision-theoretic analysis of forensic sampling criteria using bayesian decision networks. Forensic Sci Int 223:217–227
Rothman KJ, Greenland S, Lash TL (2008) Modern epidemiology. Wolters Kluwer / Lippincott Williams & Wilkins, Philadelphia
Braga J, Heuze Y, Chabadel O, Sonan NK, Gueramy A (2005) Non-adult dental age assessment: correspondence analysis and linear regression versus Bayesian predictions. Int J Legal Med 119:260–274
Thevissen PW, Fieuws S, Willems G (2010) Human dental age estimation using third molar developmental stages: does a Bayesian approach outperform regression models to discriminate between juveniles and adults? Int J Legal Med 124:35–42
Garbolino P, Taroni F (2002) Evaluation of scientific evidence using Bayesian networks. Forensic Sci Int 125:149–155
Galea S, Riddle M, Kaplan GA (2009) Causal thinking and complex system approaches in epidemiology. Int J Epidemiol 39:97–106
Marwala T (2007) Control of Complex Systems Using Bayesian Networks and Genetic Algorithm. arXiv:07051214. http://arxiv.org/abs/0705.1214. Accessed 19 June 2014
Joffe M, Gambhir M, Chadeau-Hyam M, Vineis P (2012) Causal diagrams in systems epidemiology. Emerg Themes Epidemiol 9:1
Rehfuess EA, Best N, Briggs DJ, Joffe M (2013) Diagram-based Analysis of Causal Systems (DACS): elucidating inter-relationships between determinants of acute lower respiratory infections among children in sub-Saharan Africa. Emerg Themes Epidemiol 10:13
Pe’er D (2005) Bayesian Network Analysis of Signaling Networks: A Primer. Sci STKE 2005:pl4–pl4
Sachs K, Perez O, Pe’er D, Lauffenger DA, Nolan GP (2005) Causal Protein-Signaling Networks Derived from Multiparameter Single-Cell Data. Science 308:523–529
Pearl J, Verma T (1991) A theory of inferred causation. In: Allen JA, Fikes R, Sandewall E (eds) Principles of knowledge representation and reasoning: Proceedings of the second international conference. Morgan Kaufmann, San Mateo, pp 441–452
Pearl J (2010) Causality : models, reasoning, and inference. Cambridge University Press, Cambridge
Bui AT, Jun CH (2012) Learning Bayesian network structure using Markov blanket decomposition. Pattern Recogn Lett 33:2134–2140
Tsamardinos I, Aliferis CF, Statnikov AR (2003) Algorithms for Large Scale Markov Blanket Discovery. In: Proceedings of the sixteenth international Florida artificial intelligence. Research Society Conference, AAAI Press pp. 376–381
Nagarajan R, Scutari M, Lèbre S (2012) Bayesian networks in R with applications in systems biology. Springer, New York
Margolin AA, Nemenman I, Basso K et al (2006) ARACNE: An Algorithm for the Reconstruction of Gene Regulatory Networks in a Mammalian Cellular Context. BMC Bioinforma 7(Suppl 1):S7
Zou C, Feng J (2009) Granger causality vs. Dynamic Bayesian network inference: a comparative study. BMC Bioinforma 10:122
Zuk O, Margel S, Domany E (2012) On the number of samples needed to learn the correct structure of a Bayesian network. arXiv:1206.6862 [cs.LG] http://arxiv.org/abs/1206.6862. Accessed 13 November 2014
Tsamardinos I, Brown LE, Aliferis CF (2006) The max-min hill-climbing Bayesian network structure learning algorithm. Mach Learn 65:31–78
Yu J, Smith A, Wang PP, Hartemink AJ, Jarvis ED (2004) Advances to Bayesian network inference for generating causal networks from observational biological data. Bioinformatics 20:3594–3603
Gignon M, Paupière S, Jardè O, Manaouil C (2010) Victims of assault: a Europe-wide review of procedures for evaluating the seriousness of injuries. Med Sci Law 50:145–148
French Penal Code. Article 222–11. legifrance.fr http://195.83.177.9/upl/pdf/code_33.pdf. Accessed 19 June 2014
Scutari M (2009) Learning Bayesian Networks with the bnlearn R Package. arXiv:09083817 http://arxiv.org/abs/0908.3817. Accessed 19 June 2014
Evans D, Chaix B, Lobbedez T, Verger C, Flahault A (2012) Combining directed acyclic graphs and the change-in-estimate procedure as a novel approach to adjustment-variable selection in epidemiology. BMC Med Res Methodol 12:156
Hartemink AJ (2005) Reverse engineering gene regulatory networks. Nat Biotechnol 23:554–555
Koski T, Noble J (2009) Bayesian Networks: An Introduction. Wiley-Blackwell, Chichester
Taroni PF, Aitken C, Garbolino PP, Biedermann DA (2006) Bayesian Networks and Probabilistic Inference in Forensic Science. Wiley-Blackwell, Chichester
Kim S, Imoto S, Miyano S (2004) Dynamic Bayesian network and nonparametric regression for nonlinear modeling of gene networks from time series gene expression data. Biosystems 75:57–65
Lee SY, Song XY (2012) Basic and advanced structural equation models for medical and behavioural sciences. Wiley, Hoboken
Greenland S, Poole C (2013) Living with p values: resurrecting a Bayesian perspective on frequentist statistics. Epidemiology 24:62–68
Efron B (2013) Bayes’ Theorem in the 21st Century. Science 340:1177–1178
Conflicts of interests
None.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lefèvre, T., Lepresle, A. & Chariot, P. Detangling complex relationships in forensic data: principles and use of causal networks and their application to clinical forensic science. Int J Legal Med 129, 1163–1172 (2015). https://doi.org/10.1007/s00414-015-1164-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00414-015-1164-8