Abstract
Forensic medicine lies at the crossroads between medicine and justice, with a particular connection to criminal law. This field can be broken down into two major areas: clinical forensic medicine, which focuses on the living, and forensic pathology, which focuses on the dead. The use of data, and in particular artificial intelligence (AI), in this context faces two distinct challenges. First, there needs to be a discussion about the concept of evidence both upstream and downstream. A distinction must be made between scientific evidence, which is used to train algorithms and to support forensic reasoning in order to produce valid and robust information and legal evidence, which can include scientific data from investigations and interviews, as well as data produced by algorithms. The second challenge is individualization. One of the problems found in medicine, namely the application to a particular patient and situation of statistical knowledge established based on homogeneous groups whose study characteristics do not necessarily correspond to those of the patient, is only exacerbated in the field of forensic medicine. Not only must scientific knowledge be individualized, ensuring the validity of the algorithm to the specific case, without any learning or inclusion bias, but legal reasoning and the sentences handed down must be individualized too. AI can be used to support doctors’ decision-making in forensic medicine, and it can also be used to structure research necessary for the evolution of scientific knowledge in forensic medicine. To date, the AIs used to support decision-making remain fairly immature.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Payne-James JJ. Forensic medicine, history of. In: Encyclopedia of forensic and legal medicine, vol. 2. Amsterdam: Elsevier; 2015. p. 539–67. https://doi.org/10.1016/B978-0-12-800034-2.00203-2.
Tortora L, Meynen G, Bijlsma J, Tronci E, Ferracuti S. Neuroprediction and A.I. in forensic psychiatry and criminal justice: a neurolaw perspective. Front Psychol. 2020;11:220. https://doi.org/10.3389/fpsyg.2020.00220.
Hood L, Friend SH. Predictive, personalized, preventive, participatory (P4) cancer medicine. Nat Rev Clin Oncol. 2011;8:184–7.
Godlee F. Evidence based medicine: flawed system but still the best we’ve got. BMJ. 2014;348:g440.
Bujega G, Kumar A, Banerjee AK. Exclusion of elderly people from clinical research: a descriptive study of published reports. BMJ. 1997;315:1059.
Lillie EO, Patay B, Diamant J, et al. The n-of-1 clinical trial: the ultimate strategy for individualizing medicine? Pers Med. 2011 Mar;8(2):161–73. https://doi.org/10.2217/pme.11.7.
Latour B, Woolgar S. Laboratory life: the social construction of scientific facts. Los Angeles: Sage; 1979.
Chorev M, Shpigelman L, Bak P, Yaeli A, Michael E, Goldschmidt Y. A data-driven decision-support tool for population health policies. Stud Health Technol Inform. 2017;245:332–6.
Anderson C. The end of theory: the data deluge makes the scientific method obsolete. Wired. 2008. https://www.wired.com/2008/06/pb-theory
Pigliucci M. The end of theory in science? EMBO Rep. 2009;10(6):534. https://doi.org/10.1038/embor.2009.111.
Biedermann A, Bozza S, Taroni F. The decisionalization of individualization. Forensic Sci Int. 2016 Sep;266:29–38. https://doi.org/10.1016/j.forsciint.2016.04.029.
Biedermann A, Garbolino P, Taroni F. The subjectivist interpretation of probability and the problem of individualisation in forensic science. Sci Justice. 2013 Jun;53(2):192–200. https://doi.org/10.1016/j.scijus.2013.01.003.
Biedermann A, Taroni F, Garbolino P. Equal prior probabilities: can one do any better? Forensic Sci Int. 2007;172(2–3):85–93. https://doi.org/10.1016/j.forsciint.2006.12.008.
Lefèvre T, Chariot P, Chauvin P. Multivariate methods for the analysis of complex and big data in forensic sciences. Application to age estimation in living persons. Forensic Sci Int. 2016;266:581.e1–9. https://doi.org/10.1016/j.forsciint.2016.05.014.
Pruvost MO, Boraud C, Chariot P. Skeletal age determination in adolescents involved in judicial procedures: from evidence-based principles to medical practice. J Med Ethics. 2010;36(2):71–4. https://doi.org/10.1136/jme.2009.031948.
Moons KG, de Groot JA, Bouwmeester W, Vergouwe Y, Mallett S, Altman DG, Reitsma JB, Collins GS. Critical appraisal and data extraction for systematic reviews of prediction modelling studies: the CHARMS checklist. PLoS Med. 2014;11(10):e1001744. https://doi.org/10.1371/journal.pmed.1001744.
Fernandes K, Cardoso JS, Astrup BS. A deep learning approach for the forensic evaluation of sexual assault. Pattern Anal Applic. 2018;21:629–40. https://doi.org/10.1007/s10044-018-0694-3.
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. 2015;129(5):1163–72. https://doi.org/10.1007/s00414-015-1164-8.
Trousset V, Seyller M, Dang C, Chariot P, Lefèvre T. Prédire et dépister précocement un trouble de stress post-traumatique chez les victimes d’agressions sexuelles – potentiels de l’intelligence artificielle en consultation. 51ème congrès international de médecine légale. Dijon; 2019.
Mesejo P, Martos R, Ibáñez O, Novo J, Ortega M. A survey on artificial intelligence techniques for biomedical image analysis in skeleton-based forensic human identification. Appl Sci. 2020;10(14):4703. https://doi.org/10.3390/app10144703.
Anderson NE, Harenski KA, Harenski CL, Koenigs MR, Decety J, Calhoun VD, et al. Machine learning of brain gray matter differentiates sex in a large forensic sample. Hum Brain Mapp. 2019;40:1496–506. https://doi.org/10.1002/hbm.24462.
Moore HE, Butcher JB, Day CR, Drijfhout FP. Adult fly age estimations using cuticular hydrocarbons and artificial neural networks in forensically important Calliphoridae species. For Sci Int. 2017;280:233–44. https://doi.org/10.1016/j.forsciint.2017.10.001.
Cantürk I, Özilmaz L. A computational approach to estimate postmortem interval using opacity development of eye for human subjects. Comput Biol Med. 2018;98:93–9. https://doi.org/10.1016/j.compbiomed.2018.04.023.
Duarte F, Martins B, Pinto CS, Silva MJ. Deep neural models for ICD-10 coding of death certificates and autopsy reports in free-text. J Biomed Inform. 2018;80:64–77. https://doi.org/10.1016/j.jbi.2018.02.011.
Dirnhofer R, Jackowski C, Vock P, Potter K, Thali MJ. VIRTOPSY: minimally invasive, imaging-guided virtual autopsy. Radiographics. 2006;26(5):1305–33. https://doi.org/10.1148/rg.265065001.
Ebert LC, Heimer J, Schweitzer W, Sieberth T, Leipner A, Thali M, et al. Automatic detection of hemorrhagic pericardial effusion on PMCT using deep learning – a feasibility study. For Sci Med Pathol. 2017;13:426–31. https://doi.org/10.1007/s12024-017-9906-1.
Zhou Y, Zhang J, Huang J, Deng K, Zhang J, Qin Z, et al. Digital whole-slide image analysis for automated diatom test in forensic cases of drowning using a convolutional neural network algorithm. For Sci Int. 2019;302:109922. https://doi.org/10.1016/j.forsciint.2019.109922.
Linthicum KP, Schafer KM, Ribeiro JD. Machine learning in suicide science: applications and ethics. Behav Sci Law. 2019;37:214–22. https://doi.org/10.1002/bsl.2392.
Monash University. https://www.monash.edu/news/articles/monash-designs-technology-to-map-bullet-trajectory. (2019). Accessed 25 Nov 2020.
Neumann C, Evett IW, Skerrett J. Quantifying the weight of evidence from a fingerprint comparison: a new paradigm. J R Stat Soc Ser A. 2012;175:371–416.
Taroni F, Biedermann A, Vuille J, Morling N. Whose DNA is this? How relevant a question? (a note for forensic scientists). Forensic Sci Int Genet. 2013 Jul;7(4):467–70. https://doi.org/10.1016/j.fsigen.2013.03.012.
https://shuftipro.com/blog/fighting-identity-fraud-with-ai-enabled-id-document-verification
Lefèvre T. Big data in forensic science and medicine. J Forensic Legal Med. 2018;57:1–6. https://doi.org/10.1016/j.jflm.2017.08.001.
Guez S, Laugier V, Saas C, Lefèvre T. L’IA, le légiste et le magistrat: traitement médicolégal des violences interpersonnelles. In: Julia G, editor. Sciences et sens de l’intelligence artificielle, Thèmes et commentaires. Dalloz; 2020.
Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447–53. https://doi.org/10.1126/science.aax2342.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this entry
Cite this entry
Lefèvre, T. (2022). Artificial Intelligence in Forensic Medicine. In: Lidströmer, N., Ashrafian, H. (eds) Artificial Intelligence in Medicine. Springer, Cham. https://doi.org/10.1007/978-3-030-64573-1_220
Download citation
DOI: https://doi.org/10.1007/978-3-030-64573-1_220
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64572-4
Online ISBN: 978-3-030-64573-1
eBook Packages: MedicineReference Module Medicine