Do machine learning methods solve the main pitfall of linear regression in dental age estimation?

Aug 3, 2026

Upload by Sage

Age estimation underpins forensic investigation and anthropological assessment when identifying individuals or evaluating human remains. Dental maturation is increasingly used because teeth preserve well despite environmental stressors that can distort other skeletal markers. Recent machine learning approaches yield high accuracy, yet how they affect systematic error trends seen in linear regression has not been fully clarified. This study compares Random Forest, SVR, KNN and Gradient Boosting with linear regression and SNBC, quantifying both accuracy and error-trend precision.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Introduction

Aim

Methods

Results

Conclusion

Forensic Science International 367 (2025) 112353 Contents lists available at ScienceDirect Forensic Science International journal [homepage: www.elsevier.com/locate/forsciint](homepage: www.elsevier.com/locate/forsciint) | Do machine learning methods solve the main pitfall of linear regression in dental age estimation?
Andrea Faragallia,* , Luigi Ferrantea, Nikolaos Angelakopoulosb, Roberto Camerierec,
Edlira Skramia
a Center of Epidemiology, Biostatistics and Medical Information Technology, Department of Biomedical Sciences and Public Health, Universit`a Politecnica delle Marche, Ancona 60126, Italy
b Department of Orthodontics and Dentofacial Orthopedics, University of Bern, Freiburgstrasse 7, Bern 3010, Switzerland c AgEstimation Project, Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, Campobasso, Italy | | | | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | Keywords: Age estimation Machine learning
Dental maturation Accuracy Estimation bias | | Introduction: Age estimation is crucial in forensic and anthropological fields. Teeth, are valued for their resilience to environmental factors and their preservation over time, making them essential for age estimation when other skeletal remains deteriorate. Recently, Machine Learning algorithms have been used in age estimation, demonstrating high levels of accuracy. However, their precision with respect to the trend of age estimation error, typical in some traditional methods like linear regression, has not been thoroughly investigated.
Aim: To evaluate and compare the performance of frequently used Machine Learning-assisted methods against two traditional age estimation methods, linear regression and the Segmented Normal Bayesian Calibration model.
Methods: Overall, 1.949 orthopantomographs from black and white South African children aged 5–14 years, with 49 % males, were evaluated. The performance of Random Forest, Support Vector Regression, K-Nearest Neighbors and the Gradient Boosting Method were compared against traditional linear regression and the Segmented Normal Bayesian Calibration model. The comparison was based on accuracy measures, including Mean Absolute Error and Root Mean Squared Error, and precision measures, including the Inter-Quartile Range of the error distribution and the slope of the estimated age error relative to chronological age.
Results: The Machine Learning methods outperformed linear regression and the Segmented Normal Bayesian Calibration models in terms of accuracy, although the differences were small. Gradient Boosting Method and Support Vector Regression achieved the highest levels of accuracy (Mean Absolute Error: 0.69 years, Root Mean Squared Error: 0.85 years). All Machine Learning methods and linear regression exhibited significant bias in residuals, whereas the Segmented Normal Bayesian Calibration model showed no significant bias. Genderstratified analyses revealed similar results in terms of the accuracy and precision of all considered models. Conclusion: Although Machine Learning methods demonstrate high levels of accuracy, they may be prone to trends in error distribution when estimating dental age. Evaluating this error is crucial and should be an integral part of model performance evaluation. Future research should aim to improve accuracy while rigorously addressing systematic biases. | 1. Introduction The age estimation process, used to determine the chronological age of individuals lacking identity documents or to assess the age of human remains, is a critical aspect in both anthropological and forensic fields [1]. Typically, these age assessments rely on radiological analysis of specific body parts, such as hand-wrist bones [2], knee, clavicle and teeth [3–6]). Dental structures are easily assessed through X-rays and are increasingly recognized for their utility in age estimation because they are not affected by external factors such as

FAQs

Why is age estimation important in forensic and anthropological contexts?

Age estimation determines chronological age when identity documents are unavailable and supports evaluation of human remains. It is crucial for both forensic science and anthropological research.

Which machine learning methods were evaluated for dental age estimation?

Random Forest, Support Vector Regression, K-Nearest Neighbors, and Gradient Boosting were compared against two traditional methods: linear regression and the Segmented Normal Bayesian Calibration model.

How did machine learning methods perform compared with linear regression?

Machine learning methods showed higher accuracy than linear regression and SNBC, though differences were small. Error residuals still exhibited significant bias for machine learning and linear regression, while SNBC showed no significant bias.

Aug 3, 2026

Upload by Sage