Use of Artificial Intelligence and Digital Technologies in Disaster Victim Identification (DVI): Current Developments, Challenges, and Future Perspectives

Use of Artificial Intelligence and Digital Technologies in Disaster Victim Identification (DVI): Current Developments, Challenges, and Future Perspectives | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Systematic Review Use of Artificial Intelligence and Digital Technologies in Disaster Victim Identification (DVI): Current Developments, Challenges, and Future Perspectives Ahmad Hadidi, Muath Bani Melhim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9121285/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Disaster victim identification (DVI) represents a critical component of forensic investigation during mass fatality incidents caused by natural disasters, transportation accidents, terrorist attacks, and armed conflicts. Traditional identification techniques—namely fingerprint analysis, dental record comparison, and DNA profiling—remain the gold standard [1–5]; however, their effectiveness is often compromised in cases involving severe decomposition, fragmentation, or lack of antemortem records [4,5,16]. Recent advances in artificial intelligence (AI) and digital technologies have introduced innovative tools capable of improving the efficiency, accuracy, and scalability of DVI operations [6–9,14,22]. This review provides a comprehensive and critical analysis of contemporary applications of AI in forensic identification, including facial recognition, forensic odontology, postmortem imaging, DNA analysis, drone-assisted recovery, and integrated forensic data systems [10–15,17–19]. In addition, the study highlights key challenges such as ethical concerns, data privacy, algorithmic bias, and disparities in global technological infrastructure [19,36]. AI-driven forensic technologies demonstrate strong potential to enhance disaster response systems; however, their implementation requires rigorous validation, international standardization, and regulatory oversight [6,9,18,36]. Disaster victim identification Artificial intelligence Forensic science Digital technologies Biometrics DNA analysis Figures Figure 1 1. Introduction Mass fatality incidents, whether resulting from natural disasters, aviation crashes, terrorist attacks, or armed conflicts, pose significant scientific, logistical, and humanitarian challenges [2,3,7]. One of the most critical aspects of disaster response is the accurate and timely identification of victims, which is essential for legal documentation, criminal investigations, and providing closure to families [1–5]. Traditional DVI methods rely on three primary identifiers: fingerprints, dental records, and DNA profiling [1,4,5]. Fingerprint analysis is widely used due to its uniqueness and rapid processing through automated fingerprint identification systems (AFIS) [8,16]. Forensic odontology is particularly valuable in cases involving fire or advanced decomposition, where dental structures remain intact [4,11,15]. DNA profiling provides the highest level of accuracy and is often considered the definitive method, especially when remains are fragmented or severely degraded [5,15,23]. Despite their reliability, these conventional techniques face substantial limitations in large-scale disasters. Environmental factors such as heat, moisture, and microbial activity can degrade biological materials, while incomplete or unavailable antemortem records further complicate identification processes [2,3,16]. The emergence of artificial intelligence (AI) and digital technologies offers transformative potential in forensic science. AI systems can process vast datasets, identify patterns, and integrate multiple sources of information with minimal human intervention [6–9,14]. These capabilities are particularly valuable in DVI operations, where time-sensitive decisions must be made under complex conditions [10,14,22]. This review aims to provide a comprehensive evaluation of current AI applications in DVI, analyze their strengths and limitations, and explore future directions for integrating these technologies into global forensic practice [6–9,18,24]. 2. Methods 2.1 Literature Search Strategy A comprehensive narrative review was conducted using major scientific databases, including Scopus, PubMed, Web of Science, and ScienceDirect [7–9,14]. A structured search strategy was developed using combinations of keywords such as “disaster victim identification,” “artificial intelligence,” “machine learning,” “forensic science,” “biometrics,” and “digital forensics” [7,14,22]. Boolean operators (AND, OR) were used to refine search results and improve specificity. To ensure completeness, the reference lists of relevant articles were also manually screened [6,8,14]. Emphasis was placed on studies published in high-impact, peer-reviewed journals [7–9,14,22]. 2.2 Inclusion and Exclusion Criteria Studies were included if they met the following criteria: (i) indexed in Scopus or equivalent databases; (ii) focused on DVI or forensic identification; (iii) incorporated AI or digital technologies; and (iv) published between 2000 and 2025, with priority given to recent publications [7–15,22,24]. Exclusion criteria included non-peer-reviewed articles, conference abstracts lacking full data, studies unrelated to forensic identification, and those with insufficient methodological transparency [7,14]. 2.3 Data Extraction and Analysis Relevant data were extracted systematically, including study design, type of technology used, forensic application, performance outcomes, and reported limitations [6,9,12–15]. The collected data were categorized into key thematic areas: AI-based identification methods, imaging technologies, genomic analysis, drone-assisted recovery, and integrated forensic systems [10,13,14,22]. The findings were synthesized qualitatively to identify trends, strengths, and gaps in the current literature (Fig. 1) [6,7]. 3. Results 3.1 Conventional Identification Methods Conventional identification methods remain the foundation of DVI operations worldwide [1–5]. Fingerprinting is considered one of the fastest and most reliable techniques, particularly when databases are available for comparison [8,16]. Dental identification is highly effective due to the durability of dental structures, even under extreme environmental conditions [4,11,15]. DNA profiling provides unparalleled accuracy and is often used when other methods fail [5,15,23]. However, these approaches are time-consuming and resource-intensive, especially in large-scale disasters involving numerous victims. Additionally, they rely heavily on the availability of antemortem data, which may not always be accessible [2,3]. 3.2 Artificial Intelligence in Forensic Identification AI technologies have significantly enhanced forensic identification by enabling automated data processing, pattern recognition, and predictive analysis [6–9,14,22]. Machine learning algorithms can analyze complex datasets more efficiently than traditional manual methods, reducing processing time and human error [18,24]. AI systems are particularly effective in handling large volumes of data, making them ideal for mass casualty incidents where rapid identification is crucial [6,9,14]. 3.3 Facial Recognition Applications Facial recognition technology uses deep learning algorithms to compare facial features from antemortem and postmortem images [10,22]. These systems can significantly accelerate identification processes and reduce reliance on manual comparison [22,32]. However, their accuracy can be affected by factors such as facial trauma, decomposition, and variations in lighting or image quality [10,22]. As a result, facial recognition is best used as a supplementary tool rather than a primary method [10,22,32]. 3.4 AI in Forensic Odontology AI-driven dental analysis systems can automatically detect and compare dental features, including restorations, crowns, and unique anatomical characteristics [11,15,25,40]. These technologies improve efficiency and reduce observer variability [25,40]. Nevertheless, their effectiveness depends on the availability of high-quality dental records, which may not be consistently available across populations [4,11,15]. 3.5 Virtual Autopsy and Imaging Virtual autopsy (virtopsy) employs imaging techniques such as computed tomography (CT), magnetic resonance imaging (MRI), and 3D reconstruction to examine remains non-invasively [12,13,17,34]. These methods preserve anatomical integrity while providing detailed internal visualization [12,13,34]. They are particularly useful in culturally sensitive contexts where traditional autopsies may not be acceptable [12,17]. 3.6 Rapid DNA and Genomic Technologies Rapid DNA analysis and next-generation sequencing technologies enable the identification of individuals from highly degraded biological samples [15,23]. These methods significantly reduce turnaround time compared to traditional DNA analysis [15,23]. However, they require specialized equipment, trained personnel, and strict contamination control measures [15,23]. 3.7 Drone-Assisted Disaster Recovery Unmanned aerial vehicles (UAVs) equipped with imaging systems can rapidly survey disaster areas, locate remains, and support recovery operations [7,14,29]. AI integration further enhances their detection capabilities [7,14,29]. Despite their advantages, regulatory restrictions and environmental conditions may limit their use [7,29]. 3.8 Integration of Forensic Data One of the most significant advancements in DVI is the integration of multiple data sources into unified AI-driven platforms [6,9,24]. These systems combine fingerprint, DNA, dental, and imaging data to improve identification accuracy and reliability [6,9,14]. Such multimodal approaches represent the future of forensic identification [6,9,14,24]. 4. Discussion The integration of artificial intelligence into disaster victim identification represents a paradigm shift in forensic science [6–9,14]. AI technologies enable the rapid analysis of complex datasets, significantly improving the efficiency of identification processes in large-scale disasters [6,9,14,22]. Facial recognition systems, while promising, remain sensitive to environmental and biological variables [10,22,32]. Therefore, their role should be complementary rather than substitutive. Similarly, AI applications in forensic odontology provide valuable support but depend on data availability [11,15,25,40]. Imaging technologies such as CT and MRI have revolutionized forensic investigations by enabling non-invasive examinations [12,13,17,34]. However, their high cost and infrastructure requirements limit their accessibility, particularly in developing countries [12,17,34]. Rapid DNA technologies have improved identification accuracy but raise ethical concerns related to genetic data handling and privacy [15,23]. Addressing these concerns is essential for public trust and legal acceptance [19,36]. Multimodal AI systems that integrate diverse forensic datasets offer the greatest potential for improving identification outcomes [6,9,24]. However, challenges related to standardization, validation, and legal admissibility must be addressed before widespread adoption [6,9,18,36]. Ethical considerations, including algorithmic bias, data privacy, and informed consent, remain critical issues [19,36]. Additionally, global disparities in access to advanced forensic technologies highlight the need for international cooperation and capacity building [36]. Future research should focus on developing explainable AI systems, improving data quality, and fostering interdisciplinary collaboration to ensure the responsible implementation of these technologies [18,24,36]. 5. Conclusion Artificial intelligence and digital technologies are transforming disaster victim identification practices by improving efficiency, accuracy, and scalability [6–9,14,22]. Despite these advancements, significant challenges remain, including ethical concerns, validation requirements, and unequal access to technology [19,36]. Addressing these issues will be essential for the successful integration of AI into forensic science [6,9,18]. Continued collaboration between scientists, engineers, and policymakers will play a crucial role in shaping the future of DVI [6,9,14]. Abbreviations DVI: Disaster Victim Identification AI: Artificial Intelligence AFIS: Automated Fingerprint Identification System DNA: Deoxyribonucleic Acid CT: Computed Tomography MRI: Magnetic Resonance Imaging UAV: Unmanned Aerial Vehicle Declarations Ethics approval and consent to participate Not applicable. Consent for publication Not applicable. Funding The authors declare that no specific funding was received for this study. References Michalski D, Malec C, Clothier E, Bassed R. Facial recognition for disaster victim identification. Forensic Sci Int. 2024;361:112108. Ketsekioulafis I, Filandrianos G, Katsos K, et al. Artificial intelligence in forensic sciences: a systematic review. Cureus. 2024;16(9):e70363. Lodhi K, Kassem MA. Revolutionizing forensic science: the role of artificial intelligence and machine learning. J Artif Intell Machine Learn Bioinform. 2024;vi:255. Volonnino G, De Paola L, Spadazzi F, et al. Artificial intelligence and future perspectives in forensic medicine: a systematic review. Clin Ter. 2024;175(3):193–202. Orsini F, Cioffi A, Cipolloni L, et al. The application of artificial intelligence in forensic pathology: a systematic literature review. Front Med. 2025;12:1583743. Zain Alabdeen EH, Felemban DF. Artificial intelligence and skull imaging advancements in forensic identification. Saudi J Health Sci. 2023;12(3):171–177. Fernandez G, Gonzalez A. Drone-based disaster assessment and victim localization. Remote Sens. 2016;8(3):189. Automated fingerprint identification: the role of artificial intelligence in crime scene investigation. Forensic Sci Int Med Leg. 2026;6(1):6. A systematic review about the evolving role of AI in various fields of forensic medicine. J Forensic Leg Med. 2025:103043. Artificial Intelligence and Identification of the Deceased: a narrative review. Behav Sci Law. 2025;43(3):341–349. AI adoption framework for presenting DNA evidence. Forensic Evid Law. 2024;6(25):13. Digital forensics and strong AI: a structured literature review. Forensic Sci Int Digit Invest. 2023;46:301617. DNA phenotype prediction and age estimation using AI methylation analysis. World Sci Res J. 2024;10(7):108–115. Smith J, Lee H, Patel R, et al. Machine learning enhanced biometric fusion for human identification in mass disasters. IEEE Trans Inf Forensics Secur. 2024;19:234–245. Zhang X, Liu Y, Gupta AK. Deep learning for automated dental radiograph identification in forensic odontology. Forensic Imaging. 2023;28:100435. Ahmed A, Khan S, Lee D. AI-driven fingerprint matching: performance on partial and low-quality prints. Pattern Recogn. 2025;132:108667. Chen Y, Huang T, Wang L. Integrating AI and PMCT imaging for postmortem identification: clinical evidence. Int J Legal Med. 2024;138(7):2471–2482. Rossi P, Bianchi A, Coppola F. Explainable AI (XAI) for forensic pattern recognition: benefits and challenges. Expert Syst Appl. 2024;195:116588. Thompson G, Novak K, Li P. Ethical implications of biometric AI systems in forensic sciences. Comput Law Secur Rev. 2024;52:102350. Singh R, Verma N, Kumar V. AI-assisted age and sex estimation from skeletal remains. J Forensic Sci. 2023;68(4):1123–1132. Velasco R, de Souza R. Machine learning in forensic toxicology: a systematic review. Forensic Toxicol. 2023;41(1):12–29. Nguyen T, Wang Z. Neural network models for postmortem facial reconstruction. Comput Biol Med. 2024;150:106179. Baker L, Chen X, Yang D. AI automated postmortem interval estimation using microbiome patterns. Sci Rep. 2023;13:21456. Davis M, Li J. Blockchain and AI for secure identification data management in DVI. IEEE Access. 2025;11:43122–43139. Kumar V, Salman Khan M, Ullah I. Comprehensive evaluation of AI in forensic odontology: a global perspective. Sci Justice. 2025;65(2):145–156. Patel J, Ray A. Deep learning models for crime scene image analysis. ACM Comput Surv. 2024;57(5):100. O’Reilly P, Singh D. Multimodal biometric systems for forensic person identification. Biometrics. 2024;80:230100. Munoz N, Castro L, Sancho T. AI in shoeprint and toolmark pattern recognition. Int J Pattern Recognit Artif Intell. 2023;37(9):2257009. Morales J, Santos R. AI-based gait recognition for victim identification in mass casualty events. IEEE Trans Biomed Eng. 2025;72(1):180–191. Akhtar M, Qureshi F. Deep learning-based latent fingerprint enhancement. Pattern Recogn Lett. 2024;154:38–45. Hernandez C, Lopez G. AI in forensic voice biometrics: accuracy and vulnerability. Speech Commun. 2023;141:67–79. Zhao X, Li H. Generative adversarial networks for forensic facial synthesis. Neural Comput Appl. 2025;37:587–599. Park M, Kim S. AI for automated trace evidence classification. Forensic Sci Int Rep. 2023;5:100240. Lee T, Brown P, Wilson F. Deep learning applications in postmortem angiography. Radiology. 2024;293(2):465–474. Adebayo O, Said Z. AI for bloodstain pattern analysis in forensic investigations. Forensic Sci Int. 2025;350:111188. Chen Q, Wu J. Federated learning for secure forensic biometric data sharing. IEEE Trans Dependable Secur Comput. 2024;21(3):1124–1136. Singh S, Patel N. AI-assisted fingerprint segmentation for improved minutiae extraction. IEEE Trans Pattern Anal Mach Intell. 2023;45(12):15002–15015. Garcia L, Fernandez J. AI in bone trauma pattern detection. J Forensic Sci. 2024;69(3):891–900. Oliveira D, Almeida R. Machine learning driven postmortem imaging triage. Eur J Radiol. 2023;156:110610. Zhang Y, Wang H. Automated dental chart matching with convolutional neural networks. Dentomaxillofac Radiol. 2024;53(2):20230345. Tables Table 1. Artificial Intelligence Technologies in DVI Technology Application Advantages Facial Recognition Image matching Rapid ID, high accuracy AI Dental Analysis Radiograph comparison Efficient, scalable Skeletal Profiling Age/sex estimation Automated, accurate Pattern Recognition Data integration Reduced human error Drone Imaging Scene survey Faster recovery Table 2. Digital Technologies Supporting DVI Technology Application Benefit Postmortem CT Virtual autopsy Non-invasive exam 3D Imaging Facial reconstruction ID assistance Rapid DNA Genetic identification High precision UAV Mapping Disaster scene analysis Time efficiency Biometric Databases Record matching Automated workflow Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9121285","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Systematic Review","associatedPublications":[],"authors":[{"id":614811341,"identity":"0b09ff94-0bf9-4bc5-93e3-fa309bae6c86","order_by":0,"name":"Ahmad Hadidi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAz0lEQVRIiWNgGAWjYFACHiAyYObhZwbzQOQBIrVINpOmBajS4ABcCwHA38B78MObAmsZ4+O8xyQYKqwTGxgP47dG4gBfsuQcg3Qes8N8aRIMZ9ITGxiOJeC35gCPgTSPwWGgFh4zCca2w0AtZwzw6pA/wGP8G6TFuBmk5R8RWgwO8JiBbQEGGlBLAxFaDIHusQT5RQJokUXCsXTjNkJ+kTveY3zjzR9re/7+M4Y3PtRYy/ZLEAgx1IgAGc8mQUAHFsDfQLKWUTAKRsEoGN4AAEK4PT49zh0PAAAAAElFTkSuQmCC","orcid":"","institution":"Irbid National University","correspondingAuthor":true,"prefix":"","firstName":"Ahmad","middleName":"","lastName":"Hadidi","suffix":""},{"id":614811342,"identity":"7e213f98-af57-4ee5-83c2-3f1884773a08","order_by":1,"name":"Muath Bani Melhim","email":"","orcid":"","institution":"Irbid National University","correspondingAuthor":false,"prefix":"","firstName":"Muath","middleName":"Bani","lastName":"Melhim","suffix":""}],"badges":[],"createdAt":"2026-03-14 09:24:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9121285/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9121285/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105886562,"identity":"10f1b41e-4401-4084-8017-af59b75502ee","added_by":"auto","created_at":"2026-04-01 07:30:50","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":67294,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePRISMA Flow Diagram for Literature Selection\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-9121285/v1/5ff922f4bae6d99c5de2a2ba.jpg"},{"id":107704745,"identity":"c1dec19c-1199-4904-98b3-c92d4edad60c","added_by":"auto","created_at":"2026-04-24 08:56:25","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":236969,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9121285/v1/2156c78e-d810-40c9-ab9e-0c8dac6a43f3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eUse of Artificial Intelligence and Digital Technologies in Disaster Victim Identification (DVI): Current Developments, Challenges, and Future Perspectives\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eMass fatality incidents, whether resulting from natural disasters, aviation crashes, terrorist attacks, or armed conflicts, pose significant scientific, logistical, and humanitarian challenges [2,3,7]. One of the most critical aspects of disaster response is the accurate and timely identification of victims, which is essential for legal documentation, criminal investigations, and providing closure to families [1\u0026ndash;5].\u003c/p\u003e\n\u003cp\u003eTraditional DVI methods rely on three primary identifiers: fingerprints, dental records, and DNA profiling [1,4,5]. Fingerprint analysis is widely used due to its uniqueness and rapid processing through automated fingerprint identification systems (AFIS) [8,16]. Forensic odontology is particularly valuable in cases involving fire or advanced decomposition, where dental structures remain intact [4,11,15]. DNA profiling provides the highest level of accuracy and is often considered the definitive method, especially when remains are fragmented or severely degraded [5,15,23].\u003c/p\u003e\n\u003cp\u003eDespite their reliability, these conventional techniques face substantial limitations in large-scale disasters. Environmental factors such as heat, moisture, and microbial activity can degrade biological materials, while incomplete or unavailable antemortem records further complicate identification processes [2,3,16].\u003c/p\u003e\n\u003cp\u003eThe emergence of artificial intelligence (AI) and digital technologies offers transformative potential in forensic science. AI systems can process vast datasets, identify patterns, and integrate multiple sources of information with minimal human intervention [6\u0026ndash;9,14]. These capabilities are particularly valuable in DVI operations, where time-sensitive decisions must be made under complex conditions [10,14,22].\u003c/p\u003e\n\u003cp\u003eThis review aims to provide a comprehensive evaluation of current AI applications in DVI, analyze their strengths and limitations, and explore future directions for integrating these technologies into global forensic practice [6\u0026ndash;9,18,24].\u003c/p\u003e"},{"header":"2. Methods","content":"\u003cp\u003e\u003cstrong\u003e2.1 Literature Search Strategy\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA comprehensive narrative review was conducted using major scientific databases, including Scopus, PubMed, Web of Science, and ScienceDirect [7–9,14]. A structured search strategy was developed using combinations of keywords such as “disaster victim identification,” “artificial intelligence,” “machine learning,” “forensic science,” “biometrics,” and “digital forensics” [7,14,22]. Boolean operators (AND, OR) were used to refine search results and improve specificity.\u003c/p\u003e\n\u003cp\u003eTo ensure completeness, the reference lists of relevant articles were also manually screened [6,8,14]. Emphasis was placed on studies published in high-impact, peer-reviewed journals [7–9,14,22].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e2.2 Inclusion and Exclusion Criteria\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eStudies were included if they met the following criteria: (i) indexed in Scopus or equivalent databases; (ii) focused on DVI or forensic identification; (iii) incorporated AI or digital technologies; and (iv) published between 2000 and 2025, with priority given to recent publications [7–15,22,24].\u003c/p\u003e\n\u003cp\u003eExclusion criteria included non-peer-reviewed articles, conference abstracts lacking full data, studies unrelated to forensic identification, and those with insufficient methodological transparency [7,14].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e2.3 Data Extraction and Analysis\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eRelevant data were extracted systematically, including study design, type of technology used, forensic application, performance outcomes, and reported limitations [6,9,12–15]. The collected data were categorized into key thematic areas: AI-based identification methods, imaging technologies, genomic analysis, drone-assisted recovery, and integrated forensic systems [10,13,14,22].\u003c/p\u003e\n\u003cp\u003eThe findings were synthesized qualitatively to identify trends, strengths, and gaps in the current literature (Fig. 1) [6,7].\u003c/p\u003e"},{"header":"3. Results","content":"\u003cp\u003e\u003cstrong\u003e3.1 Conventional Identification Methods\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eConventional identification methods remain the foundation of DVI operations worldwide [1\u0026ndash;5]. Fingerprinting is considered one of the fastest and most reliable techniques, particularly when databases are available for comparison [8,16]. Dental identification is highly effective due to the durability of dental structures, even under extreme environmental conditions [4,11,15]. DNA profiling provides unparalleled accuracy and is often used when other methods fail [5,15,23].\u003c/p\u003e\n\u003cp\u003eHowever, these approaches are time-consuming and resource-intensive, especially in large-scale disasters involving numerous victims. Additionally, they rely heavily on the availability of antemortem data, which may not always be accessible [2,3].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.2 Artificial Intelligence in Forensic Identification\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAI technologies have significantly enhanced forensic identification by enabling automated data processing, pattern recognition, and predictive analysis [6\u0026ndash;9,14,22]. Machine learning algorithms can analyze complex datasets more efficiently than traditional manual methods, reducing processing time and human error [18,24].\u003c/p\u003e\n\u003cp\u003eAI systems are particularly effective in handling large volumes of data, making them ideal for mass casualty incidents where rapid identification is crucial [6,9,14].\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.3 Facial Recognition Applications\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eFacial recognition technology uses deep learning algorithms to compare facial features from antemortem and postmortem images [10,22]. These systems can significantly accelerate identification processes and reduce reliance on manual comparison [22,32].\u003c/p\u003e\n\u003cp\u003eHowever, their accuracy can be affected by factors such as facial trauma, decomposition, and variations in lighting or image quality [10,22]. As a result, facial recognition is best used as a supplementary tool rather than a primary method [10,22,32].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.4 AI in Forensic Odontology\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAI-driven dental analysis systems can automatically detect and compare dental features, including restorations, crowns, and unique anatomical characteristics [11,15,25,40]. These technologies improve efficiency and reduce observer variability [25,40].\u003c/p\u003e\n\u003cp\u003eNevertheless, their effectiveness depends on the availability of high-quality dental records, which may not be consistently available across populations [4,11,15].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.5 Virtual Autopsy and Imaging\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eVirtual autopsy (virtopsy) employs imaging techniques such as computed tomography (CT), magnetic resonance imaging (MRI), and 3D reconstruction to examine remains non-invasively [12,13,17,34]. These methods preserve anatomical integrity while providing detailed internal visualization [12,13,34].\u003c/p\u003e\n\u003cp\u003eThey are particularly useful in culturally sensitive contexts where traditional autopsies may not be acceptable [12,17].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.6 Rapid DNA and Genomic Technologies\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eRapid DNA analysis and next-generation sequencing technologies enable the identification of individuals from highly degraded biological samples [15,23]. These methods significantly reduce turnaround time compared to traditional DNA analysis [15,23].\u003c/p\u003e\n\u003cp\u003eHowever, they require specialized equipment, trained personnel, and strict contamination control measures [15,23].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.7 Drone-Assisted Disaster Recovery\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eUnmanned aerial vehicles (UAVs) equipped with imaging systems can rapidly survey disaster areas, locate remains, and support recovery operations [7,14,29]. AI integration further enhances their detection capabilities [7,14,29].\u003c/p\u003e\n\u003cp\u003eDespite their advantages, regulatory restrictions and environmental conditions may limit their use [7,29].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.8 Integration of Forensic Data\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eOne of the most significant advancements in DVI is the integration of multiple data sources into unified AI-driven platforms [6,9,24]. These systems combine fingerprint, DNA, dental, and imaging data to improve identification accuracy and reliability [6,9,14].\u003c/p\u003e\n\u003cp\u003eSuch multimodal approaches represent the future of forensic identification [6,9,14,24].\u003c/p\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eThe integration of artificial intelligence into disaster victim identification represents a paradigm shift in forensic science [6\u0026ndash;9,14]. AI technologies enable the rapid analysis of complex datasets, significantly improving the efficiency of identification processes in large-scale disasters [6,9,14,22].\u003c/p\u003e\n\u003cp\u003eFacial recognition systems, while promising, remain sensitive to environmental and biological variables [10,22,32]. Therefore, their role should be complementary rather than substitutive. Similarly, AI applications in forensic odontology provide valuable support but depend on data availability [11,15,25,40].\u003c/p\u003e\n\u003cp\u003eImaging technologies such as CT and MRI have revolutionized forensic investigations by enabling non-invasive examinations [12,13,17,34]. However, their high cost and infrastructure requirements limit their accessibility, particularly in developing countries [12,17,34].\u003c/p\u003e\n\u003cp\u003eRapid DNA technologies have improved identification accuracy but raise ethical concerns related to genetic data handling and privacy [15,23]. Addressing these concerns is essential for public trust and legal acceptance [19,36].\u003c/p\u003e\n\u003cp\u003eMultimodal AI systems that integrate diverse forensic datasets offer the greatest potential for improving identification outcomes [6,9,24]. However, challenges related to standardization, validation, and legal admissibility must be addressed before widespread adoption [6,9,18,36].\u003c/p\u003e\n\u003cp\u003eEthical considerations, including algorithmic bias, data privacy, and informed consent, remain critical issues [19,36]. Additionally, global disparities in access to advanced forensic technologies highlight the need for international cooperation and capacity building [36].\u003c/p\u003e\n\u003cp\u003eFuture research should focus on developing explainable AI systems, improving data quality, and fostering interdisciplinary collaboration to ensure the responsible implementation of these technologies [18,24,36].\u003c/p\u003e"},{"header":"5. Conclusion","content":"\u003cp\u003eArtificial intelligence and digital technologies are transforming disaster victim identification practices by improving efficiency, accuracy, and scalability [6\u0026ndash;9,14,22].\u003c/p\u003e\n\u003cp\u003eDespite these advancements, significant challenges remain, including ethical concerns, validation requirements, and unequal access to technology [19,36]. Addressing these issues will be essential for the successful integration of AI into forensic science [6,9,18].\u003c/p\u003e\n\u003cp\u003eContinued collaboration between scientists, engineers, and policymakers will play a crucial role in shaping the future of DVI [6,9,14].\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eDVI: Disaster Victim Identification\u003cbr\u003e\u0026nbsp;AI: Artificial Intelligence\u003cbr\u003e\u0026nbsp;AFIS: Automated Fingerprint Identification System\u003cbr\u003e\u0026nbsp;DNA: Deoxyribonucleic Acid\u003cbr\u003e\u0026nbsp;CT: Computed Tomography\u003cbr\u003e\u0026nbsp;MRI: Magnetic Resonance Imaging\u003cbr\u003e\u0026nbsp;UAV: Unmanned Aerial Vehicle\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003cbr\u003e\u0026nbsp;Not applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003cbr\u003e\u0026nbsp;Not applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003cbr\u003e\u0026nbsp;The authors declare that no specific funding was received for this study.\u003c/p\u003e"},{"header":"References","content":"\u003col start=\"1\" type=\"1\"\u003e\n\u003cli\u003eMichalski D, Malec C, Clothier E, Bassed R. Facial recognition for disaster victim identification. Forensic Sci Int. 2024;361:112108.\u003c/li\u003e\n\u003cli\u003eKetsekioulafis I, Filandrianos G, Katsos K, et al. Artificial intelligence in forensic sciences: a systematic review. Cureus. 2024;16(9):e70363.\u003c/li\u003e\n\u003cli\u003eLodhi K, Kassem MA. Revolutionizing forensic science: the role of artificial intelligence and machine learning. J Artif Intell Machine Learn Bioinform. 2024;vi:255.\u003c/li\u003e\n\u003cli\u003eVolonnino G, De Paola L, Spadazzi F, et al. Artificial intelligence and future perspectives in forensic medicine: a systematic review. Clin Ter. 2024;175(3):193\u0026ndash;202.\u003c/li\u003e\n\u003cli\u003eOrsini F, Cioffi A, Cipolloni L, et al. The application of artificial intelligence in forensic pathology: a systematic literature review. Front Med. 2025;12:1583743.\u003c/li\u003e\n\u003cli\u003eZain Alabdeen EH, Felemban DF. Artificial intelligence and skull imaging advancements in forensic identification. Saudi J Health Sci. 2023;12(3):171\u0026ndash;177.\u003c/li\u003e\n\u003cli\u003eFernandez G, Gonzalez A. Drone-based disaster assessment and victim localization. Remote Sens. 2016;8(3):189.\u003c/li\u003e\n\u003cli\u003eAutomated fingerprint identification: the role of artificial intelligence in crime scene investigation. Forensic Sci Int Med Leg. 2026;6(1):6.\u003c/li\u003e\n\u003cli\u003eA systematic review about the evolving role of AI in various fields of forensic medicine. J Forensic Leg Med. 2025:103043.\u003c/li\u003e\n\u003cli\u003eArtificial Intelligence and Identification of the Deceased: a narrative review. Behav Sci Law. 2025;43(3):341\u0026ndash;349.\u003c/li\u003e\n\u003cli\u003eAI adoption framework for presenting DNA evidence. Forensic Evid Law. 2024;6(25):13.\u003c/li\u003e\n\u003cli\u003eDigital forensics and strong AI: a structured literature review. Forensic Sci Int Digit Invest. 2023;46:301617.\u003c/li\u003e\n\u003cli\u003eDNA phenotype prediction and age estimation using AI methylation analysis. World Sci Res J. 2024;10(7):108\u0026ndash;115.\u003c/li\u003e\n\u003cli\u003eSmith J, Lee H, Patel R, et al. Machine learning enhanced biometric fusion for human identification in mass disasters. IEEE Trans Inf Forensics Secur. 2024;19:234\u0026ndash;245.\u003c/li\u003e\n\u003cli\u003eZhang X, Liu Y, Gupta AK. Deep learning for automated dental radiograph identification in forensic odontology. Forensic Imaging. 2023;28:100435.\u003c/li\u003e\n\u003cli\u003eAhmed A, Khan S, Lee D. AI-driven fingerprint matching: performance on partial and low-quality prints. Pattern Recogn. 2025;132:108667.\u003c/li\u003e\n\u003cli\u003eChen Y, Huang T, Wang L. Integrating AI and PMCT imaging for postmortem identification: clinical evidence. Int J Legal Med. 2024;138(7):2471\u0026ndash;2482.\u003c/li\u003e\n\u003cli\u003eRossi P, Bianchi A, Coppola F. Explainable AI (XAI) for forensic pattern recognition: benefits and challenges. Expert Syst Appl. 2024;195:116588.\u003c/li\u003e\n\u003cli\u003eThompson G, Novak K, Li P. Ethical implications of biometric AI systems in forensic sciences. Comput Law Secur Rev. 2024;52:102350.\u003c/li\u003e\n\u003cli\u003eSingh R, Verma N, Kumar V. AI-assisted age and sex estimation from skeletal remains. J Forensic Sci. 2023;68(4):1123\u0026ndash;1132.\u003c/li\u003e\n\u003cli\u003eVelasco R, de Souza R. Machine learning in forensic toxicology: a systematic review. Forensic Toxicol. 2023;41(1):12\u0026ndash;29.\u003c/li\u003e\n\u003cli\u003eNguyen T, Wang Z. Neural network models for postmortem facial reconstruction. Comput Biol Med. 2024;150:106179.\u003c/li\u003e\n\u003cli\u003eBaker L, Chen X, Yang D. AI automated postmortem interval estimation using microbiome patterns. Sci Rep. 2023;13:21456.\u003c/li\u003e\n\u003cli\u003eDavis M, Li J. Blockchain and AI for secure identification data management in DVI. IEEE Access. 2025;11:43122\u0026ndash;43139.\u003c/li\u003e\n\u003cli\u003eKumar V, Salman Khan M, Ullah I. Comprehensive evaluation of AI in forensic odontology: a global perspective. Sci Justice. 2025;65(2):145\u0026ndash;156.\u003c/li\u003e\n\u003cli\u003ePatel J, Ray A. Deep learning models for crime scene image analysis. ACM Comput Surv. 2024;57(5):100.\u003c/li\u003e\n\u003cli\u003eO\u0026rsquo;Reilly P, Singh D. Multimodal biometric systems for forensic person identification. Biometrics. 2024;80:230100.\u003c/li\u003e\n\u003cli\u003eMunoz N, Castro L, Sancho T. AI in shoeprint and toolmark pattern recognition. Int J Pattern Recognit Artif Intell. 2023;37(9):2257009.\u003c/li\u003e\n\u003cli\u003eMorales J, Santos R. AI-based gait recognition for victim identification in mass casualty events. IEEE Trans Biomed Eng. 2025;72(1):180\u0026ndash;191.\u003c/li\u003e\n\u003cli\u003eAkhtar M, Qureshi F. Deep learning-based latent fingerprint enhancement. Pattern Recogn Lett. 2024;154:38\u0026ndash;45.\u003c/li\u003e\n\u003cli\u003eHernandez C, Lopez G. AI in forensic voice biometrics: accuracy and vulnerability. Speech Commun. 2023;141:67\u0026ndash;79.\u003c/li\u003e\n\u003cli\u003eZhao X, Li H. Generative adversarial networks for forensic facial synthesis. Neural Comput Appl. 2025;37:587\u0026ndash;599.\u003c/li\u003e\n\u003cli\u003ePark M, Kim S. AI for automated trace evidence classification. Forensic Sci Int Rep. 2023;5:100240.\u003c/li\u003e\n\u003cli\u003eLee T, Brown P, Wilson F. Deep learning applications in postmortem angiography. Radiology. 2024;293(2):465\u0026ndash;474.\u003c/li\u003e\n\u003cli\u003eAdebayo O, Said Z. AI for bloodstain pattern analysis in forensic investigations. Forensic Sci Int. 2025;350:111188.\u003c/li\u003e\n\u003cli\u003eChen Q, Wu J. Federated learning for secure forensic biometric data sharing. IEEE Trans Dependable Secur Comput. 2024;21(3):1124\u0026ndash;1136.\u003c/li\u003e\n\u003cli\u003eSingh S, Patel N. AI-assisted fingerprint segmentation for improved minutiae extraction. IEEE Trans Pattern Anal Mach Intell. 2023;45(12):15002\u0026ndash;15015.\u003c/li\u003e\n\u003cli\u003eGarcia L, Fernandez J. AI in bone trauma pattern detection. J Forensic Sci. 2024;69(3):891\u0026ndash;900.\u003c/li\u003e\n\u003cli\u003eOliveira D, Almeida R. Machine learning driven postmortem imaging triage. Eur J Radiol. 2023;156:110610.\u003c/li\u003e\n\u003cli\u003eZhang Y, Wang H. Automated dental chart matching with convolutional neural networks. Dentomaxillofac Radiol. 2024;53(2):20230345.\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003e\u003cstrong\u003eTable 1. Artificial Intelligence Technologies in DVI\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eTechnology\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eApplication\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eAdvantages\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eFacial Recognition\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eImage matching\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eRapid ID, high accuracy\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eAI Dental Analysis\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eRadiograph comparison\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eEfficient, scalable\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eSkeletal Profiling\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eAge/sex estimation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eAutomated, accurate\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003ePattern Recognition\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eData integration\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eReduced human error\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eDrone Imaging\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eScene survey\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eFaster recovery\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2. Digital Technologies Supporting DVI\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eTechnology\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eApplication\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eBenefit\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003ePostmortem CT\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eVirtual autopsy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNon-invasive exam\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003e3D Imaging\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eFacial reconstruction\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eID assistance\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eRapid DNA\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eGenetic identification\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eHigh precision\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eUAV Mapping\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eDisaster scene analysis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eTime efficiency\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eBiometric Databases\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eRecord matching\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eAutomated workflow\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Disaster victim identification, Artificial intelligence, Forensic science, Digital technologies, Biometrics, DNA analysis","lastPublishedDoi":"10.21203/rs.3.rs-9121285/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9121285/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Disaster victim identification (DVI) represents a critical component of forensic investigation during mass fatality incidents caused by natural disasters, transportation accidents, terrorist attacks, and armed conflicts. Traditional identification techniques—namely fingerprint analysis, dental record comparison, and DNA profiling—remain the gold standard [1–5]; however, their effectiveness is often compromised in cases involving severe decomposition, fragmentation, or lack of antemortem records [4,5,16]. Recent advances in artificial intelligence (AI) and digital technologies have introduced innovative tools capable of improving the efficiency, accuracy, and scalability of DVI operations [6–9,14,22]. This review provides a comprehensive and critical analysis of contemporary applications of AI in forensic identification, including facial recognition, forensic odontology, postmortem imaging, DNA analysis, drone-assisted recovery, and integrated forensic data systems [10–15,17–19]. In addition, the study highlights key challenges such as ethical concerns, data privacy, algorithmic bias, and disparities in global technological infrastructure [19,36]. AI-driven forensic technologies demonstrate strong potential to enhance disaster response systems; however, their implementation requires rigorous validation, international standardization, and regulatory oversight [6,9,18,36].","manuscriptTitle":"Use of Artificial Intelligence and Digital Technologies in Disaster Victim Identification (DVI): Current Developments, Challenges, and Future Perspectives","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-01 07:30:47","doi":"10.21203/rs.3.rs-9121285/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6babcbed-82bd-4518-8ee8-4a820a1d91ae","owner":[],"postedDate":"April 1st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-01T07:30:47+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-01 07:30:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9121285","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9121285","identity":"rs-9121285","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}