Korean Journal of Family Medicine

"Young-Sang Kim"

Original Articles

Application of Machine Learning Algorithms to Predict Osteoporotic Fractures in Women: Su Jeong Kang, Moon Jong Kim, Yang-Im Hur, Ji-Hee Haam, Young-Sang Kim; Korean J Fam Med 2024;45(3):144-148. Published online January 29, 2024; DOI: https://doi.org/10.4082/kjfm.23.0186

Abstract
PDF

Background
Predicting the risk of osteoporotic fractures is vital for prevention. Traditional methods such as the Fracture Risk Assessment Tool (FRAX) model use clinical factors. This study examined the predictive power of the FRAX score and machine-learning algorithms trained on FRAX parameters.
Methods
We analyzed the data of 2,147 female participants from the Ansan cohort study. The FRAX parameters employed in this study included age, sex (female), height and weight, current smoking status, excessive alcohol consumption (>3 units/d of alcohol), and diagnosis of rheumatoid arthritis. Osteoporotic fracture was defined as one or more fractures of the hip, spine, or wrist during a 10-year observation period. Machine-learning algorithms, such as gradient boosting, random forest, decision tree, and logistic regression, were employed to predict osteoporotic fractures with a 70:30 training-to-test set ratio. We evaluated the area under the receiver operating characteristic curve (AUROC) scores to assess and compare the performance of these algorithms with the FRAX score.
Results
Of the 2,147 participants, 3.5% experienced osteoporotic fractures. Those with fractures were older, shorter in height, and had a higher prevalence of rheumatoid arthritis, as well as higher FRAX scores. The AUROC for the FRAX was 0.617. The machine-learning algorithms showed AUROC values of 0.662, 0.652, 0.648, and 0.637 for gradient boosting, logistic regression, decision tree, and random forest, respectively.
Conclusion
This study highlighted the immense potential of machine-learning algorithms to improve osteoporotic fracture risk prediction in women when complete FRAX parameter information is unavailable.

Citations

Citations to this article as recorded by

Clinical Applicability of Machine Learning in Family Medicine
Jungun Lee
Korean Journal of Family Medicine.2024; 45(3): 123. CrossRef
Integrating Machine Learning for Personalized Fracture Risk Assessment: A Multimodal Approach
Sheikh Mohd Saleem, Shah Sumaya Jan
Korean Journal of Family Medicine.2024; 45(6): 356. CrossRef

2,931 View
74 Download
2 Web of Science
2 Crossref

Sex Difference in the Association between Serum Homocysteine Level and Non-Alcoholic Fatty Liver Disease: Bo-Youn Won, Kyung-Chae Park, Soo-Hyun Lee, Sung-Hwan Yun, Moon-Jong Kim, Kye-Seon Park, Young-Sang Kim, Ji-Hee Haam, Hyung-Yuk Kim, Hye-Jung Kim, Ki-Hyun Park; Korean J Fam Med 2016;37(4):242-247. Published online July 21, 2016; DOI: https://doi.org/10.4082/kjfm.2016.37.4.242

Abstract
PDF

Background

The relationship between serum homocysteine levels and non-alcoholic fatty liver disease is poorly understood. This study aims to investigate the sex-specific relationship between serum homocysteine level and non-alcoholic fatty liver disease in the Korean population.

Methods

This cross-sectional study included 150 men and 132 women who participated in medical examination programs in Korea from January 2014 to December 2014. Patients were screened for fatty liver by abdominal ultrasound and patient blood samples were collected to measure homocysteine levels. Patients that consumed more than 20 grams of alcohol per day were excluded from this study.

Results

The homocysteine level (11.56 vs. 8.05 nmol/L) and the proportion of non-alcoholic fatty liver disease (60.7% vs. 19.7%) were significantly higher in men than in women. In men, elevated serum homocysteine levels were associated with a greater prevalence of non-alcoholic fatty liver disease (quartile 1, 43.6%; quartile 4, 80.6%; P=0.01); however, in females, there was no significant association between serum homocysteine levels and the prevalence of non-alcoholic fatty liver disease. In the logistic regression model adjusted for age and potential confounding parameters, the odds ratio for men was significantly higher in the uppermost quartile (model 3, quartile 4: odds ratio, 6.78; 95% confidential interval, 1.67 to 27.56); however, serum homocysteine levels in women were not associated with non-alcoholic fatty liver disease in the crude model or in models adjusted for confounders.

Conclusion

Serum homocysteine levels were associated with the prevalence of non-alcoholic fatty liver disease in men.

Citations

Citations to this article as recorded by

Homocysteine, folate, and nonalcoholic fatty liver disease: a systematic review with meta-analysis and Mendelian randomization investigation
Shuai Yuan, Jie Chen, Lintao Dan, Ying Xie, Yuhao Sun, Xue Li, Susanna C Larsson
The American Journal of Clinical Nutrition.2022; 116(6): 1595. CrossRef
Genetic Association of Plasma Homocysteine Levels with Gastric Cancer Risk: A Two-Sample Mendelian Randomization Study
Tianpei Wang, Chuanli Ren, Jing Ni, Hui Ding, Qi Qi, Caiwang Yan, Bin Deng, Juncheng Dai, Gang Li, Yanbing Ding, Guangfu Jin
Cancer Epidemiology, Biomarkers & Prevention.2020; 29(2): 487. CrossRef
Characterization of Early-Stage Alcoholic Liver Disease with Hyperhomocysteinemia and Gut Dysfunction and Associated Immune Response in Alcohol Use Disorder Patients
Vatsalya Vatsalya, Khushboo S. Gala, Ammar Z. Hassan, Jane Frimodig, Maiying Kong, Nachiketa Sinha, Melanie L. Schwandt
Biomedicines.2020; 9(1): 7. CrossRef
Sex differences in risk factors for stroke in patients with hypertension and hyperhomocysteinemia
Hui Pang, Qiang Fu, Qiumei Cao, Lin Hao, Zhenkun Zong
Scientific Reports.2019;[Epub] CrossRef
Association between homocysteine and non-alcoholic fatty liver disease in Chinese adults: a cross-sectional study
Haijiang Dai, Weijun Wang, Xiaohong Tang, Ruifang Chen, Zhiheng Chen, Yao Lu, Hong Yuan
Nutrition Journal.2016;[Epub] CrossRef