Application of CHAID analysis in the assessment of breast tumor severity: diagnostic utility by age

Authors

Keywords:

age groups; breast neoplasms; decision making, computer-assisted; decision trees; mammography

Abstract

Introduction: Breast cancer is a frequent cause of mortality. Mammography and models such as CHAID may improve early diagnosis by structuring interactive clinical and radiological variables.

Objective: To identify and rank mammographic features associated with tumor severity according to age group using CHAID analysis.

Methods: A cross-sectional observational study was conducted using a secondary clinic-radiological database comprising 961 records, of which 956 women were included in the final analysis. The variables analyzed included tumor severity, age, nodule shape, margins, and density. A decision tree model based on chi-squared automatic interaction detection (CHAID) was applied, incorporating cross-validation and estimating sensitivity, specificity, and accuracy.

Results: The CHAID model showed higher specificity in women aged <50 years (89.5%) and higher sensitivity in those aged ≥50 years (77.8%). Regarding structural patterns, in the <50-year group, the most discriminative variable was nodule shape, with irregular shape strongly associated with malignancy (76.3%), followed by non-circumscribed margins and iso-density. In women aged ≥50 years, the tree initially split according to margin morphology, particularly spiculated margins, which were associated with a high probability of malignancy (83.3%), followed by irregular shape and low density.

Conclusions: The CHAID model demonstrated age-specific diagnostic utility, with greater accuracy in identifying benign lesions in women younger than 50 years and improved ability to detect malignancy in women aged 50 years or older.

Downloads

Download data is not yet available.

References

1. Arnold M, Morgan E, Rumgay H, Mafra A, Singh D, Laversanne M, et al. Current and future burden of breast cancer: Global statistics for 2020 and 2040 [Internet]. Breast. 2022;66:15–23. DOI: https://doi.org/10.1016/j.breast.2022.08.010

2. Barrios CH. Global challenges in breast cancer detection and treatment [Internet]. Breast. 2022;62(Suppl 1):S3–6. DOI: https://doi.org/10.1016/j.breast.2022.02.003

3. Brown AL, Vijapura C, Patel M, De La Cruz A, Wahab R. Breast cancer in dense breasts: Detection challenges and supplemental screening opportunities [Internet]. Radiographics. 2023;43(10):e230024. DOI: https://doi.org/10.1148/rg.230024

4. Schopp JG, Polat DS, Arjmandi F, Hayes JC, Ahn RW, Sullivan K, et al. Imaging challenges in diagnosing triple-negative breast cancer [Internet]. Radiographics. 2023;43(10):e230027. DOI: https://doi.org/10.1148/rg.230027

5. Patel N, Shah S, Chacha S. A prospective comparative study of breast cancer in pre- and postmenopausal women [Internet]. Natl J Physiol Pharm Pharmacol. 2025;15(2):1. DOI: https://doi.org/10.5455/njppp.2025.v15.i2.15

6. Van Diepen M, Franses PH. Evaluating chi-squared automatic interaction detection [Internet]. Inf Syst. 2006;31(8):814–31. DOI: https://doi.org/10.1016/j.is.2005.03.002

7. Xu H, Xu B. Breast cancer: Epidemiology, risk factors and screening [Internet]. Chin J Cancer Res. 2023 [acceso: 24/07/2025];35(6):565–83. Disponible en: https://doi.org/10.21147/j.issn.1000-9604.2023.06.02

8. Henzler M, Willborn KC, Janni W, Huober J, Lukac S, Otremba B, et al. Oncologic outcomes of young breast cancer patients according to tumor biology [Internet]. Cancers (Basel). 2025;17(8):1333. DOI: https://doi.org/10.3390/cancers17081333

9. Fabiano V, Mandó P, Rizzo M, Ponce C, Coló F, Loza M, et al. Breast cancer in young women presents with more aggressive pathologic characteristics: Retrospective analysis from an Argentine national database [Internet]. JCO Glob Oncol. 2020;6:639–46. DOI: https://doi.org/10.1200/JGO.19.00228

10. Li W, Zhao X, Han Q, Ren C, Gao S, Liu Y, et al. Relationship between breast tissue involution and breast cancer [Internet]. Front Oncol. 2025;15:1420350. DOI: https://doi.org/10.3389/fonc.2025.1420350

11. Lee SH, Moon WK. Glandular tissue component on breast ultrasound in dense breasts: A new imaging biomarker for breast cancer risk [Internet]. Korean J Radiol. 2022;23(6):574–80. DOI: https://doi.org/10.3348/kjr.2022.0099

12. Zhu JW, Charkhchi P, Adekunte S, Akbari MR. What is known about breast cancer in young women? [Internet]. Cancers (Basel). 2023;15(6):1917. DOI: https://doi.org/10.3390/cancers15061917

13. Shroff NK, Posleman Monetto FE. Stromal fibrosis of the breast and the associated radiological findings [Internet]. Cureus. 2021;13(6):e15995. DOI: https://doi.org/10.7759/cureus.15995

14. Nam YH. A study on the factors and prediction model of triple-negative breast cancer for public health promotion [Internet]. Diagnostics (Basel). 2023;13(22):3486. DOI: https://doi.org/10.3390/diagnostics13223486

15. Ponnuraja C, Lakshmanan BC, Srinivasan V, Prasanth BK. Decision tree classification and model evaluation for breast cancer survivability: A data mining approach [Internet]. Biomed Pharmacol J. 2017;10(1):281–9. DOI: https://doi.org/10.13005/bpj/1107

Downloads

Published

2026-01-17

How to Cite

1.
Guevara Tirado A. Application of CHAID analysis in the assessment of breast tumor severity: diagnostic utility by age. Rev. cuba. med. mil [Internet]. 2026 Jan. 17 [cited 2026 Aug. 11];55(1):e026076865. Available from: https://revmedmilitar.sld.cu/index.php/mil/article/view/76865

Issue

Vol. 55 No. 1 (2026): January - March

Section

Research Article

License

Copyright (c) 2026 Alberto Guevara Tirado

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Authors who have publications with this Journal accept the following terms:

  • The authors will retain their copyright and guarantee the Journal the right of first publication of their work, which will simultaneously be subject to the Creative Commons Attribution License. The content presented here can be shared, copied and redistributed in any medium or format; Can be adapted, remixed, transformed or created from the material, using the following terms: Attribution (giving appropriate credit to the work, providing a link to the license, and indicating if changes have been made); non-commercial (you cannot use the material for commercial purposes) and share-alike (if you remix, transform or create new material from this work, you can distribute your contribution as long as you use the same license as the original work).
  • The authors may adopt other non-exclusive license agreements for the distribution of the published version of the work (for example: depositing it in an institutional electronic archive or publishing it in a monographic volume) as long as the initial publication in this Journal is indicated.
  • Authors are allowed and recommended to disseminate their work through the Internet (e.g., in institutional electronic archives or on their website) before and during the submission process, which can produce interesting exchanges and increase citations. of the published work.