Artificial intelligence in the practice of forensic medicine: a scoping review.

Forensic medicine is a thriving application field for artificial intelligence (AI). Indeed, AI applications intended to forensic pathologists or forensic physicians have emerged since the last decade. For example, AI models were developed to help estimate the biological age of migrants or human remains. However, the uses of AI applications by forensic pathologists or physicians and their levels of integration in medicolegal practices are not well described yet. Therefore, a scoping review was conducted on PubMed, ScienceDirect, and Scopus databases. This review included articles that mention any AI application used by forensic pathologists or physicians in practice or any AI model applied in one expertise field of the forensic pathologist or physician. Articles in other languages than English or French or dealing mainly with complementary analyses handled by experts who are not forensic pathologists or physicians or with AI to analyze data for research purposes in forensic medicine were excluded from this review. All the relevant information was retrieved in each article from a grid analysis derived and adapted from the TRIPOD checklist. This review included 35 articles and revealed that AI applications are developed in thanatology and in clinical forensic medicine. However, those applications seem to mainly remain in research and development stages. Indeed, the use of AI applications by forensic pathologists or physicians is not actual due to issues discussed in this article. Finally, the integration of AI in daily medicolegal practice involves not only forensic pathologists or physicians but also legal professionals.

Automatic detection and identification of diatoms in complex background for suspected drowning cases through object detection models.

The diagnosis of drowning is one of the most difficult tasks in forensic medicine. The diatom test is a complementary analysis method that may help the forensic pathologist in the diagnosis of drowning and the localization of the drowning site. This test consists in detecting or identifying diatoms, unicellular algae, in tissue and water samples. In order to observe diatoms under light microscopy, those samples may be digested by enzymes such as proteinase K. However, this digestion method may leave high amounts of debris, leading thus to a difficult detection and identification of diatoms. To the best of our knowledge, no model is proved to detect and identify accurately diatom species observed in highly complex backgrounds under light microscopy. Therefore, a novel method of model development for diatom detection and identification in a forensic context, based on sequential transfer learning of object detection models, is proposed in this article. The best resulting models are able to detect and identify up to 50 species of forensically relevant diatoms with an average precision and an average recall ranging from 0.7 to 1 depending on the concerned species. The models were developed by sequential transfer learning and globally outperformed those developed by traditional transfer learning. The best model of diatom species identification is expected to be used in routine at the Medicolegal Institute of Paris.

Gene expression in Fusarium graminearum grown on plant cell wall.

Fusarium graminearum is a phytopathogenic filamentous fungus attacking a wide range of plants including Humulus lupulus (hop). Transcriptional analysis of F. graminearum grown on minimal media containing hop cell wall or glucose as the sole carbon source was performed by applying a highly stringent method combining microarrays and a subtracted cDNA library. In addition to genes coding for various cell wall degrading enzymes (CWDE), several metabolic pathways were induced in response to the plant cell wall substrate. Many genes participating in these pathways are probably involved in cellular transport. But the most interesting was that all the genes composing the 4-aminobutyrate-shunt (GABA-shunt) were also up-regulated in the presence of plant cell wall material and were present in the cDNA library. This study provides a description of a part of the fungal gene expression profile when it is in contact with raw biological materials, and helps in understanding the plant cell wall degradation and the infection process.

Resolving paternity relationships using X-chromosome STRs and Bayesian networks.

X-chromosomal short tandem repeats (X-STRs) are very useful in complex paternity cases because they are inherited by male and female offspring in different ways. They complement autosomal STRs (as-STRs) allowing higher paternity probabilities to be attained. These probabilities are expressed in a likelihood ratio (LR). The formulae needed to calculate LR depend on the genotype combinations of suspected pedigrees. LR can also be obtained by the use of Bayesian networks (BNs). These are graphical representations of real situations that can be used to easily calculate complex probabilities. In the present work, two BNs are presented, which are designed to derive LRs for half-sisters/half-sisters and mother/daughter/paternal grandmother relationships. These networks were validated against known formulae and show themselves to be useful in other suspect pedigree situations than those for which they were developed. The BNs were applied in two paternity cases. The application of the mother/daughter/paternal grandmother BN highlighted the complementary value of X-STRs to as-STRs. The same case evaluated without the mother underlined that missing information tends to be conservative if the alleged father is the biological father and otherwise nonconservative. The half-sisters case shows a limitation of statistical interpretations in regard to high allelic frequencies.

A rape case solved by mitochondrial DNA mixture analysis.

In cases of stains that contain mixed DNA from different contributors, analyzing mitochondrial DNA (mtDNA) requires the use of cloning techniques. We developed an efficient cloning technique that was applied in a rape case. After a differential lysis-based DNA extraction from vaginal swabs, hypervariable region I and II (HVI, HVII) amplicons obtained from the male fraction were cloned. Although we mainly found the victim's haplotype, we were able to detect the suspect's haplotype in two clones for HVI and in one clone for HVII. As the midpiece of the flagellum, which contains mitochondria, can be lost during the differential lysis, we also investigated the female fraction by cloning to evaluate the proportion of victim/suspect mtDNA. Unfortunately, only clones presenting the victim's haplotype were found. This case highlights the need for an optimal differential lysis protocol to enrich the male fraction not only with nuclear but also mitochondrial DNA.

Fusarium graminearum on plant cell wall: no fewer than 30 xylanase genes transcribed.

The transcription of a set of 32 putative xylanase genes from Fusarium graminearum was examined by quantitative PCR after growth on different carbon sources (hop cell wall, xylan, xylose, or carboxymethylcellulose). Growing on plant cell wall medium, this fungus displays a great diversity of expression of xylan-related genes, with 30 being induced. A second level of diversity exists because expression patterns can be very different for loci encoding enzymes with the same activity (the same EC number). The wealth of xylan-degrading enzymes and the differential expression confer on the fungus a great flexibility of reaction to variation in its environment.

An overview of fungal community diversity in diseased hop plantations.

Samples were taken from several hop fields presenting various symptoms. Fifty-nine pure filamentous fungal strains were isolated and identified through genomic DNA preparations, PCR amplification of the ribosomal DNA internal transcribed spacer region and database interrogations. The most frequent genera were Alternaria (16 isolates) and Epicoccum (14 isolates). The ecosystem was shown to be very diverse, since as many as 27 species belonging to 17 genera were recovered. Furthermore, many of the isolated fungi are known to be involved in phytopathogenesis.

Diversity of the exoproteome of Fusarium graminearum grown on plant cell wall.

The exoproteome of the fungus Fusarium graminearum grown on glucose and on hop (Humulus lupulus, L.) cell wall has been investigated. The culture medium was found to contain a higher quantity of proteins and the proteins are more diverse when the fungus is grown on cell wall. Using both 1D and 2D electrophoresis followed by mass spectrometry analysis and protein identification based on similarity searches, 84 unique proteins were identified in the cell wall-grown fungal exoproteome. Many are putatively implicated in carbohydrate metabolism, mainly in cell wall polysaccharide degradation. The predicted carbohydrate-active enzymes fell into 24 different enzymes classes, and up to eight different proteins within a same class are secreted. This indicates that fungal metabolism becomes oriented towards synthesis and secretion of a whole arsenal of enzymes able to digest almost the complete plant cell wall. Cellobiohydrolase is one of the only four proteins found both after growth on glucose and on plant cell wall and we propose that this enzyme could act as a sensor of the extracellular environment. Extensive knowledge of this very diverse F. graminearum exoproteome is an important step towards the full understanding of Fusarium/plants interactions.

Use of genes encoding cellobiohydrolase-C and topoisomerase II as targets for phylogenetic analysis and identification of Fusarium.

Molecular identification and phylogenetic studies rely to a large extent on rDNA sequence polymorphism. In the field of fungal taxonomy, despite the use of huge amounts of rDNA data available, some species within a given genus remain indistinguishable. Therefore, new target sequences need to be selected and validated. This is the case for Fusarium, which includes numerous species most of which are involved in both animal and plant pathologies. In addition to the rDNA fragment encompassing the internal transcribed spacers ITS1 and ITS2 and the 5.8 S sequence, two newly characterized genes were used as molecular markers for Fusarium species genotyping. The cellobiohydrolase-C (cbh-C) and the topoisomerase II (topII) gene parts were cloned and sequenced for at least one isolate of each of the eleven different species of our collection. Both cbh-C and topII were found to be single copy genes. DNA fragments amplified by PCR in order to establish phylogenetic trees range from 1123 to 1157 bp for rDNA and from 327 to 344 bp for cbh-C (this part contains one intron). The topII gene part encoding the carboxy-terminus of the ATP binding domain of the enzyme is constant in length with a value of 724 bp. PAUP-generated phylogenetic analyses based either on cbh-C or topII data enabled all species to be distinguished, and were more informative than those resulting from rDNA sequences. Furthermore, a combination of the three datasets enhanced the accuracy of the analyses and open up new possibilities for rapid molecular identification and evolution studies within the Fusarium genus.

Application of a yeast method for DNA extraction associated with database interrogations for the characterization of various filamentous fungi from diseased hop.

Filamentous fungi were collected from diseased hop (Humulus lupulus; L.) and DNA was prepared from 19 isolates. The critical step of cell lysis was carried out using zymolyase for fungal cell wall digestion. DNA was successfully prepared for all isolates and allowed ribosomal DNA region amplifications by PCR. The amplicons were sequenced and sequences were compared with nucleotides databases. These analyses allowed identification of each fungus and gave a precise view of the ecosystem. Seven different genera were found among the 19 isolates. A phylogenetic tree was constructed and revealed the diversity of the hop plant environment.

Development of a bipartite method for Fusarium identification based on cellobiohydrolase-C: CAPS and Western blot analysis.

The identification of 12 Fusarium strains isolated from diseased hops (Humulus lupulus, L.) was achieved by a strategy based on cellobiohydrolase-C: cleaved amplified polymorphic sequence analysis targeting the gene and the use of an antibody directed against a peptide of the Fusarium graminearum enzyme. This strategy is shown to be rapid and reliable for all the Fusarium of our collection: F. avenaceum, F. graminearum, F. sambucinum, F. sporotrichioides, F. tricinctum and F. venenatum.