Related Experiment Video
Updated: Sep 14, 2025
Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics
Published on: November 29, 2024
Untangling the Postmortem Metabolome: A Machine Learning Approach for Accurate PMI Estimation
Ida Marie M Løber1,2,3, Mette S Hedemann4, Palle Villesen2,3
1Department of Forensic Medicine, Aarhus University, 8200 Aarhus, Denmark.
Abstract:
Accurate estimation of the postmortem interval (PMI) is crucial for medico-legal investigations, providing critical timelines for criminal cases. Current PMI methods, however, often lack precision, limiting their forensic utility. In this study, we developed models to estimate PMI with high accuracy across various tissues within the first 4 days after death. Using untargeted UHPLC-qTOF-MS, we analyzed thousands of molecules in rat tissues with different PMIs. We employed machine learning on stable and highly reproducible molecules in each tissue to select candidate biomarkers and then built a second model using only the top 15 molecules. Both Lasso and Random Forest approaches yielded high cross-validation accuracy across all tissues, with the latter showing slightly superior performance. Validation was conducted using an independently collected and analyzed set of rats. The identified metabolites, including amino acids, derivatives, nucleosides, and other markers, are common to humans and mammals, underscoring their potential applicability in human forensic contexts. Our findings highlight the tissue-specific predictive potential and variability in predictive accuracy across different tissues in a rodent model.
Insights
This study developed accurate machine learning models for estimating the postmortem interval (PMI) using molecular data from rat tissues within 4 days of death. These findings offer potential for improved forensic timelines in human investigations.
Area of Science:
- Forensic Science
- Biochemistry
- Computational Biology
Background:
- Accurate postmortem interval (PMI) estimation is vital for medico-legal investigations.
- Existing PMI methods often lack the required precision for forensic applications.
- Developing novel, accurate PMI estimation techniques is a critical need.
Purpose of the Study:
- To develop and validate accurate machine learning models for PMI estimation.
- To identify reliable molecular biomarkers for PMI determination across different tissues.
- To assess the tissue-specific predictive potential for PMI estimation.
Main Methods:
- Utilized untargeted UHPLC-qTOF-MS to analyze thousands of molecules in rat tissues.
- Employed machine learning (Lasso, Random Forest) to build predictive models for PMI.
- Validated models using an independent dataset of rat tissues.
Main Results:
- Achieved high cross-validation accuracy in PMI estimation across various tissues within the first 4 days.
- Random Forest models demonstrated slightly superior predictive performance.
- Identified key metabolites (amino acids, nucleosides) as potential PMI biomarkers.
Conclusions:
- The developed models accurately estimate PMI using tissue molecular profiles.
- Identified metabolites are conserved across mammals, suggesting human forensic applicability.
- Tissue-specific analysis is crucial for optimizing PMI estimation accuracy.
More Related Videos
07:11Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis
Published on: November 10, 2023
11:25Multi-step Preparation Technique to Recover Multiple Metabolite Compound Classes for In-depth and Informative Metabolomic Analysis
Published on: July 11, 2014