Orsini Francesco, Cioffi Andrea, Cipolloni Luigi, Bibbò Roberta, Montana Angelo, De Simone Stefania, Cecannecchia Camilla
Department of Clinical and Experimental Medicine, Section of Legal Medicine, University of Foggia, Foggia, Italy.
Department of Biomedical Sciences and Public Health, University Politecnica delle Marche, Ancona, Italy.
Front Med (Lausanne). 2025 Jul 24;12:1583743. doi: 10.3389/fmed.2025.1583743. eCollection 2025.
Recent advancements in Artificial Intelligence have shown immense potential across various domains of healthcare, including forensic pathology. This systematic review aims to evaluate the latest innovations brought by Artificial Intelligence in forensic pathology and provide insights into future directions in this evolving field.
A systematic literature search was conducted using databases for papers published from 1990 to 2025. The search strategy combined terms related to artificial intelligence, forensic odontology, forensic psychiatry and forensic medicine/pathology. Following PRISMA guidelines, 65 articles were initially identified, of which 18 met the inclusion criteria after applying exclusion criteria.
Artificial Intelligence applications demonstrated significant success across multiple forensic domains. In post-mortem analysis, deep learning achieved 70-94% accuracy in neurological forensics. Wound analysis systems showed high accuracy rates (87.99-98%) in gunshot wound classification. Artificial Intelligence-enhanced diatom testing for drowning cases achieved precision scores of 0.9 and recall scores of 0.95. Microbiome analysis applications reached accuracy rates up to 90% for individual identification and geographical origin determination. AI shows promise in forensic age estimation, psychiatric risk assessment, and insanity evaluations.
While Artificial Intelligence shows promise as a supportive tool in forensic pathology, several limitations persist, including small sample sizes and variable performance across different applications. Artificial Intelligence serves best as an enhancement rather than a replacement for human expertise. Future development should focus on larger datasets, specialized systems for different forensic applications, and improved interpretability of Artificial Intelligence decisions for legal contexts. The integration of Artificial Intelligence in forensic pathology represents a significant advancement, requiring careful balance between technological innovation and human expertise for optimal implementation.
人工智能的最新进展在医疗保健的各个领域都展现出了巨大潜力，包括法医病理学。本系统综述旨在评估人工智能在法医病理学中带来的最新创新，并洞察这一不断发展领域的未来方向。
使用数据库对1990年至2025年发表的论文进行系统文献检索。检索策略结合了与人工智能、法医牙科学、法医精神病学和法医学/病理学相关的术语。按照PRISMA指南，最初识别出65篇文章，应用排除标准后，其中18篇符合纳入标准。
人工智能应用在多个法医领域都取得了显著成功。在尸检分析中，深度学习在神经法医学方面的准确率达到70 - 94%。伤口分析系统在枪伤分类中的准确率很高（87.99 - 98%）。人工智能增强的溺水案件硅藻检测的精确率得分为0.9，召回率得分为0.95。微生物组分析应用在个体识别和地理来源确定方面的准确率高达90%。人工智能在法医年龄估计、精神风险评估和精神错乱评估方面显示出前景。
虽然人工智能在法医病理学中作为一种辅助工具显示出前景，但仍存在一些局限性，包括样本量小以及不同应用中的性能差异。人工智能最适合作为对人类专业知识的增强，而不是替代。未来的发展应侧重于更大的数据集、针对不同法医应用的专门系统，以及提高人工智能决策在法律背景下的可解释性。人工智能在法医病理学中的整合代表了一项重大进步，需要在技术创新和人类专业知识之间仔细权衡以实现最佳实施。
