Application of artificial intelligence and machine learning technology for the prediction of postmortem interval: A systematic review of preclinical and clinical studies

Background /purpose: Establishing an accurate postmortem interval (PMI) is exceptionally crucial in forensic investigation. Artificial intelligence (AI) and Machine learning (ML) models are widely employed in forensic practice. ML is a part of AI, both terms are highly associated and sometimes used interchangeably. This systematic review aims to evaluate the application and performance of AI technology for the prediction of PMI.Methods: Systematic literature search across different electronic databases using PubMed/Google Scholar/ EMBASE/Scopus/CINAHL/Web of Science/Cochrane library was conducted from inception to 3 December 2021 for preclinical and clinical studies reported ML models for PMI estimation.Results: We identified 18 studies (12 preclinical and 06 clinical) that met the inclusion criteria in the qualitative analysis. Most of the studies employed supervised learning (N = 15), and others employed un-supervised learning (N = 3). Due to the heterogeneity of the samples, quantitative analysis was not per-formed. Conclusion: In this systematic review, we discussed the performance of AI-based automated systems in PMI estimation. ML models have demonstrated accuracy and precision and the ability to overcome human er-rors and bias. However, the research is limited, conducted in primarily small, selected human populations. In addition, we suggest further research in larger population-based studies is needed to fully understand the extent of integrated ML models.(c) 2022 Elsevier B.V. All rights reserved.

Automated summary

This systematic review evaluates the application and performance of AI technology in postmortem interval (PMI) prediction. The studies show that machine learning models have demonstrated accuracy, precision, and the ability to overcome human errors and bias in PMI estimation. However, the research is limited to small, selected populations, and further large-scale population-based studies are needed to fully understand the integration of ML models.