Artificial intelligence in forensic age assessment: a systematic review.

Area of Science:

• Forensic Science
• Medical Imaging
• Artificial Intelligence

Background:

• Forensic age assessment is vital for undocumented individuals in medico-legal cases.
• Artificial intelligence (AI) is emerging as a tool to enhance age estimation accuracy.
• The forensic applicability of AI for age assessment, especially around legal age thresholds, requires further characterization.

Purpose of the Study:

• To systematically review the application of AI techniques in forensic age estimation.
• To evaluate the performance and forensic applicability of AI-driven age assessment methods.
• To identify research gaps and future directions for AI in forensic age determination.

Main Methods:

• A systematic review following PRISMA 2020 guidelines.
• Searches of MEDLINE (PubMed) and Scopus databases up to March 1, 2026.
• Inclusion of 48 studies applying AI to forensic age estimation with quantitative metrics.

Main Results:

• AI applied to dental radiographs achieved mean absolute errors of 0.5–1.5 years.
• DNA methylation models reported errors between 3–5 years; MRI-based skeletal models showed errors near 1 year.
• Few studies assessed AI performance around critical legal age thresholds (e.g., 18 years).

Conclusions:

• AI demonstrates significant potential for automating and improving the reproducibility of forensic age estimation.
• Further research with diverse datasets, external validation, and standardized reporting is crucial for clinical implementation.
• AI-powered forensic age assessment requires robust validation for reliable medico-legal application.