Association between serum uric acid level and bone mineral density at multiple skeletal sites in middle-aged and elderly men: a cross-sectional study of a healthy population in Taiwan

Lin, Zih-Cen; Wu, Jhu-Fong; Chang, Chiung-Yun; Lai, Kuan-Ming; Yang, Hsin-Yi

doi:10.1007/s11657-022-01186-7

Cited by 2 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…57 However, other studies have found no direct relationship between UA and BMD. Lin et al 60 reported that UA is not associated with BMD at different skeletal sites in elderly men, and the only positive association was found in normal weight groups, implying that BMI has an impact on this relationship. Another study of 328 postmenopausal women found no significant relationship between UA and BMD.…”

Section: Discussionmentioning

confidence: 97%

Comparison between linear regression and four different machine learning methods in selecting risk factors for osteoporosis in a Chinese female aged cohort

Tzou,

Peng,

Huang

et al. 2023

Journal of the Chinese Medical Association

View full text Add to dashboard Cite

Background: Population aging is emerging as an increasingly acute challenge for countries around the world. One particular manifestation of this phenomenon is the impact of osteoporosis on individuals and national health systems. Previous studies of risk factors for osteoporosis were conducted using traditional statistical methods, but more recent efforts have turned to machine learning approaches. Most such efforts, however, treat the target variable (bone mineral density or fracture rate) as a categorical one which provides no quantitative information. The present study uses five different machine learning methods to analyze the risk factors for T-score of bone mineral density, seeking to: (1) Compare the prediction accuracy between different machine learning methods and traditional multiple linear regression and (2) rank the importance of 25 different risk factors. Methods: The study sample includes 24,412 women aged > 55 y/o with 25 related variables, applying traditional multiple linear regression (MLR) and five different machine learning methods: classification and regression tree (CART), Naïve Bayes (NB), Random Forest (RF), stochastic gradient boosting (SGB), and eXtreme Gradient Boosting (XGBoost). The metrics used for model performance comparisons are the symmetric mean absolute percentage error, and relative absolute error, root relative squared error and root mean squared error. Results: Machine learning approaches outperformed MLR for all four prediction errors. The average importance ranking of each factor generated by the machine learning methods indicate that age is the most important factor determining T-score, followed by eGFR, BMI, UA, and education level. Conclusion: In a group of women aged > 55 years, we demonstrated that machine learning methods provide superior performance in estimating T-Score, with age being the most important impact factor, followed by eGFR, BMI, UA, and education level.

show abstract

Section: Discussionmentioning

confidence: 97%

Comparison between linear regression and four different machine learning methods in selecting risk factors for osteoporosis in a Chinese female aged cohort

Tzou,

Peng,

Huang

et al. 2023

Journal of the Chinese Medical Association

View full text Add to dashboard Cite

show abstract

Association of serum uric acid levels with bone mineral density and the presence of osteoporosis in Chinese patients with Parkinson’s disease: a cross-sectional study

et al. 2023

J Bone Miner Metab

View full text Add to dashboard Cite

Association between serum uric acid level and bone mineral density at multiple skeletal sites in middle-aged and elderly men: a cross-sectional study of a healthy population in Taiwan

Cited by 2 publications

References 36 publications

Comparison between linear regression and four different machine learning methods in selecting risk factors for osteoporosis in a Chinese female aged cohort

Comparison between linear regression and four different machine learning methods in selecting risk factors for osteoporosis in a Chinese female aged cohort

Association of serum uric acid levels with bone mineral density and the presence of osteoporosis in Chinese patients with Parkinson’s disease: a cross-sectional study

Contact Info

Product

Resources

About