Artificially intelligent scoring and classification engine for forensic identification.

08:00 EDT 19th September 2019 | BioPortfolio

Summary of "Artificially intelligent scoring and classification engine for forensic identification."

Despite advances in genotyping technologies, traditional kinship analysis tools utilized in forensic identification have seen limited evolution and lack measures of accuracy. Here, we leverage artificial intelligence (AI) and extend the Elston-Stewart algorithm to deliver a method that provides an unprecedented level of flexibility to matching individuals with pedigrees by likelihood ratio. We designed an AI that utilizes a prediction cascade based on gradient descent logistic regression which allows for iterative solution of multi missing person scenarios. Furthermore, the AI can quantify the confidence underlying likelihood ratios across the spectrum of pedigrees, regardless of the amount of genetic information available and the number of missing persons. The algorithm accommodates an arbitrary number of generations and ancestral relationships, including multiple marriages, mutations, and consanguinity. We demonstrate that a properly trained AI significantly and reproducibly outperforms a human interpreter. We discuss published limitations of existing tools and demonstrate that they are not amenable to the size and complexity of this study. This novel method significantly improves the trade-off between sensitivity and specificity beyond the limits of traditional kinship analysis tools and introduces opportunities beyond the field of forensic genetics.


Journal Details

This article was published in the following journal.

Name: Forensic science international. Genetics
ISSN: 1878-0326
Pages: 102162


DeepDyve research library

PubMed Articles [7604 Associated PubMed Articles listed on BioPortfolio]

The Use of Artificially Intelligent Self-Diagnosing Digital Platforms by the General Public: Scoping Review.

Self-diagnosis is the process of diagnosing or identifying a medical condition in oneself. Artificially intelligent digital platforms for self-diagnosis are becoming widely available and are used by t...

Accurate peptide fragmentation predictions allow data driven approaches to replace and improve upon proteomics search engine scoring functions.

The use of post-processing tools to maximize the information gained from a proteomics search engine is widely accepted and used by the community, with the most notable example being Percolator - a sem...

A Pilot Study Comparing Postmortem and Antemortem CT for the Identification of Unknowns: Could a Forensic Pathologist Do It?

Forensic pathologists are commonly tasked with identifying human remains. Although DNA analysis remains the gold standard in identification, time and cost make it particularly prohibitive. Radiologica...

An automatic single-channel EEG-based sleep stage scoring method based on hidden Markov model.

Sleep stage scoring is essential for diagnosing sleep disorders. Visual scoring of sleep stages is very time-consuming and prone to human errors. In this work, we introduce an efficient approach to im...

Geometric morphometric analysis of sexual dimorphism in the mandible from panoramic X-ray images.

The human mandible is routinely utilised as part of the assessment of biological identity in forensic anthropological and odontological practice. The research introduces a novel geometric morphometric...

Clinical Trials [2372 Associated Clinical Trials listed on BioPortfolio]

The Accuracy of an Artificially-Intelligent Stethoscope

This study will characterize the accuracy of a commercially available artificially-intelligent stethoscope in determining which childhood murmurs suggest underlying congenital structural h...

Traumatic Characteristics of the Forensic Cases Admitted to Emergency Department and Errors in the Forensic Reports

Objectives: to detect the mistakes and deficiencies of the forensic reports which was written and to detect the injury characteristics of the forensic cases applied to emergency service of...

VALIDATE: Virtual Agent Linked Intelligent Disease Assessment Tool Engine

The collection and analysis of family, medical, lifestyle, and environmental exposure history (a Comprehensive Health History or "CHH") can identify critical risk factors for many chronic ...

An Engagement Engine for Fitness Trackers

The iTrackFitness study aims to test the "engagement engine" that was developed from activity tracker and survey data gathered during phase I of the study. For the current phase the "engag...

An Evaluation of an Adapted STEPPS Group Within Forensic Services

The purpose of this study is to determine how effective the STEPPS-HI group is at improving emotional regulation skills in those with identified difficulties in this area within forensic i...

Medical and Biotech [MESH] Definitions

Scientific study of human skeletal remains with the express purpose of identification. This includes establishing individual identity, trauma analysis, facial reconstruction, photographic superimposition, determination of time interval since death, and crime-scene recovery. Forensic anthropologists do not certify cause of death but provide data to assist in determination of probable cause. This is a branch of the field of physical anthropology and qualified individuals are certified by the American Board of Forensic Anthropology. (From Am J Forensic Med Pathol 1992 Jun;13(2):146)

Disciplines that apply sciences to law. Forensic sciences include a wide range of disciplines, such as FORENSIC TOXICOLOGY; FORENSIC ANTHROPOLOGY; FORENSIC MEDICINE; FORENSIC DENTISTRY; and others.

Techniques for standardizing and expediting taxonomic identification or classification of organisms that are based on deciphering the sequence of one or a few regions of DNA known as the "DNA barcode".

An alpha-globulin found in the plasma of man and other vertebrates. It is apparently synthesized in the liver and carries vitamin D and its metabolites through the circulation and mediates the response of tissue. It is also known as group-specific component (Gc). Gc subtypes are used to determine specific phenotypes and gene frequencies. These data are employed in the classification of population groups, paternity investigations, and in forensic medicine.

Tabular numerical representations of sequence motifs displaying their variability as likelihood values for each possible residue at each position in a sequence. Position-specific scoring matrices (PSSMs) are calculated from position frequency matrices.

Quick Search

DeepDyve research library

Searches Linking to this Article