Supplementary Files
Keywords
Machine learning
Forensic genetics
Forensic pathology
Digital forensics
How to Cite
Abstract
Artificial intelligence (AI) and machine learning (ML) are increasingly used in forensic sciences to analyze large-scale and heterogeneous evidence, providing improved speed, consistency, and decision support. This review aims to categorize current AI/ML application domains in forensic practice, summarize methodological trends, and discuss key validation requirements for operational and court-defensible use. The scope covers forensic image analysis and computer vision (traces, injuries, and crime-scene imagery), biometric identification, AI-assisted interpretation of complex forensic genetic data (including mixtures and low-template DNA), AI-enabled triage and authenticity assessment in digital/cyber forensics, and segmentation/classification tasks in forensic pathology and postmortem imaging. Despite promising performance in research settings, critical barriers remain, including explainability, data representativeness and bias, cross-laboratory reproducibility, robustness against manipulation, privacy-preserving governance, and legal admissibility. The review highlights the need for independent validation, standardized performance reporting, and clearly defined human oversight to ensure responsible and defensible integration of AI into forensic workflows.
References
Jain AK, Feng J. Latent fingerprint matching. IEEE Trans Pattern Anal Mach Intell. 2011;33(1):88-100. https://doi.org/10.1109/TPAMI.2010.59
Moretti TR, Just RS, Kehl SC, Willis KD, Buckleton JS, Bright JA, et al. Internal validation of STRmix™ for the interpretation of single source and mixed DNA profiles. Forensic Sci Int Genet. 2017;29:126-144. https://doi.org/10.1016/j.fsigen.2017.04.004
Garfinkel SL. Digital forensics research: the next 10 years. Digit Investig. 2010;7 Suppl:S64-S73. https://doi.org/10.1016/j.diin.2010.05.009
Cao K, Jain AK. Automated latent fingerprint recognition. IEEE Trans Pattern Anal Mach Intell. 2019;41(4):788-800. https://doi.org/10.1109/TPAMI.2018.2818162
Grother PJ, Ngan M, Hanaoka K. Face recognition vendor test (FRVT) part 3: demographic effects. NIST Interagency Report 8280. 2019. https://doi.org/10.6028/NIST.IR.8280
Verdoliva L. Media forensics and deepfakes: an overview. IEEE J Sel Top Signal Process. 2020;14(5):910-932. https://doi.org/10.1109/JSTSP.2020.3002101
Zimmermann N, Sieberth T, Dobay A. Automated wound segmentation and classification of seven common injuries in forensic medicine. Forensic Sci Med Pathol. 2024;20(2):443-451. https://doi.org/10.1007/s12024-023-00668-5
Drozdowski P, Rathgeb C, Dantcheva A, Damer N, Busch C. Demographic bias in biometrics: a survey on an emerging challenge. IEEE Trans Technol Soc. 2020;1(2):89-103. https://doi.org/10.1109/TTS.2020.2992344
Phillips PJ, Jiang F, Narvekar A, Ayyad J, O'Toole AJ. An other-race effect for face recognition algorithms. NIST Interagency Report 7666. 2010. https://doi.org/10.6028/NIST.IR.7666
Adamowicz MS, Rambo TN, Clarke JL. Internal validation of MaSTR™ probabilistic genotyping software for the interpretation of 2-5 person mixed DNA profiles. Genes (Basel). 2022;13(8):1429. https://doi.org/10.3390/genes13081429
Bleka Ø, Storvik G, Gill P. EuroForMix: an open source software based on a continuous model to evaluate STR DNA profiles from a mixture of contributors with artefacts. Forensic Sci Int Genet. 2016;21:35-44. https://doi.org/10.1016/j.fsigen.2015.11.008
Bright JA, Richards R, Kruijver M, Kelly H, McGovern C, Magee A, et al. Internal validation of STRmix™: a multi-laboratory response to PCAST. Forensic Sci Int Genet. 2018;34:11-24. https://doi.org/10.1016/j.fsigen.2018.01.003
Casey E, Nelson A, Hyde J. Standardization of file recovery classification and authentication. Digit Investig. 2019;31:100873. https://doi.org/10.1016/j.diin.2019.06.004
Mirsky Y, Lee W. The creation and detection of deepfakes: a survey. ACM Comput Surv. 2021;54(1):1-41. https://doi.org/10.1145/3425780
Nataraj L, Karthikeyan S, Jacob G, Manjunath BS. Malware images: visualization and automatic classification. In: Proceedings of the 8th International Symposium on Visualization for Cyber Security; 2011. p. 4:1-4:7. https://doi.org/10.1145/2016904.2016908
Dobay A, Ford J, Decker SJ, Ampanozi G, Franckenberg S, Affolter R, et al. Potential use of deep learning techniques for postmortem imaging. Forensic Sci Med Pathol. 2020;16(4):671-679. https://doi.org/10.1007/s12024-020-00307-3
Fehr J, Kurmann A, Handschin P, Garyfalia A, Franckenberg S, Golomingi R, et al. Automated volumetric estimation of six basic thoracic and abdominal organs in postmortem computed tomography data using deep learning techniques. Forensic Imaging. 2025;42:200642. https://doi.org/10.1016/j.fri.2025.200642
Cheng J, Schmidt C, Wilson A, Wang Z, Hao W, Pantanowitz J, et al. Artificial intelligence for human gunshot wound classification. J Pathol Inform. 2023;15:100361. https://doi.org/10.1016/j.jpi.2023.100361
Lopez-Melia M, Magnin V, Schranz S, Andrearczyk V, Depeursinge A, Marchand-Maillet S, et al. Automatic rib fracture detection on postmortem CT data using deep learning. Int J Legal Med. 2026;140(2):857-866. https://doi.org/10.1007/s00414-025-03669-x
European Network of Forensic Science Institutes (ENFSI). Guideline for evaluative reporting in forensic science: strengthening the evaluation of forensic results across Europe (STEOFRAE). Wiesbaden: ENFSI; 2015.
Morrison GS. What should a forensic practitioner's likelihood ratio be? II. Sci Justice. 2017;57(6):472-476. https://doi.org/10.1016/j.scijus.2017.08.004
Samek W, Wiegand T, Müller KR. Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. arXiv. 2017. https://doi.org/10.48550/arXiv.1708.08296
Cheng K, Bright JA, Kelly H, Liu YY, Lin MH, Kruijver M, et al. Developmental validation of STRmix™ NGS, a probabilistic genotyping tool for the interpretation of autosomal STRs from forensic profiles generated using NGS. Forensic Sci Int Genet. 2023;62:102804. https://doi.org/10.1016/j.fsigen.2022.102804
Huffman K, Ballantyne J. Validation of probabilistic genotyping software for single cell STR analysis. Genes (Basel). 2023;14(3):674. https://doi.org/10.3390/genes14030674
Meuwly D, Ramos D, Haraksim R. A guideline for the validation of likelihood ratio methods used for forensic evidence evaluation. Forensic Sci Int. 2017;276:142-153. https://doi.org/10.1016/j.forsciint.2016.03.048
International Organization for Standardization. ISO/IEC 17025:2017: general requirements for the competence of testing and calibration laboratories. Geneva: ISO; 2017.
Campanella G, Hanna MG, Geneslaw L, Miraflor A, Werneck Krauss Silva V, Busam KJ, et al. Clinical-grade computational pathology using weakly supervised deep learning on whole-slide images. Nat Med. 2019;25(8):1301-1309. https://doi.org/10.1038/s41591-019-0508-1
Kayser M. Forensic DNA phenotyping: predicting human appearance from crime scene material for investigative purposes. Forensic Sci Int Genet. 2015;18:33-48. https://doi.org/10.1016/j.fsigen.2015.02.003
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2026 Melek ŞENIŞIK