法医学杂志 ›› 2024, Vol. 40 ›› Issue (2): 135-142.DOI: 10.12116/j.issn.1004-5619.2023.231208

• 法医人类学年龄推断专题 • 上一篇    

Demirjian法结合机器学习算法推断北方汉族儿童及青少年牙龄

郭瑜鑫1(), 卜雯卿1,2, 唐羽1,2, 吴迪1,2, 杨徽1,2, 孟昊天1, 郭昱成1,2()   

  1. 1.陕西省颅颌面精准医学研究重点实验室 西安交通大学口腔医院,陕西 西安 710004
    2.西安交通大学口腔医院正畸科,陕西 西安 710004
  • 收稿日期:2023-12-24 发布日期:2024-06-07 出版日期:2024-04-25
  • 通讯作者: 郭昱成
  • 作者简介:郭瑜鑫(1992—),女,博士,助理研究员,主要从事颅颌面形态及其相关分子标记的法医学研究;E-mail:guoyuxin004@163.com
  • 基金资助:
    国家自然科学基金青年基金资助项目(81701869)

Dental Age Estimation in Northern Chinese Han Children and Adolescents Using Demirjian’s Method Combined with Machine Learning Algorithms

Yu-xin GUO1(), Wen-qing BU1,2, Yu TANG1,2, Di WU1,2, Hui YANG1,2, Hao-tian MENG1, Yu-cheng GUO1,2()   

  1. 1.Key Laboratory of Shaanxi Province for Craniofacial Precision Medicine Research, Hospital of Stomatology, Xi’an Jiaotong University, Xi’an 710004, China
    2.Department of Orthodontics, Hospital of Stomatology, Xi’an Jiaotong University, Xi’an 710004, China
  • Received:2023-12-24 Online:2024-06-07 Published:2024-04-25
  • Contact: Yu-cheng GUO

摘要:

目的 探讨Demirjian法结合机器学习算法在北方汉族儿童及青少年牙龄推断中的应用价值。 方法 收集10 256例我国北方汉族5~24岁人群的口腔全景片,运用Demirjian法对左下颌8颗恒牙的发育进行分期,并结合支持向量回归、梯度提升回归、线性回归、随机森林回归和决策树回归等多种机器学习算法,分别基于总样本、女性样本和男性样本构建年龄推断模型,并评价不同机器学习算法在3组样本中的拟合性能。 结果 对于总样本和女性样本,推断准确率最高的模型均为支持向量回归模型;对于男性样本,推断准确率最高的模型为梯度提升回归模型。最佳年龄推断模型在总样本、女性样本和男性样本的平均绝对误差分别为1.246 3、1.281 8和1.153 8岁。最佳年龄推断模型对各年龄区间的推断准确率不同,对于18岁以下人群的年龄推断相对准确。 结论 本研究构建的年龄推断机器学习模型在我国北方汉族儿童及青少年中具有较好的准确率,但在成年人群中的推断效果不理想,可以考虑联合其他变量以提高年龄推断的准确性。

关键词: 法医人类学, 法医齿科学, 年龄推断, 机器学习, Demirjian法, 口腔全景片, 儿童, 青少年

Abstract:

Objective To investigate the application value of combining the Demirjian’s method with machine learning algorithms for dental age estimation in northern Chinese Han children and adolescents. Methods Oral panoramic images of 10 256 Han individuals aged 5 to 24 years in northern China were collected. The development of eight permanent teeth in the left mandibular was classified into different stages using the Demirjian’s method. Various machine learning algorithms, including support vector regression (SVR), gradient boosting regression (GBR), linear regression (LR), random forest regression (RFR), and decision tree regression (DTR) were employed. Age estimation models were constructed based on total, female, and male samples respectively using these algorithms. The fitting performance of different machine learning algorithms in these three groups was evaluated. Results SVR demonstrated superior estimation efficiency among all machine learning models in both total and female samples, while GBR showed the best performance in male samples. The mean absolute error (MAE) of the optimal age estimation model was 1.246 3, 1.281 8 and 1.153 8 years in the total, female and male samples, respectively. The optimal age estimation model exhibited varying levels of accuracy across different age ranges, which provided relatively accurate age estimations in individuals under 18 years old. Conclusion The machine learning model developed in this study exhibits good age estimation efficiency in northern Chinese Han children and adolescents. However, its performance is not ideal when applied to adult population. To improve the accuracy in age estimation, the other variables can be considered.

Key words: forensic anthropology, forensic dentistry, age estimation, machine learning, Demirjian’s method, oral panoramic image, children, adolescents

中图分类号: