The application of decision trees for estimating osteological sex from common measurements of the skull.
Saved in:
| Title: | The application of decision trees for estimating osteological sex from common measurements of the skull. |
|---|---|
| Authors: | Ferrell MJ; Department of Anthropology, University of Kentucky, Lexington, Kentucky, USA., Schultz JJ; Department of Anthropology, University of Kentucky, Lexington, Kentucky, USA., Adams DM; Department of Anthropology, University of Central Florida, Orlando, Florida, USA.; National Center for Forensic Science, Orlando, Florida, USA. |
| Source: | Journal of forensic sciences [J Forensic Sci] 2025 May; Vol. 70 (3), pp. 854-867. Date of Electronic Publication: 2025 Mar 26. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: Blackwell Pub Country of Publication: United States NLM ID: 0375370 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1556-4029 (Electronic) Linking ISSN: 00221198 NLM ISO Abbreviation: J Forensic Sci Subsets: MEDLINE |
| Imprint Name(s): | Publication: 2006- : Malden, MA : Blackwell Pub. Original Publication: [Chicago, Ill.] : Callaghan and Co., 1956- |
| MeSH Terms: | Decision Trees* , Sex Determination by Skeleton*/methods , Skull*/anatomy & histology, Adolescent ; Adult ; Aged ; Aged, 80 and over ; Female ; Humans ; Male ; Middle Aged ; Young Adult ; Black or African American ; Cephalometry ; Forensic Anthropology ; White |
| Abstract: | Skull measurements are commonly evaluated for osteological sex estimation in forensic anthropology, and decision tree-based classification models for the skull may improve accuracy compared to current metric methods. Additionally, decision trees can provide accurate sex classification with a limited number of measurements, which is valuable when analyzing fragmentary remains. Thus, the present study seeks to test the utility of decision trees for generating sex classification models from metric variables of the skull. Twenty-one skull measurements were evaluated for 403 adult males and females. Relative technical error of measurement was used to assess intraobserver error, and two-way ANOVAs and aligned rank transformation were used to examine the effects of sex, population, age, and temporal period on the measurements. The data set was split into 80% training and 20% holdout testing samples to assess the predictive accuracy of each tree. Trees were generated for the skull and cranium, with models for European Americans, African Americans, and the pooled population sample. Overall, the recommended trees for the cranium achieved higher accuracies (85.3-95.0%) compared to the skull trees (84.0-92.5%). Accuracies for the population-inclusive trees ranged from 84.0% to 85.3%, whereas the European American (92.5-95.0%) and African American (90.9%) trees achieved slightly higher accuracies. Improved accuracies were achieved compared to previous decision tree research as well as compared to current metric methods for the skull. These trees provide an additional option for estimating osteological sex, particularly when morphological methods do not yield adequate classification accuracies or cannot be assessed due to damage. (© 2025 American Academy of Forensic Sciences.) |
| References: | Byers SN. Introduction to forensic anthropology. 5th ed. London, UK: Routledge; 2016. Spradley MK, Jantz RL. Sex estimation in forensic anthropology: skull versus postcranial elements. J Forensic Sci. 2011;56(2):289–296. https://doi.org/10.1111/j.1556‐4029.2010.01635.x. Scott S, Jantz RL. Survivability versus rate of recovery for skeletal elements in forensic anthropology. J Forensic Sci. 2022;67(5):1758–1765. https://doi.org/10.1111/1556‐4029.15087. Klales AR. Practitioner preferences for sex estimation from human skeletal remains. In: Klales AR, editor. Sex estimation of the human skeleton: history, methods, and emerging techniques. Cambridge, MA: Academic Press; 2020. p. 11–23. Klales AR. Current state of sex estimation in forensic anthropology. Forensic Anthropol. 2021;4(2):118–127. https://doi.org/10.5744/fa.2020.3033. Garvin HM. Adult sex determination: methods and application. In: Dirkmaat DC, editor. A companion to forensic anthropology. Hoboken, NJ: Wiley‐Blackwell; 2012. p. 239–247. Klales AR, Ousley SD, Passalacqua NV. Statistical approaches to sex estimation. In: Klales AR, editor. Sex estimation of the human skeleton: history, methods, and emerging techniques. Cambridge, MA: Academic Press; 2020. p. 203–217. Giles E. Sex determination by discriminant function analysis of the mandible. Am J Phys Anthropol. 1964;22(2):129–135. https://doi.org/10.1002/ajpa.1330220212. Giles E, Elliot O. Sex determination by discriminant function analysis of crania. Am J Phys Anthropol. 1963;21(1):53–68. https://doi.org/10.1002/ajpa.1330210108. Franklin D, Cardini A, Flavel A, Kuliukas A. Estimation of sex from cranial measurements in a Western Australian population. Forensic Sci Int. 2013;229(1–3):158.e1–158.e8. https://doi.org/10.1016/j.forsciint.2013.03.005. Ousley SD, Jantz RL. FORDISC 3.1: Personal Computer Forensic Discriminant Functions [computer program]. Knoxville, TN: University of Tennessee; 2012. Slice DE, Ross AH. 3D‐ID: Geometric Morphometric Classification of Crania for Forensic Scientists [computer program]. Raleigh, NC: North Carolina State University; 2018. Ousley SD, Jantz RL. Fordisc 3 and statistical methods for estimating sex and ancestry. In: Dirkmaat DC, editor. A companion to forensic anthropology. Hoboken, NJ: Wiley‐Blackwell; 2012. p. 311–329. Nikita E, Nikitas P. Sex estimation: a comparison of techniques based on binary logistic, probit and cumulative probit regression, linear and quadratic discriminant analysis, neural networks, and naïve Bayes classification using ordinal variables. Int J Leg Med. 2020;134(3):1213–1225. https://doi.org/10.1007/s00414‐019‐02148‐4. Ferrell MJ, Schultz JJ, Adams DM. Sex estimation research trends in forensic anthropology between 2000 and 2022 in five prominent journals. J Forensic Sci. 2024;69(4):1138–1154. https://doi.org/10.1111/1556‐4029.15522. Langley NR, Dudzik B, Cloutier A. A decision tree for nonmetric sex assessment from the skull. J Forensic Sci. 2018;63(1):31–37. https://doi.org/10.1111/1556‐4029.13534. Navega D, Vicente R, Vieira DN, Ross AH, Cunha E. Sex estimation from the tarsal bones in a Portuguese sample: a machine learning approach. Int J Leg Med. 2015;129(3):651–659. https://doi.org/10.1007/s00414‐014‐1070‐5. Nikita E, Nikitas P. On the use of machine learning algorithms in forensic anthropology. Legal Med. 2020;47:101771. https://doi.org/10.1016/j.legalmed.2020.101771. Savall F, Faruch‐Bilfeld M, Dedouit F, Sans N, Rousseau H, Rougé D, et al. Metric sex determination of the human coxal bone on a virtual sample using decision trees. J Forensic Sci. 2015;60(6):1395–1400. https://doi.org/10.1111/1556‐4029.12845. Toneva DH, Nikolova SY, Agre GP, Zlatareva DK, Hadjidekov VG, Lazarov NE. Data mining for sex estimation based on cranial measurements. Forensic Sci Int. 2020;315:110441. https://doi.org/10.1016/j.forsciint.2020.110441. Toy S, Secgin Y, Oner Z, Turan MK, Oner S, Senol D. A study on sex estimation by using machine learning algorithms with parameters obtained from computerized tomography images of the cranium. Sci Rep. 2022;12:4278. https://doi.org/10.1038/s41598‐022‐07415‐w. Zhou ZH. Machine learning. Singapore: Springer Singapore; 2021. p. 79–102. Freitas AA. Comprehensible classification models: a position paper. ACM SIGKDD Explor Newsl. 2014;15(1):1–10. https://doi.org/10.1145/2594473.2594475. Loyola‐Gonzalez O. Black‐box vs. white‐box: understanding their advantages and weaknesses from a practical point of view. IEEE Access. 2019;7:154096–154113. https://doi.org/10.1109/ACCESS.2019.2949286. Carlson DL. Quantitative methods in archaeology using R. New York, NY: Cambridge University Press; 2017. Toneva D, Nikolova S, Agre G, Zlatareva D, Fileva N, Lazarov N. Sex estimation based on mandibular measurements. Anthropol Anz. 2024;81(1):19–42. https://doi.org/10.1127/anthranz/2023/1733. Mota MJS, Vieira ACA, Lima LS, Sátiro JVM, Menezes Neto CMD, Paixão PLP, et al. Sex determination based on craniometric parameters: a comparative approach between linear and non‐linear machine learning algorithms. J Arch Health. 2024;5(1):634–651. https://doi.org/10.46919/archv5n1‐042. Christensen AM, Crowder CM. Evidentiary standards for forensic anthropology. J Forensic Sci. 2009;54(6):1211–1216. https://doi.org/10.1111/j.1556‐4029.2009.01176.x. Nakhaeizadeh S, Dror IE, Morgan RM. Cognitive bias in sex estimation: the influence of context on forensic decision‐making. In: Klales AR, editor. Sex estimation of the human skeleton. Cambridge, MA: Academic Press; 2020. p. 327–342. Alioto AP. A new division of labor? Understanding structural violence through occupational stress: an examination of entheseal patterns and osteoarthritis in the Hamann–Todd collection. In: Tremblay LA, Reedy S, editors. The bioarchaeology of structural violence. Cham, Switzerland: Springer International Publishing; 2020. p. 169–201. Academy Standards Board. ASB Standard 132 – Standard for population affinity estimation in forensic anthropology. Colorado Springs, CO: AAFS Standards Board; 2023. Maier C, Craig A, Adams DM. Language use in ancestry research and estimation. J Forensic Sci. 2021;66(1):11–24. https://doi.org/10.1111/1556‐4029.14601. Spradley K, Jantz R. What are we really estimating in forensic anthropological practice, population affinity or ancestry? Forensic Anthropol. 2022;4(4):309–318. https://doi.org/10.5744/fa.2021.0017. Harrison D. Investigations in sex estimation. Amsterdam, Netherlands: Elsevier; 2019. Ferrell MJ. Improving osteological sex estimation methods for the skull: combining morphological traits and measurements utilizing decision trees and random forest modeling [dissertation]. Orlando, FL: University of Central Florida; 2024. Perini TA, de Oliveira GL, dos Santos Ornellas J, de Palha Oliveira F. Technical error of measurement in anthropometry. Rev Bras Med Esporte. 2005;11(1):81–85. https://doi.org/10.1590/S1517‐86922005000100009. Langley NR, Meadows Jantz L, McNulty S, Maijanen H, Ousley SD, Jantz RL. Error quantification of osteometric data in forensic anthropology. Forensic Sci Int. 2018;287:183–189. https://doi.org/10.1016/j.forsciint.2018.04.004. Langley NR, Jantz LM, Ousley SD, Jantz RL, Milner G. Data collection procedures for forensic skeletal material 2.0. Knoxville, TN: The University of Tennessee; 2016. R Core Team. Package “stats”. 2019. https://www.rdocumentation.org/packages/stats/versions/3.6.2. Accessed 12 Mar 2025. Wuertz D, Setz T, Chalabi Y, Maechler M, Boshnakov GN. Package “fBasics”. 2024. https://cran.r‐project.org/web/packages/fBasics/index.html. Accessed 12 Mar 2025. Gross J, Ligges U. Package “nortest”. 2015. https://cran.r‐project.org/web/packages/nortest/index.html. Accessed 12 Mar 2025. Yap BW, Sim CH. Comparisons of various types of normality tests. J Stat Comput Simul. 2011;81(12):2141–2155. https://doi.org/10.1080/00949655.2010.520163. Fox J, Weisberg S, Price B, Adler D, Bates D, Baud‐Bovy G, et al. Package “car”. 2024. https://cran.r‐project.org/web/packages/car/index.html. Accessed 12 Mar 2025. Revelle W. Package “psych”. 2024. https://cran.r‐project.org/web/packages/psych/index.html. Accessed 12 Mar 2025. Kay M, Elkin LA, Higgins JJ, Wobbrock JO. Package ‘ARTool’. 2021. https://cran.r‐project.org/web/packages/ARTool/ARTool.pdf. Accessed 12 Mar 2025. Lesciotto K, Doershuk L. Effect of age on nonmetric cranial traits for sex estimation in adults. Forensic Anthropol. 2018;1(3):150–159. https://doi.org/10.5744/fa.2018.0016. Tallman S. Cranial nonmetric sexual dimorphism and sex estimation in east and southeast asian individuals. Forensic Anthropol. 2019;2(4):204–221. https://doi.org/10.5744/fa.2019.1010. Boldsen JL, Milner GR, Konigsberg LW, Wood JW. Transition analysis: a new method for estimating age from skeletons. In: Hoppa RD, Vaupel JW, editors. Paleodemography. Cambridge: Cambridge University Press; 2002. p. 73–106. Milner GR, Boldsen JL. Skeletal age estimation. Where we are and where we should go. In: a companion to forensic anthropology. West Sussex, UK: Blackwell Publishing; 2012. p. 224–238. Garvin HM, Passalacqua NV, Uhl NM, Gipson DR, Overbury RS, Cabo LL. Developments in forensic anthropology: Age‐at‐death estimation. A companion to forensic anthropology. West Sussex, UK: Blackwell Publishing; 2012. p. 202–223. Signorell A, Aho K, Alfons A, Anderegg N, Aragon T, Arachchige C, et al. Package “DescTools”. 2023. https://cran.r‐project.org/web/packages/DescTools/index.html. Accessed 12 Mar 2025. Cohen J. Statistical power analysis for the behavioral sciences. 2nd ed. New York, NY: Lawrence Erlbaum Associates; 1988. Hothorn T, Hornik K, Strobl C, Zeileis A. Package “party”. 2023. https://cran.r‐project.org/web/packages/party/party.pdf. Accessed 12 Mar 2025. Hothorn T, Hornik K, Zeileis A. Unbiased recursive partitioning: a conditional inference framework. J Comput Graph Stat. 2006;15(3):651–674. https://doi.org/10.1198/106186006X133933. Haynes W. Bonferroni correction. In: Dubitzky W, Wolkenhauer O, Cho KH, Yokota H, editors. Encyclopedia of systems biology. New York, NY: Springer New York; 2013. p. 154. Hothorn T, Hornik K, Zeileis A. ctree: Conditional inference trees. Cranr‐Proj. 2015. https://cran.r‐project.org/web/packages/partykit/vignettes/ctree.pdf. Accessed 12 Mar 2025. Martin DC, Danforth ME. An analysis of secular change in the human mandible over the last century. Am J Hum Biol. 2009;21(5):704–706. https://doi.org/10.1002/ajhb.20866. Pessa JE, Slice DE, Hanz KR, Broadbent TH, Rohrich RJ. Aging and the shape of the mandible. Plast Reconstr Surg. 2008;121(1):196–200. https://doi.org/10.1097/01.prs.0000293864.94138.ae. Jantz RL. Cranial change in Americans: 1850‐1975. J Forensic Sci. 2001;46(4):784–787. https://doi.org/10.1520/JFS15047J. Jantz RL, Meadows Jantz L. Secular change in craniofacial morphology. Am J Hum Biol. 2000;12(3):327–338. https://doi.org/10.1002/(sici)1520‐6300(200005/06)12:3%3C327::aid‐ajhb3%3E3.0.co;2‐1. Wescott DJ, Jantz RL. Assessing craniofacial secular change in American blacks and whites using geometric morphometry. In: Slice DE, editor. Modern morphometrics in physical anthropology. New York, NY: Kluwer Academic; 2005. p. 231–246. Kelley SR, Tallman SD. Population‐inclusive assigned‐sex‐at‐birth estimation from skull computed tomography scans. Forensic Sci. 2022;2(2):321–348. https://doi.org/10.3390/forensicsci2020024. Pilloud MA, Kenessey DE, Smith EM, Vlemincq‐Mendieta T. Estimation of sex assigned at birth using dental crown and cervical measurements in a modern global sample. J Forensic Sci. 2024;69(6):1996–2008. https://doi.org/10.1111/1556‐4029.15593. Adams DM, Pilloud M. The (mis)appropriation of biological anthropology in race science and the implications for forensic anthropology. Forensic Sci Int. 2021;4(4):235–256. https://doi.org/10.5744/fa.2021.0010. Ferrell MJ, Schultz JJ, Adams DM. Decision trees for estimating osteological sex from the skull using an expanded suite of morphological traits. In press. https://doi.org/10.1111/1556‐4029.70017. Constantinou C, Nikita E. SexEst: an open access web application for metric skeletal sex estimation. Int J Osteoarchaeol. 2022;32(4):832–844. https://doi.org/10.1002/oa.3109. Jantz RL, Ousley SD. Sexual dimorphism variation in Fordisc samples. In: Klales AR, editor. Sex estimation of the human skeleton. London, UK: Academic Press/Elsevier; 2020. p. 185–200. Nikita E, Nikitas P. Data mining and decision trees. In: Obertova Z, Stewart A, Cattaneo C, editors. Statistics and probability in forensic anthropology. Cambridge, MA: Academic Press; 2020. p. 87–105. |
| Contributed Indexing: | Keywords: biological profile; decision trees; forensic anthropology; machine learning; sex estimation; skull |
| Entry Date(s): | Date Created: 20250326 Date Completed: 20250502 Latest Revision: 20250514 |
| Update Code: | 20250514 |
| DOI: | 10.1111/1556-4029.70031 |
| PMID: | 40135464 |
| Database: | MEDLINE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | Skull measurements are commonly evaluated for osteological sex estimation in forensic anthropology, and decision tree-based classification models for the skull may improve accuracy compared to current metric methods. Additionally, decision trees can provide accurate sex classification with a limited number of measurements, which is valuable when analyzing fragmentary remains. Thus, the present study seeks to test the utility of decision trees for generating sex classification models from metric variables of the skull. Twenty-one skull measurements were evaluated for 403 adult males and females. Relative technical error of measurement was used to assess intraobserver error, and two-way ANOVAs and aligned rank transformation were used to examine the effects of sex, population, age, and temporal period on the measurements. The data set was split into 80% training and 20% holdout testing samples to assess the predictive accuracy of each tree. Trees were generated for the skull and cranium, with models for European Americans, African Americans, and the pooled population sample. Overall, the recommended trees for the cranium achieved higher accuracies (85.3-95.0%) compared to the skull trees (84.0-92.5%). Accuracies for the population-inclusive trees ranged from 84.0% to 85.3%, whereas the European American (92.5-95.0%) and African American (90.9%) trees achieved slightly higher accuracies. Improved accuracies were achieved compared to previous decision tree research as well as compared to current metric methods for the skull. These trees provide an additional option for estimating osteological sex, particularly when morphological methods do not yield adequate classification accuracies or cannot be assessed due to damage.<br /> (© 2025 American Academy of Forensic Sciences.) |
|---|---|
| ISSN: | 1556-4029 |
| DOI: | 10.1111/1556-4029.70031 |