A Machine Learning Approach for Using the Postmortem Skin Microbiome to Estimate the Postmortem Interval
Problem
Forensic investigators need to estimate the postmortem interval (time since death) for cadavers found after unknown time periods, and current methods have substantial limitations.
Why it matters
Accurate time-of-death estimation is critical for death investigations and legal outcomes.
What the AI did
Sampled skin microbiota from decomposing human cadavers and developed statistical regression models to predict postmortem interval from microbial data, finding the complete dataset outperformed curated indicator species.
Results
not stated in source
Impact
Peer-reviewed PLoS ONE paper with 167 citations indicates sustained research interest.
Record
| Venue | PLoS ONE |
|---|---|
| Published | 2016 |
| Work type | article |
| Authors | Hunter Johnson, Donovan Trinidad, Stephania Guzman, Zenab Khan, James V. Parziale, Jennifer M. DeBruyn, Nathan H. Lents |
| Citations | 167 (OpenAlex, at import time) |
| References | 32 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1371/journal.pone.0167370 |
| Open access | gold |
| Keywords | microbiome, postmortem interval, forensic science, machine learning, regression |
Importance rating
real but narrower advance
Accurate postmortem interval estimation is critical for death investigations and legal outcomes, a real but narrow forensic advance; no scale stated.