Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Apr 30;15(9):1147.
doi: 10.3390/diagnostics15091147.

Equation Built by Multiple Adaptive Regression Spline to Estimate Biological Age in Healthy Postmenopausal Women in Taiwan

Chun-Feng Chang  1   2 , Ta-Wei Chu  3   4 , Chi-Hao Liu  5   6 , Sheng-Tang Wu  1   2 , Chung-Chi Yang  7   8   9   10
Affiliations

Equation Built by Multiple Adaptive Regression Spline to Estimate Biological Age in Healthy Postmenopausal Women in Taiwan

Chun-Feng Chang et al. Diagnostics (Basel). .

Abstract

Background: Biological age (BA) is a better representative of health status than chronological age (CA), as it uses different biological markers to quantify cellular and systemic change status. However, BA can be difficult to accurately estimate using current methods. This study uses multiple adaptive regression spline (MARS) to build an equation to estimate BA among healthy postmenopausal women, thereby potentially improving the efficiency and accuracy of BA assessment. Methods: A total of 11,837 healthy women were enrolled (≥51 years old), excluding participants with metabolic syndrome variable values outside two standard deviations. MARS was applied, with the results compared to traditional multiple linear regression (MLR). The method with the smaller degree of estimation error was considered to be more accurate. The lower prediction errors yielded by MARS compared to the MLR method suggest that MARS performs better than MLR. Results: The equation derived from MARS is depicted. It could be noted that BA could be determined by marriage, systolic blood pressure (SBP), diastolic blood pressure (DBP), waist-hip ratio (WHR), alkaline phosphatase (ALP), lactate dehydrogenase (LDH), creatinine (Cr), carcinoembryonic antigen (CEA), bone mineral density (BMD), education level, and income. The MARS equation is generated. Conclusions: Using MARS, an equation was built to estimate biological age among healthy postmenopausal women in Taiwan. This equation could be used as a reference for calculating BA in general. Our equation showed that the most important factor was BMD, followed by WHR, Cr, marital status, education level, income, CEA, blood pressure, ALP, and LDH.

Keywords: aging; biological age; machine learning; postmenopausal.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Subject identification process.
Figure 2
Figure 2
Influence of important variables on biological age. (A) Marriage. (B) Systolic blood pressure. (C) Diastolic blood pressure. (D) Waist–hip ratio. (E) Alkaline Phosphatase. (F) Lactic dehydrogenase (G) Creatinine. (H) Carcinoembryonic Antigen. (I) Bone Mass Density. (J) Education level. (K) Income.
Figure 2
Figure 2
Influence of important variables on biological age. (A) Marriage. (B) Systolic blood pressure. (C) Diastolic blood pressure. (D) Waist–hip ratio. (E) Alkaline Phosphatase. (F) Lactic dehydrogenase (G) Creatinine. (H) Carcinoembryonic Antigen. (I) Bone Mass Density. (J) Education level. (K) Income.
See this image and copyright information in PMC

References

    1. Yin D., Chen K. The essential mechanisms of aging: Irreparable damage accumulation of biochemical side-reactions. Exp. Gerontol. 2005;40:455–465. doi: 10.1016/j.exger.2005.03.012. - DOI - PubMed
    1. Hollingsworth J.W., Hashizume A., Jablon S. Correlations between tests of aging in Hiroshima subjects—An attempt to define ”physiologic age”. Yale J. Biol. Med. 1965;38:11–26. - PMC - PubMed
    1. Comfort A. Test-battery to measure ageing-rate in man. Lancet. 1969;2:1411–1414. doi: 10.1016/S0140-6736(69)90950-7. - DOI - PubMed
    1. Horvath S., Raj K. DNA methylation-based biomarkers and the epigenetic clock theory of ageing. Nat. Rev. Genet. 2018;19:371–384. doi: 10.1038/s41576-018-0004-3. - DOI - PubMed
    1. Ashiqur Rahman S., Giacobbi P., Pyles L., Mullett C., Doretto G., Adjeroh D.A. Deep learning for biological age estimation. Brief. Bioinform. 2021;22:1767–1781. doi: 10.1093/bib/bbaa021. - DOI - PMC - PubMed

LinkOut - more resources