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

Abstract

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 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 and are able to estimate the age using the pubic symphysis across the entire adult age range.

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

“…It should also be noted that the models of Stoyanova are restricted to male individuals only. Kotěrová et al, Kotěrová and Figueroa-Soto et al 50 also included male individuals only 27 , 30 , while Joubert et al 28 , Johnson and Bethard 29 and the present study incorporated both sexes. As the results of all the validation studies are similar, the inclusion of female individuals did not appear to affect the performance of the method.…”

“…This results in the strong underestimation of not only older individuals 25 but of the whole sample 27 . Validation studies on different population samples uniformly show low correlation with actual age and higher estimation error 27 – 30 than the error in the original study (27–32 years), which was comparable to the error of one of the traditional visual methods 25 . Recently, Bravo Morante et al presented a new quantitative method based on the bandpass filtering of partial warp bending energy 31 , which is a modification of one of the shape scores (bending energy) applied in a previous study 25 .…”

“…In our previous study 27 based on the sample of 96 individuals with a mean age of 45 years, it was 36–44 years 27 . Slightly better results were found in the Thai population, with the age interval ranging from 30 to 40 30 . Johnson and Bethard 29 reported very broad age intervals, ranging from 60 to 82 years.…”

“…Even though the approach of Stoyanova et al is relatively new, there are several validation studies on different population samples 27 – 29 , 50 . Kotěrová et al 27 conducted a validation on a pooled European sample and later on a Thai sample (unpublished 30 ). Samples used in 27 and 30 are in fact small sub-samples of the significantly extended dataset used in this present study.…”

“…Kotěrová et al 27 conducted a validation on a pooled European sample and later on a Thai sample (unpublished 30 ). Samples used in 27 and 30 are in fact small sub-samples of the significantly extended dataset used in this present study. Johnson and Bethard 29 tested the Stoyanova models on a Portuguese sample, Joubert et al 28 on a sample of South Africans of European ancestry, and Figueroa-Soto et al on skeletal samples from Latin America 50 .…”