The age at death assessment in a multi-ethnic sample of pelvic bones using nature-inspired data mining methods

Application of machine-learning methods in age-at-death estimation from 3D surface scans of the adult acetabulum

OBJECTIVE

Age-at-death estimation is usually done manually by experts. As such, manual estimation is subjective and greatly depends on the past experience and proficiency of the expert. This becomes even more critical if experts need to evaluate individuals with unknown population affinity or with affinity that they are not familiar with. The purpose of this study is to design a novel age-at-death estimation method allowing for automatic evaluation on computers, thus eliminating the human factor.

METHODS

We used a traditional machine-learning approach with explicit feature extraction. First, we identified and described the features that are relevant for age-at-death estimation. Then, we created a multi-linear regression model combining these features. Finally, we analysed the model performance in terms of Mean Absolute Error (MAE), Mean Bias Error (MBE), Slope of Residuals (SoR) and Root Mean Squared Error (RMSE).

RESULTS

The main result of this study is a population-independent method of estimating an individual's age-at-death using the acetabulum of the pelvis. Apart from data acquisition, the whole procedure of pre-processing, feature extraction and age estimation is fully automated and implemented as a computer program. This program is a part of a freely available web-based software tool called CoxAGE3D, which is available at https://coxage3d.fit.cvut.cz/. Based on our dataset, the MAE of the presented method is about 10.7 years. In addition, five population-specific models for Thai, Lithuanian, Portuguese, Greek and Swiss populations are also given. The MAEs for these populations are 9.6, 9.8, 10.8, 10.5 and 9.2 years, respectively. Our age-at-death estimation method is suitable for individuals with unknown population affinity and provides acceptable accuracy. The age estimation error cannot be completely eliminated, because it is a consequence of the variability of the ageing process of different individuals not only across different populations but also within a certain population.

Applicability of the six-phase method for auricular age estimation in an Indian population: A CT-based study

Age estimation plays a crucial role in human identification. Amongst numerous age markers located throughout the skeletal framework, the auricular surface of the ilium presents as a resilient structure, with different methods for auricular age estimation currently in practice. Amongst these methods, the Osborne method is believed to permit accurate age estimation through its use of robust age categories and discrete phase descriptors. The present study aimed to assess the applicability of the Osborne method in an Indian population through a computed tomographic (CT) examination of the auricular surface, an aspect presently unreported. In order to do so, CT scans of 380 individuals were collected and evaluated using the Osborne method. A CT-based examination indicated that surface texture described by Osborne is difficult to appreciate through 3D CT images. Indistinct definitions associated with certain features, and the mosaic display of features within each phase further prevents applying the method effectively. Overall accuracy percentages of 99.47% and 98.90% were obtained using the method in males and females, respectively, with corresponding inaccuracy values of 10.10 years and 9.04 years. Significantly reduced accuracy percentages were obtained with alternate, more robust age brackets presented within the original study, demonstrating the limited reliability associated with the method. Inaccuracy and bias values computed for each decade indicate the relative utility of the method in aging 40-59-year-old individuals. Low accuracy percentages, high error rates and different methodological hindrances encountered within the present study illustrate the limited applicability of the Osborne method in aging an Indian population.

Information fusion for infant age estimation from deciduous teeth using machine learning

OBJECTIVES

Over the past few years, several methods have been proposed to improve the accuracy of age estimation in infants with a focus on dental development as a reliable marker. However, traditional approaches have limitations in efficiently combining information from different teeth and features. In order to address these challenges, this article presents a study on age estimation in infants with Machine Learning (ML) techniques, using deciduous teeth.

MATERIALS AND METHODS

The involved dataset comprises 114 infant skeletons from the Granada osteological collection of identified infants, aged between 5 months of gestation and 3 years of age. The samples consist of features such as the maximum length and mineralization and alveolar stages of teeth. For the purpose of designing a method capable of combining all the information available from each individual, a Multilayer Perceptron model is proposed, one of the most popular artificial neural networks. This model has been validated using the leave-one-out experimental validation protocol. Through different groups of experiments, the study examines the informativeness of the aforementioned features, individually and in combination.

RESULTS

The results indicate that the fusion of different variables allows for more accurate age estimates (RMSE = 66 days) than when variables are analyzed separately (RMSE = 101 days). Additionally, the study demonstrates the benefits of involving multiple teeth, which significantly reduces the RMSE compared to a single tooth.

DISCUSSION

This article underlines the clear advantages of ML-based methods, emphasizing their potential to improve the accuracy and robustness when estimating the age of infants.

Application of entire dental panorama image data in artificial intelligence model for age estimation

BACKGROUND

Accurate age estimation is vital for clinical and forensic purposes. With the rapid advancement of artificial intelligence(AI) technologies, traditional methods relying on tooth development, while reliable, can be enhanced by leveraging deep learning, particularly neural networks. This study evaluated the efficiency of an AI model by applying the entire panoramic image for age estimation. The outcome performances were analyzed through supervised learning (SL) models.

METHODS

Total of 27,877 dental panorama images from 5 to 90 years of age were classified by 2 types of grouping. In type 1 they were classified by each age and in type 2, applying heuristic grouping, the age over 20 years were classified by every 5 years. Wide ResNet (WRN) and DenseNet (DN) were used for supervised learning. In addition, the analysis with ± 3 years of deviation in both types were performed.

RESULTS

For the DN model, while the type 1 grouping achieved an accuracy of 0.1016 and F1 score of 0.058, the type 2 achieved an accuracy of 0.3146 and F1 score of 0.2027. Incorporating ± 3years of deviation, the accuracy of type 1 and 2 were 0.281, 0.7323 respectively; and the F1 score were 0.1768, 0.6583 respectively. For the WRN model, while the type 1 grouping achieved an accuracy of 0.1041 and F1 score of 0.0599, the type 2 achieved an accuracy of 0.3182 and F1 score of 0.2071. Incorporating ± 3years of deviation, the accuracy of type 1 and 2 were 0.2716, 0.7323 respectively; and the F1 score were 0.1709, 0.6437 respectively.

CONCLUSIONS

The application of entire panorama image data for supervised with classification by heuristics grouping with ± 3years of deviation for supervised learning models and demonstrated satisfactory outcome for the age estimation.

The computational age-at-death estimation from 3D surface models of the adult pubic symphysis using data mining methods

Age-at-death estimation of adult skeletal remains is a key part of biological profile estimation, yet it remains problematic for several reasons. One of them may be the subjective nature of the evaluation of age-related changes, or the fact that the human eye is unable to detect all the relevant surface changes. We have several aims: (1) to validate already existing computer models for age estimation; (2) to propose our own expert system based on computational approaches to eliminate the factor of subjectivity and to use the full potential of surface changes on an articulation area; and (3) to determine what age range the pubic symphysis is useful for age estimation. A sample of 483 3D representations of the pubic symphyseal surfaces from the ossa coxae of adult individuals coming from four European (two from Portugal, one from Switzerland and Greece) and one Asian (Thailand) identified skeletal collections was used. A validation of published algorithms showed very high error in our dataset-the Mean Absolute Error (MAE) ranged from 16.2 and 25.1 years. Two completely new approaches were proposed in this paper: SASS (Simple Automated Symphyseal Surface-based) and AANNESS (Advanced Automated Neural Network-grounded Extended Symphyseal Surface-based), whose MAE values are 11.7 and 10.6 years, respectively. Lastly, it was demonstrated that our models could estimate the age-at-death using the pubic symphysis over the entire adult age range. The proposed models offer objective age estimates with low estimation error (compared to traditional visual methods) and are able to estimate age using the pubic symphysis across the entire adult age range.

DXAGE 2.0 - adult age at death estimation using bone loss in the proximal femur and the second metacarpal

The accurate age at death assessment of unidentified adult skeletal individuals is a critical research task in forensic anthropology, being a key feature for the determination of biological profiles of individual skeletal remains. We have previously shown that the age-related decrease of bone mineral density (BMD) in the proximal femur could be used to assess age at death in women (Navega et al., J Forensic Sci 63:497-503, 2018). The present study aims to generate models for age estimation in both sexes through bone densitometry of the femur and radiogrammetry of the second metacarpal. The training sample comprised 224 adults (120 females, 104 males) from the "Coimbra Identified Skeletal Collection," and different models were generated through least squares regression and general regression neural networks (GRNN). The models were operationalized in a user-friendly online interface at https://osteomics.com/DXAGE2/ . The mean absolute difference between the known and estimated age at death ranges from 9.39 to 13.18 years among women and from 10.33 to 15.76 among men with the least squares regression models. For the GRNN models, the mean absolute difference between documented and projected age ranges from 8.44 to 12.58 years in women and from 10.56 to 16.18 years in men. DXAGE 2.0 enables age estimation in incomplete and/or fragmentary skeletal remains, using alternative skeletal regions, with reliable results.

Adult Skeletal Age-at-Death Estimation through Deep Random Neural Networks: A New Method and Its Computational Analysis

Age-at-death assessment is a crucial step in the identification process of skeletal human remains. Nonetheless, in adult individuals this task is particularly difficult to achieve with reasonable accuracy due to high variability in the senescence processes. To improve the accuracy of age-at-estimation, in this work we propose a new method based on a multifactorial macroscopic analysis and deep random neural network models. A sample of 500 identified skeletons was used to establish a reference dataset (age-at-death: 19–101 years old, 250 males and 250 females). A total of 64 skeletal traits are covered in the proposed macroscopic technique. Age-at-death estimation is tackled from a function approximation perspective and a regression approach is used to infer both point and prediction interval estimates. Based on cross-validation and computational experiments, our results demonstrate that age estimation from skeletal remains can be accurately (~6 years mean absolute error) inferred across the entire adult age span and informative estimates and prediction intervals can be obtained for the elderly population. A novel software tool, DRNNAGE, was made available to the community.

Technical note: preliminary insight into a new method for age-at-death estimation from the pubic symphysis

Age-at-death estimation methods are important in forensic anthropology. However, age assessment is problematic due to inter-individual variation. The subjectivity of visual scoring systems can affect the accuracy and reliability of methods as well. One of the most studied skeletal regions for age assessment is the pubic symphysis. Few studies on Spanish pubic symphysis collections have been conducted, making further research necessary as well as the sampling of more forensic skeletal collections. This study is a preliminary development of an age-at-death estimation method from the pubic symphysis based on a new simple scoring system. A documented late twentieth century skeletal collection (N = 29) and a twenty-first century forensic collection (N = 76) are used. Sixteen traits are evaluated, and a new trait (microgrooves) is described and evaluated for the first time in this study. All traits are scored in a binary manner (present or absent), thus reducing ambiguity and subjectivity. Several data sets are constructed based on different age intervals. Machine learning methods are employed to evaluate the scoring system's performance. The results show that microgrooves, macroporosity, beveling, lower extremity, ventral and dorsal margin decomposition, and lipping are the best preforming traits. The new microgroove trait proves to be a good age predictor. Reliable classification results are obtained for three age intervals (≤ 29, 30-69, ≥ 70). Older individuals are reliably classified with two age intervals (< 80, ≥ 80). The combination of binary attributes and machine learning algorithms is a promising tool for gaining objectivity in age-at-death assessment.

An evaluation of statistical models for age estimation and the assessment of the 18-year threshold using conventional pelvic radiographs

The developmental patterns of the pelvic epiphyses are one of the anatomical markers used in the assessment of skeletal age and the legally relevant age threshold. In this study, four regression models and five classification models were developed for forensic age estimation and the determination of the 18-year threshold, respectively. A total of 2137 conventional pelvic radiographs (1215 males and 922 females) aged 10.00-25.99 years were analyzed, and the ossification and fusion of the iliac crest and ischial tuberosity epiphyses were scored separately. The epiphyses on both sides were used as inputs for all models. The accuracy of the regression models was compared using the mean absolute error (MAE) and root mean square error. The percentages of correct classifications were evaluated for the determination of the 18-year threshold. Support vector regression (SVR) and gradient boosting regression (GBR) showed higher accuracy for age estimation in both sexes. The lowest MAE was 1.38 years in males when using SVR and 1.16 years in females when using GBR. In the demarcation of minors and adults, the percentage of correct classification was over 92%, and the area under the receiver operating characteristic curves was over 0.91 in all models, except the Bernoulli naive Bayes classifier. This study demonstrated that the present models may be helpful for age estimation and the determination of the 18-year threshold. However, owing to the high effective dose of ionizing radiation used during conventional radiography of the pelvis, it is expected that these models will be tested with pelvic MRI for age estimation.

A validation study of the Stoyanova et al. method (2017) for age-at-death estimation quantifying the 3D pubic symphyseal surface of adult males of European populations

The age-at-death estimation thresholds have recently been shifted towards a more objective assessment of the aging process. Such a non-subjective approach offers quantitative methods of age estimation; for instance, the method relating to the surfaces of pubic symphyses of males published by Stoyanova et al. (J Forensic Sci 62:1434-1444, 2017). A validation study was conducted to test the method performance in European samples. The sample consisted of 96 meshes of pubic symphyses of male individuals (known sex and age) that came from four different samples (two Portuguese collections, one Swiss, and one Crete). Stoyanova's method based on five regression models (three univariate and two multivariate models) performed worse in our sample, but only when the whole sample (without age limitation) was included. A sample limited to individuals under 40 years of age achieved better results in our study. The best results were reached through the thin plate spline algorithm (TPS/BE) with a root mean square error of 5.93 years and inaccuracy of 4.47 years. Generally, the multivariate regression models did not contribute to better age estimation. In our sample in all age categories, age was systematically underestimated. The quantitative method tested in this study works best for individuals under 40 years of age and provides a suitable basis for further research.

Determining gender by taking measurements from magnetic resonance images of the patella

BACKGROUND

A key step in making a positive identification in forensic medicine is the establishment of a biological profile, which involves determining factors such as gender, age, ancestry, and stature. The goal of this study was to determine if gender could be established by taking various measurements of the patella taken from magnetic resonance imaging (MRI) images and analyzing the variations by gender.

METHODS

The sample group consisted of 220 patients (110 male and 110 female) whose patella were measured using MRI images of their left knee. Reasons for exclusion were any previous surgery, patella bipartite variation, any fracture in the patella due to trauma or findings of mass or infection. Three measurements - transverse length (TP), craniocaudal length (CC) and anteroposterior length (APP) - were taken off T2-weighted axial and sagittal MRI scans. The program SPSS (Version 21.0) was used to make a descriptive analysis, independent t-test and discriminative analysis.

RESULTS

It was found possible to determine gender with an accuracy rate of 91% for females and 87% for males. Since measurements were made individually the accuracy for gender estimation is lower than that seen in other methods.

CONCLUSION

The findings are important in that they show that it is possible to determine gender with a high degree of accuracy using just a few measurements taken from the patella.

An evaluation of dental methods by Lamendin and Prince and Ubelaker for estimation of adult age in a sample of modern Greeks

Teeth can be used as accurate tools in age-at-death estimation in forensic cases. No previous data exist on estimating age from teeth in a modern Greek population. The aim of this study was to evaluate Lamendin's and Prince and Ubelaker's ageing methods on a modern Greek skeletal sample. In total, 1436 single-rooted teeth from 306 adult individuals (161 males and 145 females) were examined. Only measurements of periodontosis and translucency showed positive correlation with age. Results showed a bias - an overestimation for ages under 40 years and an underestimation over this age. However, the use of wider age groups proved to be more appropriate. Low values of error were observed for the group of middle-aged individuals. In conclusion, both methods can be considered accurate in estimating age-at-death of middle-aged individuals. This study provides more information about the accuracy and applicability of these dental methods on modern European populations.

A test of four innominate bone age assessment methods in a modern skeletal collection from Medellin, Colombia

Studying bone collections with known data has proven to be useful in assessing reliability and accuracy of biological profile reconstruction methods used in Forensic Anthropology. Thus, it is necessary to calibrate these methods to clarify issues such as population variability and accuracy of estimations for the elderly. This work considers observations of morphological features examined by four innominate bone age assessment methods: (1) Suchey-Brooks Pubic Symphysis, (2) Lovejoy Iliac Auricular Surface, (3) Buckberry and Chamberlain Iliac Auricular Surface, and (4) Rouge-Maillart Iliac Auricular Surface and Acetabulum. This study conducted a blind test of a sample of 277 individuals from two contemporary skeletal collections from Universal and San Pedro cemeteries in Medellin, for which known pre-mortem data support the statistical analysis of results obtained using the four age assessment methods. Results from every method show tendency to increase bias and inaccuracy in relation to age, but Buckberry-Chamberlain and Rougé-Maillart's methods are the most precise for this particular Colombian population, where Buckberry-Chamberlain's is the best for analysis of older individuals.

Novel age estimation model based on development of permanent teeth compared with classical approach and other modern data mining methods

In order to analyze and improve the dental age estimation in children and adolescents for forensic purposes, 22 age estimation methods were compared to a sample of 976 orthopantomographs (662 males, 314 females) of healthy Czech children and adolescents aged between 2.7 and 20.5 years. All methods are compared in terms of the accuracy and complexity and are based on various data mining methods or on simple mathematical operations. The winning method is presented in detail. The comparison showed that only three methods provide the best accuracy while remaining user-friendly. These methods were used to build a tabular multiple linear regression model, an M5P tree model and support vector machine model with first-order polynomial kernel. All of them have mean absolute error (MAE) under 0.7 years for both males and females. The other well-performing data mining methods (RBF neural network, K-nearest neighbors, Kstar, etc.) have similar or slightly better accuracy, but they are not user-friendly as they require computing equipment and the implementation as computer program. The lowest estimation accuracy provides the traditional model based on age averages (MAE under 0.96 years). Different relevancy of various teeth for the age estimation was found. This finding also explains the lowest accuracy of the traditional averages-based model. In this paper, a technique for missing data replacement for the cases with missing teeth is presented in detail as well as the constrained tabular multiple regression model. Also, we provide free age prediction software based on this wining model.

Inaccuracy and bias in adult skeletal age estimation: Assessing the reliability of eight methods on individuals of varying body sizes

Accurate age estimations are essential for identifying human skeletal remains and narrowing missing persons searches. This study examines how BMI, body mass, and stature influence inaccuracy and bias in adult skeletal age estimations obtained using eight methods. 746 skeletons from the Hamann-Todd and William Bass Collections were used. Underweight BMI, light body mass, and short-stature individuals have the most error associated with their age estimates and are consistently under-aged between 3 to 13years. Obese BMI, heavy body mass, and tall-stature individuals are consistently over-aged between 3 to 8.5years. The most reliable methods for smaller-bodied individuals are Kunos et al. (first rib) and Buckberry-Chamberlain (auricular surface); for individuals in the average range, İşcan et al. (fourth ribs) and Passalacqua (sacrum); and for larger-bodied individuals, İşcan et al., Passalacqua, and Rougé-Maillart et al. (auricular surface and acetabulum). Lovejoy et al. (auricular surface) and Suchey-Brooks (pubic symphysis) produce consistent inaccuracy and bias scores across all body size groups. The least reliable method for smaller-bodied individuals is İşcan et al.; for larger-bodied individuals, Buckberry-Chamberlain; and across all body size groups, DiGangi et al. (first rib).

Analysis of axial prestretch in the abdominal aorta with reference to post mortem interval and degree of atherosclerosis

It is a well-known fact that the length of an artery in situ and the length of an excised artery differs. Retraction of blood vessels is usually observed. This prestretch plays an important role in arterial physiology. We have recently determined that the decrease of axial prestretch in the human abdominal aorta is so closely correlated with age that it is suitable for forensic applications (estimation of the age at time of death for cadavers of unknown identity). Since post mortem autolysis may affect the reliability of an estimate based on axial prestretch, the present study aims to detail analysis of the effect of post mortem time. The abdominal aorta is a prominent site of atherosclerotic changes (ATH), which may potentially affect longitudinal prestretch. Thus ATH was also involved in the analysis. Axial prestretch in the human abdominal aorta, post mortem interval (PMI), and the degree of ATH were documented in 365 regular autopsies. The data was first age adjusted to remove any supposed correlation with age. After the age adjustment of the sample, the correlation analysis showed no significant PMI effects on the prestretch in non-putrefied bodies. Analysis of the prestretch variance with respect to ATH suggested that ATH is not a suitable factor to explain the prestretch variability remaining after the age adjustment. It was concluded that, although atherosclerotic plaques may certainly change the biomechanics of arteries, they do not significantly affect the longitudinal prestretch in the human abdominal aorta.