Application of artificial intelligence and machine learning technology for the prediction of postmortem interval: A systematic review of preclinical and clinical studies. (November 2022)

• Record Type: Journal Article
• Authors: Sharma, Rishi; Diksha, ; Bhute, Ashish Ramesh; Bastia, Binaya Kumar
• Is Part Of: Forensic science international. Volume 340(2022)
• Publication Date: 2022-11
• Subjects: AI, Artificial Intelligence -- BN, Bayesian Network -- ML, Machine Learning -- BRR, Bayesian ridge regression -- PMI, Postmortem interval -- ATR, Attenuated Total Reflection -- SL, Supervised Learning -- UnSL, Unsupervised Learning -- PCA, Principal Component Analysis -- ANN, Artificial Neural Network -- PLS, Partial Least Square -- RF/R, Random Forest/Regression -- ANOVA, Analysis of variance -- SVM, Support Vector Machine -- ADD, Accumulated Degree Days -- SVR, Support Vector Regression -- NBC, Naïve Bayesian classifier -- KNN, K-Nearest Neighbors -- DL, Decision tree -- LASSO, Least Absolute Shrinkage and Selection Operator -- FTIR, Fourier-transform infrared spectroscopy; Postmortem interval -- Artificial intelligence -- Machine learning -- Intelligent computing -- Forensic science -- Forensic medicine; Medical jurisprudence -- Periodicals; Chemistry, Forensic -- Periodicals; Forensic Medicine -- Periodicals; Médecine légale -- Périodiques; Chimie légale -- Périodiques; Gerechtelijke geneeskunde; Gerechtelijke chemie; Gerechtelijke psychiatrie; Chemistry, Forensic; Medical jurisprudence; Electronic journals; Periodicals; Electronic journals; 614.1
• DOI: 10.1016/j.forsciint.2022.111473
• Languages: English
• ISSNs: 0379-0738

Abstract

Abstract: 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 unsupervised learning (N = 3). Due to the heterogeneity of the samples, quantitative analysis was not performed. 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 errors 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. Highlights: Eighteen studies were included in the final review. Preclinical and clinical studies reported use of ML models to estimate PMI. ML techniques analyze large and complex datasets such as microbiome sequencing. Majority of studies employed supervised learning than unsupervised learning. ML algorithms displayed excellent accuracy and precision to predict PMI. AI technology could serve as a potential forensic tool to predict accurate PMI.