Artificial Intelligence in Forensic Medicine and Medicolegal Practice: Applications, Limitations, and Readiness for Implementation
DOI:
https://doi.org/10.58600/eurjther3161Keywords:
artificial intelligence, explainable AI, forensic medicine, forensic toxicology, medicolegal practice, postmortem imagingAbstract
Objective: Artificial intelligence (AI) is increasingly being explored as a support tool in forensic medicine and medicolegal practice, where objective, reproducible, and timely interpretation of complex evidence is essential. This narrative review aimed to evaluate current applications of AI in forensic medicine and to discuss the methodological, ethical, and medicolegal requirements for responsible implementation.
Methods: A literature search was conducted in PubMed, Scopus, Web of Science, and Google Scholar for peer-reviewed English-language studies published between January 2018 and October 2025. Eligible publications included original research articles and reviews addressing AI-based methods in forensic domains, including postmortem imaging, age estimation, toxicology, human identification, traumatology, histopathology, and forensic reporting. The selected literature was synthesized thematically according to major applications and cross-cutting implementation challenges.
Results: Machine learning and deep learning approaches may improve efficiency, reproducibility, and pattern recognition in several forensic workflows, particularly postmortem imaging, skeletal age estimation, mass spectrometry-based toxicology, biometric identification, digital pathology, and natural language processing of medicolegal reports. However, most models remain limited by heterogeneous datasets, insufficient forensic-specific validation, algorithmic opacity, potential bias, and limited external generalizability.
Conclusion: AI should currently be regarded as a human-supervised adjunct rather than an autonomous source of forensic evidence. Future implementation requires forensic-specific validation, transparent reporting, explainability, preservation of digital chain of custody, and human-in-the-loop oversight to ensure scientific reliability, professional accountability, and medicolegal readiness.
References
[1] Volonnino G, De Paola L, Spadazzi F, et al. (2024) Artificial intelligence and future perspectives in Forensic Medicine: a systematic review. Clin Ter. 175(3):193–202. https://doi.org/10.7417/CT.2024.5062
[2] Sharma R, Diksha, Bhute AR, Bastia BK. (2022) Application of artificial intelligence and machine learning technology for the prediction of postmortem interval: A systematic review of preclinical and clinical studies. Forensic Sci Int. 340:111473. https://doi.org/10.1016/j.forsciint.2022.111473
[3] Treglia M, La Russa R, Napoletano G, Ghamlouch A, Del Duca F, Treves B, Frati P, Maiese A (2025) Artificial intelligence in forensic neuropathology: A systematic review. J Forensic Leg Med. 115:102944. https://doi.org/10.1016/j.jflm.2025.102944
[4] Parker S. (2025) Supervised natural language processing classification of violent death narratives: development and assessment of a compact large language model. JMIR AI. 4:e68212. https://doi.org/10.2196/68212
[5] Hartung T, Hoffmann S, Whaley P. (2025) Assessing risk of bias in toxicological studies in the era of artificial intelligence. Arch Toxicol. 99(8):3065–3090. https://doi.org/10.1007/s00204-025-03978-5
[6] Ogawara T, Usui A, Homma N, Funayama M. (2022) Diagnosing drowning in postmortem CT images using artificial intelligence. Tohoku J Exp Med. 259(1):65–75. https://doi.org/10.1620/tjem.2022.J097
[7] Ishida M, Gonoi W, Abe H, Ushiku T, Abe O (2023) Essence of postmortem computed tomography for in-hospital deaths: what clinical radiologists should know. Jpn J Radiol. 41(10):1039–1050. https://doi.org/10.1007/s11604-023-01443-w
[8] Khatam-Lashgari A, Harving ML, Villa C, Lynnerup N, Larsen ST. (2024) Forensic age estimation of the knee by post-mortem DR, CT, and MR imaging: a comparative study. Int J Legal Med. 138(3):971–981. https://doi.org/10.1007/s00414-024-03158-7
[9] Chernysheva A, Gundler C, Wiederhold AJ, et al. (2025) Latent spaces of generative models for forensic age estimation. Rechtsmedizin. 35(2):101–110. https://doi.org/10.1007/s00194-025-00745-9
[10] Kondou H, Morohashi R, Ichioka H, Bandou R, Matsunari R, Kawamoto M, Idota N, Ting D, Kimura S, Ikegaya H (2023) Deep neural networks-based age estimation of cadavers using CT imaging of vertebrae. Int J Environ Res Public Health. 20(6):4806. https://doi.org/10.3390/ijerph20064806
[11] Jiangtao W, Ruhaiyem NIR, Panpan F (2025) A comprehensive review of U-Net and its variants: advances and applications in medical image segmentation. IET Image Process. 19(1):e70019. https://doi.org/10.1049/ipr2.70019
[12] Shamshad F, Khan S, Zamir SW, Khan MH, Hayat M, Khan FS, Fu H (2023) Transformers in medical imaging: a survey. Med Image Anal. 88:102802. https://doi.org/10.1016/j.media.2023.102802
[13] Yeh YL, Wen CY, Hsieh CL, Chang YH, Wang SM. In vitro metabolic studies and machine learning analysis of mass spectrometry data: A dual strategy for differentiating alpha-pyrrolidinohexiophenone (α-PHP) and alpha-pyrrolidinoisohexanophenone (α-PiHP) in urine analysis. Forensic Sci Int. 2024;361:112134. https://doi.org/10.1016/j.forsciint.2024.112134
[14] Hosseini SM, Mohtarami SA, Shadnia S, Rahimi M, Evini PET, Mostafazadeh B, Memarian A, Heidarli E. Detection of body packs in abdominal CT scans through artificial intelligence; developing a machine learning-based model. Arch Acad Emerg Med. 2024;13(1):e23. https://doi.org/10.22037/aaemj.v13i1.2479
[15] Šoša I. (2025) In silico forensic toxicology: is it feasible? Toxics. 13(9):790. https://doi.org/10.3390/toxics13090790
[16] Shaki F, Amirkhanloo M, Chahardori M. (2024) The future and application of artificial intelligence in toxicology. Asia Pac J Med Toxicol. 13(1). https://doi.org/10.22038/apjmt.2024.78877.1449
[17] Steuer AE, Wartmann Y, Schellenberg R, Mantinieks D, Glowacki LL, Gerostamoulos D, Kraemer T, Brockbals L (2024) Postmortem metabolomics: influence of time since death on the level of endogenous compounds in human femoral blood. Metabolomics. 20(3):51. https://doi.org/10.1007/s11306-024-02117-y
[18] Wankhade TD, Ingale SW, Mohite PM, Bankar NJ. (2022) Artificial intelligence in forensic medicine and toxicology: the future of forensic medicine. Cureus. 14(8):e28376. https://doi.org/10.7759/cureus.28376
[19] Yang M, Li S, Zeng J. (2024) The effects of AI-driven face restoration on forensic face recognition. Appl Sci. 14(9):3783. https://doi.org/10.3390/app14093783
[20] Garg R, Singh G, Singh A, Singh MP. (2024) Fingerprint recognition using convolution neural network with inversion and augmented techniques. Systems and Soft Computing. 6:200106. https://doi.org/10.1016/j.sasc.2024.200106
[21] Barash M, McNevin D, Fedorenko V, Giverts P. (2024) Machine learning applications in forensic DNA profiling: a critical review. Forensic Sci Int Genet. 69:102994. https://doi.org/10.1016/j.fsigen.2023.102994
[22] Wang X, Shen T, Yang S, Lan J, Xu Y, Wang M, Zhang J, Han X (2021) A deep learning algorithm for automatic detection and classification of acute intracranial hemorrhages in head CT scans. Neuroimage Clin. 32:102785. https://doi.org/10.1016/j.nicl.2021.102785
[23] Cheng CT, Ooyang CH, Liao CH, Kang SC. (2025) Applications of deep learning in trauma radiology: a narrative review. Biomed J. 48(1):100743. https://doi.org/10.1016/j.bj.2024.100743
[24] McGenity C, Clarke EL, Jennings C, Matthews G, Cartlidge C, Freduah-Agyemang H, Stocken DD, Treanor D (2024) Artificial intelligence in digital pathology: diagnostic accuracy across multiple diseases—a systematic review and meta-analysis. NPJ Digit Med. 7(1):114. https://doi.org/10.1038/s41746-024-01106-8
[25] Orsini F, Cioffi A, Cipolloni L, Bibbò R, Montana A, De Simone S, Cecannecchia C (2025) The application of artificial intelligence in forensic pathology: a systematic literature review. Front Med (Lausanne). 12:1583743. https://doi.org/10.3389/fmed.2025.1583743
[26] Garland J, Tse R, Stables S, Da Broi U, Ondruschka B (2025) Artificial intelligence in forensic pathology: an Australian and New Zealand perspective. Rechtsmedizin. 35(2):65–72. https://doi.org/10.1007/s00194-025-00741-z
[27] Casey A, Davidson E, Poon M, Dong H, Duma D, Grivas A, Grover C, Suárez-Paniagua V, Tobin R, Whiteley W, Wu H, Alex B (2021) A systematic review of natural language processing applied to radiology reports. BMC Med Inform Decis Mak. 21:179. https://doi.org/10.1186/s12911-021-01533-7
[28] Nerella S, Bandyopadhyay S, Zhang J, Contreras M, Siegel S, Bumin A, Silva B, Sena J, Shickel B, Bihorac A, Khezeli K, Rashidi P (2024) Transformers and large language models in healthcare: a review. Artif Intell Med. 154:102900. https://doi.org/10.1016/j.artmed.2024.102900
[29] Hall SW, Sakzad A, Choo KKR (2022) XAI—explainable artificial intelligence—for digital forensics. WIRES Forensic Sci. 4(2):e1434. https://doi.org/10.1002/wfs2.1434
[30] Stacey J, Fleming R, Sheppard D, Sheppard J, Dobbie G, Karunakaran D. (2025) A responsible artificial intelligence framework for forensic science. Forensic Sci Int. 375:112548. https://doi.org/10.1016/j.forsciint.2025.112548
[31] Hefetz I. (2025) Integrating AI systems in criminal justice: the forensic expert as a corridor between algorithms and courtroom evidence. Forensic Sci. 5(4):53. https://doi.org/10.3390/forensicsci5040053
[32] Hefetz I. (2023) Mapping AI-ethics’ dilemmas in forensic case work: to trust AI or not? Forensic Sci Int. 350:111807. https://doi.org/10.1016/j.forsciint.2023.111807
[33] Zhan S, Huang L, Luo G, Zheng S, Gao Z, Chao H-C. (2025) A review on federated learning architectures for privacy-preserving AI: lightweight and secure cloud–edge–end collaboration. Electronics. 14(13):2512. https://doi.org/10.3390/electronics14132512
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2026 Emre Yuluğ
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The content of this journal is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
