On the accuracy of visual age estimation from the adult skull (methodological aspects)

Abstract

Introduction. The task of differentiating groups using various statistical methods remains relevant due to the limitations often encountered with standard algorithms. Some of these limitations, such as the assumption of normal distribution of traits and the absence of high correlations between them, can be circumvented by the method based on step-wise partitioning – decision trees.

Materials and methods. In this study, this method was tested on 15 linear dimensions of the skull and 16 indices calculated based on them. The entropy index was chosen as the criterion of heterogeneity. The craniometric features used correspond to the standard methodology adopted in Russian anthropology. The data consisted of average values of craniometric dimensions from 39 ethno-territorial groups from 13 macro-regions of the Old World.

Results and discussion. The results of the differentiation show that indices have a greater weight than linear features. Five linear dimensions and seven indices participated in the differentiation. Three indices were based on the overall dimensions of the braincase (M.1, M.8, M.17), and four indices included the bizygomatic width (M.45). The first split occurs based on the transverse facial index (46:45), separating the groups of Northern, Middle, Central Asia, and Europe from the groups of Africa, Eastern, Southeast, and Southern Asia.

Conclusion. The study demonstrates the high differentiating ability of indices, particularly the transverse facial index, fronto-zygomatic index, and height-length index. The iterative differentiation system allows for a more informative separation of groups, as different combinations of features demonstrate effectiveness at different hierarchical levels of taxonomy. © 2025. This work is licensed under a CC BY 4.0 license

References

Alekseev V.P., Debetz G.F. Kraniometriya. Metodika antropologicheskih issledovanij [Craniometry. Methodology of anthropological research]. Moscow, Nauka Publ., 1964. 128 p. (In Russ.).

Bunak V.V. Crania armenica. Studies on anthropology of West Asia. Moscow, 1927. 314 p. (In Russ.).

Benevolenskaya Yu.D. Group-distinguishing properties of features of the occipital region of the skull. In: Collection of the MAE, 1980, 36, pp. 108–120. (In Russ.).

Benevolenskaya Yu.D. Cranial vault features as markers of different levels of differentiation of different races. In: Collection of the MAE, 1991, 44, pp.136–152. (In Russ.).

Goncharova N.N., Konopel'kin D.S. New data on the anthropology of the Finnish tribes of the Upper Volga and Oka basin. In: Physical anthropology: methods, databases, scientific results, 2014, pp. 89–103. (In Russ.).

Debetz G.F. Paleoanthropology of the USSR. In: Proceedings of the Institute of Ethnography, New Series, IV, 1948. (In Russ.).

Debetz G.F. Paleoanthropology of ancient Eskimos (Ipiutak, Tigara). Ethnic relations of the peoples of the north of Asia and America on the basis of anthropological data. Moscow, 1986. pp. 6–149.

Deryabin V.E. A lecture course on multivariate biometrics for anthropologists. Moscow, Moscow, Moscow State University MGU, 2008. 332 p. (In Russ.).

Ismagulov O. The population of Kazakhstan from the Bronze Age to the present (paleoanthropological study). Alma-Ata, Nauka Publ., 1970. 241 p. (In Russ.).

Pestryakov A.P., Grigor'eva O.M. Craniological differentiation of the modern population. Races and peoples, 2004, 30, pp. 86—131. (In Russ.).

Pestryakov A.P., Grigor'eva O.M. Australian Aborigines in the craniologic background of East Asian and Western Oceania populations. In: Vestnik Moskovskogo universiteta. Seriya 23. Antropologiya [Moscow University Anthropology Bulletin], 2013, 2, pp. 17–33. (In Russ.).

Fedorchuk O.A. Materials to the correlative variability of measuring features of the human skull. Moscow, Klub Pechati Publ., 2022. 239 p. (In Russ.).

Fedorchuk O.A., Goncharova N.N. Applying the decision tree method to differentiate groups of humanity. Archaeology, Ethnography and Anthropology of Eurasia, 2024. 52(3) pp.148–156. DOI: 10.17746/1563-0102.2024.52.3.148-156. (In Russ.).

Fel'dman M.G. Using the Random Forest method to predict pink salmon runs in the Northeast Kamchatka Peninsula. The Researches of the Aquatic Biological Resources of Kamchatka and the North-West Part of the Pacific Ocean. 2021, 59, pp. 76–96. (In Russ.).

Martin R. Lehrbuch der Anthropologie in Systematischer darstellung. Bd. II. Kraniologie. Osteologie. Jena, 1928. 1182 p.

Breiman L., Stone C.J. Parsimonious binary classification trees. Technical Note, 1978.

Bonin G. von. Beitrag Zur Kraniologie von Ost-Asien. Biometrika, 1931а, 23 (1/2), pp. 52–113.

Bonin G. von. A Contribution to the Craniology of the Easter Islanders. Biometrika, 1931б, 23 (3/4), pp. 249–270.

Bonin G. von. On the Craniology of Oceania. Crania from New Britain. Biometrika, 1936, 28 (1/2), pp. 123–148.

Breiman L., Friedman J.H., Olshen R.A., Stone C.J. Classification and regression trees. Wadsworth Inc, 1984. 354 p.

Cartmill M. A sort of revolution: Systematics and physical anthropology in the 20th century. American Journal of Physical Anthropology, 2018, 165 (4), pp. 677–687. DOI: 10.1002/ajpa.23321.

Djuris J., Ibric S., Djuric Z. Neural computing in pharmaceutical products and process development. Computer-Aided Applications in Pharmaceutical Technology, 2013, pp. 91–175. DOI: 10.1533/9781908818324.91.

Drontschilow K. Metrische Studien an 93 Schädeln aus Kamerun. Archiv für antropologie, 1913, pp. 161–183.

Hambly W.D. Craniometry of New Guinea. Chicago, 1940. 338 p.

Harrower G. A Study of the Hokien and Tamil Skull. Biometrika, 1924, 54 (3), pp. 573–599.

Hugenholtz P., Chuvochina M., Oren A., Parks D.H., Soo R.M. Prokaryotic taxonomy and nomenclature in the age of big sequence data. ISME Journal, 2021, 15 (7), pp. 1879–1892. DOI: 10.1038/s41396-021-00941-x.

Kitson E. A Study of the Negro Skull with Special Reference to the Crania from Kenya Colony. Biometrika, 1931, 23 (3), pp. 271–314.

Al Mamun M.H., Keikhosrokiani P. Predicting onset (type-2) of diabetes from medical records using binary class classification. Big Data Analytics for Healthcare, 2022, pp. 301–312. DOI: 10.1016/B978-0-323-91907-4.00012.

Martin R. Lehrbuch der Anthropologie. 2-te Aufl. Bd. II, 1928.

Morant G.M. A Study of Certain Oriental Series of Crania Including the Nepalese and Tibetan Series in the British Museum (Natural History). Biometrika, 1924, 16 (1/2), pp. 1–10.

Morant G.M. A Contribution to Basque Craniometry. Biometrika, 1929, 21 (1/4), pp. 67–84.

Pedregosa F., Varoquaux, G., Gramfort, A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay E. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 2011, 12, pp. 2825–2830.

Quinlan J.R. Induction of decision trees. Machine Learning, 1986, 1 (1), pp. 81–106. DOI: 10.1007/BF00116251.

Sergi S. Crania habessinica: contributo all’antropologia dell’Africa orientale. Loescher, Roma, 1912. 519 p.

Sokal R.R., Sneath P.H.A. Principles of Numerical Taxonomy. W. H. Freeman, Ed., 1963. 359 p.

Tildesley M.L. A First Study of the Burmese Skull. Biometrika, 1921, 13 (2/3), pp. 176–262.

Wong S.L., Zhang L.V, Y Tong A.H., Li Z., Goldberg D. S., King O.D., Lesage G., Vidal M., Andrews B., Bussey H., Boone C., Roth F.P. Combining biological networks to predict genetic interactions. Proc Natl Acad Sci USA, 2004, 101 (44), pp. 15682–15687. www.pnas.orgcgidoi10.1073pnas.0406614101.