Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Clinical Research Article
  • Published:

Evaluation of height prediction models: from traditional methods to artificial intelligence

Pediatric Research volume 95, pages 308–315 (2024)Cite this article

Abstract

Background

Traditional methods for predicting adult height (AHP) rely on manual readings of bone age (BA). However, the incorporation of artificial intelligence has recently improved the accuracy of BA readings and their incorporation into AHP models.

Methods

This study aimed to identify the AHP model that fits the current average height for adults in Mexico. Using a cross-sectional design, the study included 1173 participants (5–18 yr). BA readings were done by two experts (manually) and with an automated method (BoneXpert®). AHP was carried out using both traditional and automated methods. The best AHP model was the one that was closest to the population mean.

Results

All models overestimated the population mean (males: 0.7–6.7 cm, females: 0.9–3.7 cm). The AHP models with the smallest difference were BoneXpert for males and Bayley & Pinneau for females. However, the manual readings of BA showed significant interobserver variability (up to 43% of predictions between observers exceeded 5 cm using the Bayley & Pinneau method).

Conclusion

Traditional AHP models relying on manual BA readings have high interobserver variability. Therefore, BoneXpert is the most reliable option, reducing such variability and providing AHP models that remain close to the mean population height.

Impact

  • Traditional models for predicting adult height often result in overestimated height predictions.

  • The manual reading of bone age is prone to interobserver variability, which can introduce significant biases in the prediction of adult height.

  • The BoneXpert method minimizes the variability associated with traditional methods and demonstrates consistent results in relation to the average height of the population.

  • This study is the first to assess adult height prediction models specifically in the current generations of Mexican children.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Agreement between manual BA readings using the GP and TW2 methods.
Fig. 2: Predictions obtained using different AHP models, by sex.
Fig. 3: AHPs obtained using each of the models, by sex and CA.

Similar content being viewed by others

Data availability

The data that support the results of this study are not publicly available because they contain information that could compromise the privacy of the pediatric participants who participated in the research. For more information, you can contact the corresponding author: A.L.M-L. with e-mail: americaml@hotmail.com.

References

  1. Martin, D. D. et al. The Use of Bone Age in Clinical Practice - Part 1. Horm. Res. Paediatr. 76, 1–9 (2011).

    Article  CAS  PubMed  Google Scholar 

  2. Martin, D. D. et al. The Use of Bone Age in Clinical Practice - Part 2. Horm. Res. Paediatr. 76, 10–16 (2011).

    Article  CAS  PubMed  Google Scholar 

  3. Greulich, W. W. & Pyle, S. I. Radiographic Atlas of Skeletal Development of the Hand and Wrist 2nd Ed., Vol. 11 (Stanford, CA: Stanford University Press, 1959).

  4. Tanner, J. M. & Whitehouse, R. J. A New System for Estimating Skeletal Maturity from the Hand and Wrist, with Standards Derived from a Study of 2600 Healthy British Children. Part Ii: The Scoring System, Vol. 2 (International Children’s Centre, 1959).

  5. Roche, A. F., Rohmann, C. G., French, N. Y. & Dávila, G. H. Effect of Training on Replicability of Assessments of Skeletal Maturity (Greulich-Pyle). Am. J. Roentgenol. Radium Ther. Nucl. Med. 108, 511–515 (1970).

    Article  CAS  PubMed  Google Scholar 

  6. Bull, R. K., Edwards, P. D., Kemp, P. M., Fry, S. & Hughes, I. A. Bone Age Assessment: A Large Scale Comparison of the Greulich and Pyle, and Tanner and Whitehouse (Tw2) Methods. Arch. Dis. Child 81, 172–173 (1999).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Thodberg, H. H., Kreiborg, S., Juul, A. & Pedersen, K. D. The Bonexpert Method for Automated Determination of Skeletal Maturity. IEEE Trans. Med. Imaging 28, 52–66 (2009).

    Article  PubMed  Google Scholar 

  8. Thodberg, H. H. & Sävendahl, L. Validation and Reference Values of Automated Bone Age Determination for Four Ethnicities. Acad. Radio. 17, 1425–1432 (2010).

    Article  Google Scholar 

  9. Klünder-Klünder, M. et al. Skeletal Maturation in the Current Pediatric Mexican Population. Endocr. Pr. 26, 1053–1061 (2020).

    Article  Google Scholar 

  10. Bayley, N. & Pinneau, S. R. Tables for Predicting Adult Height from Skeletal Age: Revised for Use with the Greulich-Pyle Hand Standards. J. Pediatr. 40, 423–441 (1952).

    Article  CAS  PubMed  Google Scholar 

  11. Roche, A. F., Wainer, H. & Thissen, D. The Rwt Method for the Prediction of Adult Stature. Pediatrics 56, 1027–1033 (1975).

    Article  CAS  PubMed  Google Scholar 

  12. Tanner, J. M., Landt, K. W., Cameron, N., Carter, B. S. & Patel, J. Prediction of Adult Height from Height and Bone Age in Childhood. A New System of Equations (Tw Mark Ii) Based on a Sample Including Very Tall and Very Short Children. Arch. Dis. Child 58, 767–776 (1983).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Preece, M. A. Prediction of Adult Height: Methods and Problems. Acta Paediatr. Scand. Suppl. 347, 4–11 (1988).

    CAS  PubMed  Google Scholar 

  14. Martin, D. D., Calder, A. D., Ranke, M. B., Binder, G. & Thodberg, H. H. Accuracy and Self-Validation of Automated Bone Age Determination. Sci. Rep. 12, 6388 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Tanner JM, H. M., Goldstein H., Cameron N. Assessment of Skeletal Maturity and Prediction of Adult Height (Tw3 Method). 3rd Ed (London; New York: W.B. Saunders, 2001).

  16. Thodberg, H. H. et al. Adult Height Prediction Models. In Handbook of Growth and Growth Monitoring in Health and Disease (ed. Preedy, V.) 1–14 (Springer, New York, NY, 2012).

  17. Martin, D. D., Schittenhelm, J. & Thodberg, H. H. Validation of Adult Height Prediction Based on Automated Bone Age Determination in the Paris Longitudinal Study of Healthy Children. Pediatr. Radio. 46, 263–269 (2016).

    Article  Google Scholar 

  18. Thodberg, H. H., Jenni, O. G., Caflisch, J., Ranke, M. B. & Martin, D. D. Prediction of Adult Height Based on Automated Determination of Bone Age. J. Clin. Endocrinol. Metab. 94, 4868–4874 (2009).

    Article  CAS  PubMed  Google Scholar 

  19. BoneXpert. Whitepaper on the Bonexpert. Adult Height Prediction Method, Version 3.0, Available: https://bonexpert.com/files/AHP-BoneXpert-whitepaper-2021.pdf?4f45e3&4f45e3 (2021).

  20. Miranda-Lora, A. L. et al. Reference Values of Automated Bone Age and Bone Health Index for Mexican Children and Adolescents. 57th Annual European Society for Paediatric Endocrinology (Espe). Horm. Res. Paediatr. ume 90, 111–112 (2018).

    Google Scholar 

  21. Marshall, W. A. & Tanner, J. M. Growth and Physiological Development During Adolescence. Annu Rev. Med. 19, 283–300 (1968).

    Article  CAS  PubMed  Google Scholar 

  22. INSP. Bases De Datos De Encuesta Nacional De Salud Y Nutrición 2021, Available: https://ensanut.insp.mx (2021).

  23. WHO Multicentre Growth Reference Study Group. WHO Child Growth Standards based on length/height, weight and age. Acta. Paediatr. Suppl. 95, 76–85 (2006).

  24. Roemmich, J. N. et al. Longitudinal Assessment of Hormonal and Physical Alterations During Normal Puberty in Boys. Iv: Predictions of Adult Height by the Bayley-Pinneau, Roche-Wainer-Thissen, and Tanner-Whitehouse Methods Compared. Am. J. Hum. Biol. 9, 371–380 (1997).

    Article  PubMed  Google Scholar 

  25. Lenko, H. L. Prediction of Adult Height with Various Methods in Finnish Children. Acta Paediatr. Scand. 68, 85–92 (1979).

    Article  CAS  PubMed  Google Scholar 

  26. CDC. Growth Charts. Centers for Disease Control and Prevention., Available: https://www.cdc.gov/growthcharts/clinical_charts.htm (2000).

  27. Cossio-Bolaños, M. A. et al. Estimation of Pubertal Growth Spurt Parameters in Children and Adolescents Living at Moderate Altitude in Colombia. Front. Endocrinol. (Lausanne) 12, 718292 (2021).

    Article  PubMed  Google Scholar 

  28. Mao, S. H. et al. An Updated Analysis of Pubertal Linear Growth Characteristics and Age at Menarche in Ethnic Chinese. Am. J. Hum. Biol. 23, 132–137 (2011).

    Article  PubMed  Google Scholar 

  29. Ali, M. A., Lestrel, P. E. & Ohtsuki, F. Adolescent Growth Events in Eight Decades of Japanese Cohort Data: Sex Differences. Am. J. Hum. Biol. 13, 390–397 (2001).

    Article  CAS  PubMed  Google Scholar 

  30. Bogin, B., Wall, M. & MacVean, R. B. Longitudinal Analysis of Adolescent Growth of Ladino and Mayan School Children in Guatemala: Effects of Environment and Sex. Am. J. Phys. Anthropol. 89, 447–457 (1992).

    Article  CAS  PubMed  Google Scholar 

  31. Ostojic, S. M. Prediction of Adult Height by Tanner-Whitehouse Method in Young Caucasian Male Athletes. Qjm 106, 341–345 (2013).

    Article  CAS  PubMed  Google Scholar 

  32. Lolli, L. et al. Tanner-Whitehouse and Modified Bayley-Pinneau Adult Height Predictions in Elite Youth Soccer Players from the Middle East. Med. Sci. Sports Exerc. 53, 2683–2690 (2021).

    Article  PubMed  Google Scholar 

  33. Mansukoski, L. & Johnson, W. How Can Two Biological Variables Have Opposing Secular Trends, yet Be Positively Related? A Demonstration Using Timing of Puberty and Adult Height. Ann. Hum. Biol. 47, 549–554 (2020).

    Article  PubMed  Google Scholar 

  34. Juul, F., Chang, V. W., Brar, P. & Parekh, N. Birth Weight, Early Life Weight Gain and Age at Menarche: A Systematic Review of Longitudinal Studies. Obes. Rev. 18, 1272–1288 (2017).

    Article  CAS  PubMed  Google Scholar 

  35. Currie, C. et al. Is Obesity at Individual and National Level Associated with Lower Age at Menarche? Evidence from 34 Countries in the Health Behaviour in School-Aged Children Study. J. Adolesc. Health 50, 621–626 (2012).

    Article  PubMed  Google Scholar 

  36. Eitel, K. B. & Eugster, E. A. Diferences in Bone Age Readings between Pediatric Endocrinologist and Radiologist. Endocr. Pr. 26, 328–331 (2020).

    Article  Google Scholar 

  37. Beunen, G. & Cameron, N. The Reproducibility of Tw2 Skeletal Age Assessments by a Self-Taught Assessor. Ann. Hum. Biol. 7, 155–162 (1980).

    Article  CAS  PubMed  Google Scholar 

  38. Little, B. B. & Malina, R. M. Gene-Environment Interaction in Skeletal Maturity and Body Dimensions of Urban Oaxaca Mestizo Schoolchildren. Ann. Hum. Biol. 34, 216–225 (2007).

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

We thank Dr. Thodberg for the support with licenses for the use of BoneXpert software and the Consejo Nacional de Ciencia y Tecnología (CONACYT) for the scholarship awarded to the master’s student Ana Gabriela Chávez Vázquez.

Funding

The study was supported by Mexican Federal Funds (HIM/2017/058 SSA 1344). The funding source was not involved in the research and/or preparation of the paper.

Author information

Authors and Affiliations

  1. Unit of Epidemiological Research in Endocrinology and Nutrition, Hospital Infantil de México Federico Gómez, Mexico City, Mexico

    Ana G. Chávez-Vázquez & América L. Miranda-Lora

  2. Research Subdirectorate, Hospital Infantil de México Federico Gómez, Mexico City, Mexico

    Miguel Klünder-Klünder

  3. Pediatric Obesity Clinic and Wellness Unit, Hospital General de México “Dr. Eduardo Liceaga” and Hospital Ángeles del Pedregal, Mexico City, Mexico

    Nayely G. Garibay-Nieto

  4. Research Unit in Clinical Epidemiology, Hospital Infantil de México Federico Gómez, Mexico City, Mexico

    Desirée López-González

  5. Radiology Department, Hospital Infantil de México Federico Gómez, Mexico City, Mexico

    Mariana Sánchez-Curiel Loyo

Authors
  1. Ana G. Chávez-Vázquez
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Miguel Klünder-Klünder
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nayely G. Garibay-Nieto
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Desirée López-González
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mariana Sánchez-Curiel Loyo
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. América L. Miranda-Lora
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

C-V. and M-L. conceptualized and designed the study, drafted the initial paper, designed the data collection instruments, collected data, carried out the initial analyses and drafted the initial paper. K-K. conceptualized and designed the study and carried out the statical analyses. G-N., L-G. and S-C. Loyo designed the data collection instruments and collected data. All authors critically reviewed the paper for important intellectual content and approved the final paper as submitted and agree to be accountable for all aspects of the work.

Corresponding author

Correspondence to América L. Miranda-Lora.

Ethics declarations

Competing interests

The authors declare no competing interests.

Informed consent

All participants signed the letters of consent and informed assent, in accordance with the Declaration of Helsinki.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chávez-Vázquez, A.G., Klünder-Klünder, M., Garibay-Nieto, N.G. et al. Evaluation of height prediction models: from traditional methods to artificial intelligence. Pediatr Res 95, 308–315 (2024). https://doi.org/10.1038/s41390-023-02821-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41390-023-02821-w

Search

Advanced search

Quick links