Advances in artificial intelligence-based microbiome for PMI estimation

A novel approach for estimating postmortem intervals under varying temperature conditions using pathology images and artificial intelligence models

Estimating the postmortem interval (PMI) is a critical yet complex task in forensic investigations, with accurate and timely determination playing a key role in case resolution and legal outcomes. Traditional methods often suffer from environmental variability and subjective biases, emphasizing the need for more reliable and objective approaches. In this study, we present a novel predictive model for PMI estimation, introduced here for the first time, that leverages pathological tissue images and artificial intelligence (AI). The model is designed to perform under three temperature conditions: 25 °C, 37 °C, and 4 °C. Using a ResNet50 neural network, patch-level images were analyzed to extract deep learning-derived features, which were integrated with machine learning algorithms for whole slide image (WSI) classification. The model achieved strong performance, with micro and macro AUC values of at least 0.949 at the patch-level and 0.800 at the WSI-level in both training and testing sets. In external validation, micro and macro AUC values at the patch-level exceeded 0.960. These results highlight the potential of AI to improve the accuracy and efficiency of PMI estimation. As AI technology continues to advance, this approach holds promise for enhancing forensic investigations and supporting more precise case resolutions.

Unveiling the Forensic Potential of Oral and Nasal Microbiota in Post-Mortem Interval Estimation

Microbiota have emerged as a promising tool for estimating the post-mortem interval (PMI) in forensic investigations. The role of oral and nasal microbiota in cadaver decomposition is crucial; however, their distribution across human cadavers at different PMIs remains underexplored. In this study, we collected 88 swab samples from the oral and nasal cavities of 10 healthy volunteers and 34 human cadavers. Using 16S rRNA gene sequencing, we conducted comprehensive analyses of the alpha diversity, beta diversity, and relative abundance distribution to characterize the microbial communities in both healthy individuals and cadavers at varying PMIs and under different freezing conditions. Random forest models identified Firmicutes, Proteobacteria, Bacteroidota, Actinobacteriota, and Fusobacteriota as potential PMI-associated biomarkers at the phylum level for both the oral and nasal groups, along with genus-level biomarkers specific to each group. These biomarkers exhibited nonlinear changes over increasing PMI, with turning points observed on days 5, 12, and 22. The random forest inference models demonstrated that oral biomarkers at both the genus and phylum levels achieved the lowest mean absolute error (MAE) values in the training dataset (MAE = 2.16 days) and the testing dataset (MAE = 5.14 days). Additionally, freezing had minimal impact on the overall phylum-level microbial composition, although it did affect the relative abundance of certain phyla. At the genus level, significant differences in microbial biomarkers were observed between frozen and unfrozen cadavers, with the oral group showing greater stability compared to the nasal group. These findings suggest that the influence of freezing should be considered when using genus-level microbial data to estimate PMIs. Overall, our results highlight the potential of oral and nasal microbiota as robust tools for PMI estimation and emphasize the need for further research to refine predictive models and explore the environmental factors shaping microbial dynamics.

Exploring the Post Mortem Interval (PMI) Estimation Model by circRNA circRnf169 in Mouse Liver Tissue

Estimating the post mortem interval (PMI) is a crucial and contentious issue in forensic research, particularly in criminal cases. Traditional methods for PMI estimation are limited by constraints and inaccuracies. Circular RNA (circRNA), formed through exon or intron looping to create a complete circular structure without a 5' end cap and a 3' poly(A) tail, exhibits exceptional stability, abundance, and tissue-specific characteristics that make it potentially valuable for PMI estimation. However, research on the exploration or application of circRNA in PMI estimation has been limited. This study aims to investigate the correlation between circRNA and PMI. In this study, liver tissue samples were collected from mice at six different time points at 4 °C, 18 °C, 25 °C, and 35 °C, respectively. The reference gene 28S rRNA and the biomarker circRnf169 were successfully screened. Quantitative PCR was employed to examine the correlation between circRnf169 levels and PMI. At 4 °C, the level of circRnf169 decreased with prolonged PMI, whereas at 18 °C, 25 °C, and 35 °C, the circRnf169 RNA was degraded rapidly, indicating that circRnf169 is suitable for PMI estimation at low temperatures or early PMI. These findings suggest the establishment of mathematical model for early PMI based on circRnf169 using liver tissue, which may serve as a reliable marker. Further research is required in order to develop more markers in mice and/or to validate these mathematical models in human samples.

Multimodal Approaches Based on Microbial Data for Accurate Postmortem Interval Estimation

Accurate postmortem interval (PMI) estimation is critical for forensic investigations, aiding case classification and providing vital trial evidence. Early postmortem signs, such as body temperature and rigor mortis, are reliable for estimating PMI shortly after death. However, these indicators become less useful as decomposition progresses, making late-stage PMI estimation a significant challenge. Decomposition involves predictable microbial activity, which may serve as an objective criterion for PMI estimation. During decomposition, anaerobic microbes metabolize body tissues, producing gases and organic acids, leading to significant changes in skin and soil microbial communities. These shifts, especially the transition from anaerobic to aerobic microbiomes, can objectively segment decomposition into pre- and post-rupture stages according to rupture point. Microbial communities change markedly after death, with anaerobic bacteria dominating early stages and aerobic bacteria prevalent post-rupture. Different organs exhibit distinct microbial successions, providing valuable PMI insights. Alongside microbial changes, metabolic and volatile organic compound (VOC) profiles also shift, reflecting the body's biochemical environment. Due to insufficient information, unimodal models could not comprehensively reflect the PMI, so a muti-modal model should be used to estimate the PMI. Machine learning (ML) offers promising methods for integrating these multimodal data sources, enabling more accurate PMI predictions. Despite challenges such as data quality and ethical considerations, developing human-specific multimodal databases and exploring microbial-insect interactions can significantly enhance PMI estimation accuracy, advancing forensic science.

Estimating postmortem interval based on oral microbial community succession in rat cadavers

The accurate estimation of the postmortem interval has been one of the crucial issues to be solved in forensic research, and it is influenced by various factors in the process of decay. With the development of high-throughput sequencing technology, forensic microbiology has become the major hot topic in forensic science, which provides new research options for postmortem interval estimation. The oral microbial community is one of the most diverse of microbiomes, ranking as the second most abundant microbiota following the gastrointestinal tract. It is remarkable that oral microorganisms have a significant function in the decay process of cadavers. Therefore, we collected outdoor soil to simulate the death environment and focused on the relationship between oral microbial community succession and PMI in rats above the soil. In addition, linear regression models and random forest regression models were developed for the relationship between the relative abundance of oral microbes and PMI. We also identified a number of microorganisms that may be important to estimate PMI, including: Ignatzschineria, Morganella, Proteus, Lysinibacillus, Pseudomonas, Globicatella, Corynebacterium, Streptococcus, Rothia, Aerococcus, Staphylococcus, and so on.

Artificial intelligence in forensic medicine and related sciences - selected issues

Aim

The aim of the work is to provide an overview of the potential application of artificial intelligence in forensic medicine and related sciences, and to identify concerns related to providing medico-legal opinions and legal liability in cases in which possible harm in terms of diagnosis and/or treatment is likely to occur when using an advanced system of computer-based information processing and analysis.

Material and methods

The material for the study comprised scientific literature related to the issue of artificial intelligence in forensic medicine and related sciences. For this purpose, Google Scholar, PubMed and ScienceDirect databases were searched. To identify useful articles, such terms as "artificial intelligence," "deep learning," "machine learning," "forensic medicine," "legal medicine," "forensic pathology" and "medicine" were used. In some cases, articles were identified based on the semantic proximity of the introduced terms.

Conclusions

Dynamic development of the computing power and the ability of artificial intelligence to analyze vast data volumes made it possible to transfer artificial intelligence methods to forensic medicine and related sciences. Artificial intelligence has numerous applications in forensic medicine and related sciences and can be helpful in thanatology, forensic traumatology, post-mortem identification examinations, as well as post-mortem microscopic and toxicological diagnostics. Analyzing the legal and medico-legal aspects, artificial intelligence in medicine should be treated as an auxiliary tool, whereas the final diagnostic and therapeutic decisions and the extent to which they are implemented should be the responsibility of humans.

Advances in machine learning-based bacteria analysis for forensic identification: identity, ethnicity, and site of occurrence

When faced with an unidentified body, identifying the victim can be challenging, particularly if physical characteristics are obscured or masked. In recent years, microbiological analysis in forensic science has emerged as a cutting-edge technology. It not only exhibits individual specificity, distinguishing different human biotraces from various sites of occurrence (e.g., gastrointestinal, oral, skin, respiratory, and genitourinary tracts), each hosting distinct bacterial species, but also offers insights into the accident's location and the surrounding environment. The integration of machine learning with microbiomics provides a substantial improvement in classifying bacterial species compares to traditional sequencing techniques. This review discusses the use of machine learning algorithms such as RF, SVM, ANN, DNN, regression, and BN for the detection and identification of various bacteria, including Bacillus anthracis, Acetobacter aceti, Staphylococcus aureus, and Streptococcus, among others. Deep leaning techniques, such as Convolutional Neural Networks (CNN) models and derivatives, are also employed to predict the victim's age, gender, lifestyle, and racial characteristics. It is anticipated that big data analytics and artificial intelligence will play a pivotal role in advancing forensic microbiology in the future.

ChatGPT in forensic sciences: a new Pandora's box with advantages and challenges to pay attention

ChatGPT is a variant of the generative pre-trained transformer (GPT) language model that uses large amounts of text-based training data and a transformer architecture to generate human-like text adjusted to the received prompts. ChatGPT presents several advantages in forensic sciences, namely, constituting a virtual assistant to aid lawyers, judges, and victims in managing and interpreting forensic expert data. But what would happen if ChatGPT began to be used to produce forensic expertise reports? Despite its potential applications, the use of ChatGPT and other Large Language Models and artificial intelligence tools in forensic writing also poses ethical and legal concerns, which are discussed in this perspective together with some expected future perspectives.

Changes in Microbial Communities Using Pigs as a Model for Postmortem Interval Estimation

Microbial communities can undergo significant successional changes during decay and decomposition, potentially providing valuable insights for determining the postmortem interval (PMI). The microbiota produce various gases that cause cadaver bloating, and rupture releases nutrient-rich bodily fluids into the environment, altering the soil microbiota around the carcasses. In this study, we aimed to investigate the underlying principles governing the succession of microbial communities during the decomposition of pig carcasses and the soil beneath the carcasses. At early decay, the phylum Firmicutes and Bacteroidota were the most abundant in both the winter and summer pig rectum. However, Proteobacteria became the most abundant in the winter pig rectum in late decay. Using genus as a biomarker to estimate the PMI could get the MAE from 1.375 days to 2.478 days based on the RF model. The abundance of bacterial communities showed a decreasing trend with prolonged decomposition time. There were statistically significant differences in microbial diversity in the two periods (pre-rupture and post-rupture) of the four groups (WPG 0-8Dvs. WPG 16-40D, p < 0.0001; WPS 0-16Dvs. WPS 24-40D, p = 0.003; SPG 0D vs. SPG 8-40D, p = 0.0005; and SPS 0D vs. SPS 8-40D, p = 0.0208). Most of the biomarkers in the pre-rupture period belong to obligate anaerobes. In contrast, the biomarkers in the post-rupture period belong to aerobic bacteria. Furthermore, the genus Vagococcus shows a similar increase trend, whether in winter or summer. Together, these results suggest that microbial succession was predictable and can be developed into a forensic tool for estimating the PMI.

The Future Is Now: Unraveling the Expanding Potential of Human (Necro)Microbiome in Forensic Investigations

The relevance of postmortem microbiological examinations has been controversial for decades, but the boom in advanced sequencing techniques over the last decade is increasingly demonstrating their usefulness, namely for the estimation of the postmortem interval. This comprehensive review aims to present the current knowledge about the human postmortem microbiome (the necrobiome), highlighting the main factors influencing this complex process and discussing the principal applications in the field of forensic sciences. Several limitations still hindering the implementation of forensic microbiology, such as small-scale studies, the lack of a universal/harmonized workflow for DNA extraction and sequencing technology, variability in the human microbiome, and limited access to human cadavers, are discussed. Future research in the field should focus on identifying stable biomarkers within the dominant Bacillota and Pseudomonadota phyla, which are prevalent during postmortem periods and for which standardization, method consolidation, and establishment of a forensic microbial bank are crucial for consistency and comparability. Given the complexity of identifying unique postmortem microbial signatures for robust databases, a promising future approach may involve deepening our understanding of specific bacterial species/strains that can serve as reliable postmortem interval indicators during the process of body decomposition. Microorganisms might have the potential to complement routine forensic tests in judicial processes, requiring robust investigations and machine-learning models to bridge knowledge gaps and adhere to Locard's principle of trace evidence.

Enhancing the Evidence with Algorithms: How Artificial Intelligence Is Transforming Forensic Medicine

BACKGROUND

The integration of artificial intelligence (AI) into various fields has ushered in a new era of multidisciplinary progress. Defined as the ability of a system to interpret external data, learn from it, and adapt to specific tasks, AI is poised to revolutionize the world. In forensic medicine and pathology, algorithms play a crucial role in data analysis, pattern recognition, anomaly identification, and decision making. This review explores the diverse applications of AI in forensic medicine, encompassing fields such as forensic identification, ballistics, traumatic injuries, postmortem interval estimation, forensic toxicology, and more.

RESULTS

A thorough review of 113 articles revealed a subset of 32 papers directly relevant to the research, covering a wide range of applications. These included forensic identification, ballistics and additional factors of shooting, traumatic injuries, post-mortem interval estimation, forensic toxicology, sexual assaults/rape, crime scene reconstruction, virtual autopsy, and medical act quality evaluation. The studies demonstrated the feasibility and advantages of employing AI technology in various facets of forensic medicine and pathology.

CONCLUSIONS

The integration of AI in forensic medicine and pathology offers promising prospects for improving accuracy and efficiency in medico-legal practices. From forensic identification to post-mortem interval estimation, AI algorithms have shown the potential to reduce human subjectivity, mitigate errors, and provide cost-effective solutions. While challenges surrounding ethical considerations, data security, and algorithmic correctness persist, continued research and technological advancements hold the key to realizing the full potential of AI in forensic applications. As the field of AI continues to evolve, it is poised to play an increasingly pivotal role in the future of forensic medicine and pathology.