Department of General Dentistry, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
College of Stomatology, Shanghai Jiao Tong University, Shanghai, People's Republic of China.
BMC Oral Health. 2023 Sep 20;23(1):680. doi: 10.1186/s12903-023-03284-5.
Having a reliable and feasible method to estimate whether an individual has reached 16 years of age would greatly benefit forensic analysis. The study of age using dental information has matured recently. In addition, machine learning (ML) is gradually being applied for dental age estimation.
The purpose of this study was to evaluate the development of the third molar using the Demirjian method (Demirjian), measure the development index of the third molar (I) using the method by Cameriere, and assess the periodontal ligament development of the second molar (PL). This study aimed to predict whether Chinese adolescents have reached the age of criminal responsibility (16 years) by combining the above measurements with ML techniques.
SUBJECTS & METHODS: A total of 665 Chinese adolescents aged between 12 and 20 years were recruited for this study. The development of the second and third molars was evaluated by taking orthopantomographs. ML algorithms, including random forests (RF), decision trees (DT), support vector machines (SVM), K-nearest neighbours (KNN), Bernoulli Naive Bayes (BNB), and logistic regression (LR), were used for training and testing to determine the dental age. This is the first study to combine ML with an evaluation of periodontal ligament and tooth development to predict whether individuals are over 16 years of age.
The study showed that SVM had the highest Bayesian posterior probability at 0.917 and a Youden index of 0.752. This finding provides an important reference for forensic identification, and the combination of traditional methods and ML is expected to improve the accuracy of age determination for this population, which is of substantial significance for criminal litigation.
拥有一种可靠且可行的方法来估计个体是否已满 16 岁，将极大地有益于法医学分析。最近，利用牙齿信息来研究年龄的方法已经成熟。此外，机器学习（ML）也逐渐被应用于牙齿年龄估计。
本研究旨在使用 Demirjian 法（Demirjian）评估第三磨牙的发育情况，使用 Cameriere 方法测量第三磨牙的发育指数（I），评估第二磨牙的牙周韧带发育（PL）。本研究旨在通过结合以上测量方法和 ML 技术，预测中国青少年是否达到刑事责任年龄（16 岁）。
本研究共招募了 665 名年龄在 12 至 20 岁之间的中国青少年。通过拍摄全景片评估第二和第三磨牙的发育情况。使用 ML 算法，包括随机森林（RF）、决策树（DT）、支持向量机（SVM）、K-近邻（KNN）、伯努利朴素贝叶斯（BNB）和逻辑回归（LR），进行训练和测试，以确定牙齿年龄。这是第一项结合 ML 技术评估牙周韧带和牙齿发育来预测个体是否已满 16 岁的研究。
研究表明，SVM 的贝叶斯后验概率最高为 0.917，约登指数为 0.752。这一发现为法医鉴定提供了重要参考，传统方法与 ML 的结合有望提高该人群年龄确定的准确性，这对于刑事诉讼具有重要意义。
