Artificial intelligence in forensic science: a systematic review. Part II: long-range postmortem interval estimation
Valentina Bugelli, Francesco Calabrò, Jessika Camatti, Rossana Cecchi, Marco Di Paolo, Lorenzo Franceschetti · 2026
Read Artificial intelligence in forensic science: a systematic review. Part II: long-range postmortem interval estimation by Valentina Bugelli, Francesco Calabrò, Jessika Camatti, Rossana Cecchi, Marco Di Paolo, Lorenzo Franceschetti (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13499855.txt.
Description
Valentina Bugelli leads a 2026 systematic review, the second in a series, on artificial intelligence for estimating how long ago a person died, a central forensic question called the postmortem interval. Decomposition depends on many interacting factors, which makes timing hard and motivates data-driven models. Searches of two major databases up to March 2026 followed current reporting guidance, keeping only studies that applied learning methods to real postmortem data.
Sixty-four studies qualified. Models built on body microbes were most common, followed by chemical and protein approaches and imaging-based systems, with one algorithm family, random forests, used most often in microbe work. Reported accuracy varied widely by data type and interval range. Small datasets, mixed methods, and scarce outside validation limit current proof, so the authors call for large shared datasets and models that fuse several data sources.
Catalog record
| CREATOR | Valentina Bugelli, Francesco Calabrò, Jessika Camatti, Rossana Cecchi, Marco Di Paolo, Lorenzo Franceschetti |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45254 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |