Human identification via digital palatal scans: a machine learning validation pilot study

Abstract Background This study aims to validate a machine learning algorithm previously developed in a training population on a different randomly chosen population (i.e., test set). The discrimination potential of the palatal intraoral scan-based geometric and superimposition methods was evaluated....

Full description

Saved in:
Bibliographic Details
Main Authors: Ákos Mikolicz, Botond Simon, Aida Roudgari, Arvin Shahbazi, János Vág
Format: Article
Language:English
Published: BMC 2024-11-01
Series:BMC Oral Health
Subjects:
Online Access:https://doi.org/10.1186/s12903-024-05162-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846100846198128640
author Ákos Mikolicz
Botond Simon
Aida Roudgari
Arvin Shahbazi
János Vág
author_facet Ákos Mikolicz
Botond Simon
Aida Roudgari
Arvin Shahbazi
János Vág
author_sort Ákos Mikolicz
collection DOAJ
description Abstract Background This study aims to validate a machine learning algorithm previously developed in a training population on a different randomly chosen population (i.e., test set). The discrimination potential of the palatal intraoral scan-based geometric and superimposition methods was evaluated. Methods A total of 23 participants (16 females and seven males) from different countries underwent palatal scans using the Emerald intraoral scanner. Geometric-based identification involved measuring the height, width, and depth of the palatal vault in each scan. These parameters were then input into Fisher’s linear discriminant equations with coefficients determined previously on a training set. Sensitivity and specificity were calculated. For the superimposition method, scan repeatability was compared to between-subjects differences, calculating mean absolute differences (MAD) between aligned scans. Multiple linear regression analysis determined the effects of sex, longitude, and latitude of country of origin on concordance. Results The geometric-based method achieved 91.2% sensitivity and 97.1% specificity, consistent with the results from the training set, showing no significant difference. Latitude and longitude did not significantly affect geometric-based matches. In the superimposition method, the between-subjects MAD range (1.068–0.214 mm) and the repeatability range (0.011–0.093 mm) did not overlap. MAD was minimally affected by longitude and not influenced by latitude. The sex determination function recognized females over males with 69.0% sensitivity, similar to the training set. However, the specificity (62.5%) decreased. Conclusions The assessment of geometric and superimposition discrimination has unequivocally demonstrated its robust reliability, remaining impervious to population. In contrast, the distinction between sexes carries only moderate reliability. The significant correlation observed among longitude, latitude, and palatal height suggests the feasibility of a comprehensive large-scale study to determine one’s country of origin. Clinical significance Portable intraoral scanners can aid forensic investigations as adjunct identification methods by applying the proposed discriminant function to palatal geometry without population restrictions. Trial registration The Clinicatrial.gov registration number is NCT05349942 (27/04/2022).
format Article
id doaj-art-9aa56ad24a2a49c6a2bca3cd5f13ab1f
institution Kabale University
issn 1472-6831
language English
publishDate 2024-11-01
publisher BMC
record_format Article
series BMC Oral Health
spelling doaj-art-9aa56ad24a2a49c6a2bca3cd5f13ab1f2024-12-29T12:50:11ZengBMCBMC Oral Health1472-68312024-11-012411910.1186/s12903-024-05162-0Human identification via digital palatal scans: a machine learning validation pilot studyÁkos Mikolicz0Botond Simon1Aida Roudgari2Arvin Shahbazi3János Vág4Department of Restorative Dentistry and Endodontics, Semmelweis UniversityDepartment of Restorative Dentistry and Endodontics, Semmelweis UniversityDepartment of Restorative Dentistry and Endodontics, Semmelweis UniversityDepartment of Restorative Dentistry and Endodontics, Semmelweis UniversityDepartment of Restorative Dentistry and Endodontics, Semmelweis UniversityAbstract Background This study aims to validate a machine learning algorithm previously developed in a training population on a different randomly chosen population (i.e., test set). The discrimination potential of the palatal intraoral scan-based geometric and superimposition methods was evaluated. Methods A total of 23 participants (16 females and seven males) from different countries underwent palatal scans using the Emerald intraoral scanner. Geometric-based identification involved measuring the height, width, and depth of the palatal vault in each scan. These parameters were then input into Fisher’s linear discriminant equations with coefficients determined previously on a training set. Sensitivity and specificity were calculated. For the superimposition method, scan repeatability was compared to between-subjects differences, calculating mean absolute differences (MAD) between aligned scans. Multiple linear regression analysis determined the effects of sex, longitude, and latitude of country of origin on concordance. Results The geometric-based method achieved 91.2% sensitivity and 97.1% specificity, consistent with the results from the training set, showing no significant difference. Latitude and longitude did not significantly affect geometric-based matches. In the superimposition method, the between-subjects MAD range (1.068–0.214 mm) and the repeatability range (0.011–0.093 mm) did not overlap. MAD was minimally affected by longitude and not influenced by latitude. The sex determination function recognized females over males with 69.0% sensitivity, similar to the training set. However, the specificity (62.5%) decreased. Conclusions The assessment of geometric and superimposition discrimination has unequivocally demonstrated its robust reliability, remaining impervious to population. In contrast, the distinction between sexes carries only moderate reliability. The significant correlation observed among longitude, latitude, and palatal height suggests the feasibility of a comprehensive large-scale study to determine one’s country of origin. Clinical significance Portable intraoral scanners can aid forensic investigations as adjunct identification methods by applying the proposed discriminant function to palatal geometry without population restrictions. Trial registration The Clinicatrial.gov registration number is NCT05349942 (27/04/2022).https://doi.org/10.1186/s12903-024-05162-0GeometryPalateMachine learningIntraoral scannerSexHuman identification
spellingShingle Ákos Mikolicz
Botond Simon
Aida Roudgari
Arvin Shahbazi
János Vág
Human identification via digital palatal scans: a machine learning validation pilot study
BMC Oral Health
Geometry
Palate
Machine learning
Intraoral scanner
Sex
Human identification
title Human identification via digital palatal scans: a machine learning validation pilot study
title_full Human identification via digital palatal scans: a machine learning validation pilot study
title_fullStr Human identification via digital palatal scans: a machine learning validation pilot study
title_full_unstemmed Human identification via digital palatal scans: a machine learning validation pilot study
title_short Human identification via digital palatal scans: a machine learning validation pilot study
title_sort human identification via digital palatal scans a machine learning validation pilot study
topic Geometry
Palate
Machine learning
Intraoral scanner
Sex
Human identification
url https://doi.org/10.1186/s12903-024-05162-0
work_keys_str_mv AT akosmikolicz humanidentificationviadigitalpalatalscansamachinelearningvalidationpilotstudy
AT botondsimon humanidentificationviadigitalpalatalscansamachinelearningvalidationpilotstudy
AT aidaroudgari humanidentificationviadigitalpalatalscansamachinelearningvalidationpilotstudy
AT arvinshahbazi humanidentificationviadigitalpalatalscansamachinelearningvalidationpilotstudy
AT janosvag humanidentificationviadigitalpalatalscansamachinelearningvalidationpilotstudy