Journal of Diagnostics Concepts & Practice ›› 2026, Vol. 25 ›› Issue (04): 467-475.doi: 10.16150/j.1671-2870.2026.04.010
• Original articles • Previous Articles Next Articles
MA Shanyuan1,2, PENG Liang2, HOU Yanqiang2, LIU Weiwei1,3(
)
Received:2026-03-06
Revised:2026-05-26
Accepted:2026-05-27
Online:2026-08-25
Published:2026-08-31
Contact:
LIU Weiwei
E-mail:huashanvivian@126.com
CLC Number:
MA Shanyuan, PENG Liang, HOU Yanqiang, LIU Weiwei. Research on construction of osteoporotic fracture prediction models based on machine learning algorithms[J]. Journal of Diagnostics Concepts & Practice, 2026, 25(04): 467-475.
Table 1
Overview of included case data
| Variables | n | Missing[n(%)] | |
|---|---|---|---|
| PTH (pg/mL) | 333 | 50.915±25.093 | 0(0) |
| N-MID-OT (ng/mL) | 333 | 13.070±9.556 | 0(0) |
| ALP (U/L) | 333 | 84.207±29.837 | 0(0) |
| ALB (g/L) | 333 | 43.507±4.297 | 0(0) |
| Ca (mmol/L) | 332 | 2.310±0.127 | 1(0.3%) |
| MCH (pg) | 291 | 30.461 5±2.000 | 42(12.6%) |
| MCHC (g/L) | 291 | 329.777±10.518 | 42(12.6%) |
| Hb (g/L) | 291 | 128.533±15.148 | 42(12.6%) |
| P (mmol/L) | 329 | 1.097±0.180 | 4(1.2%) |
Table 2
Descriptive statistics of baseline patient demographics and biochemical indicators
| Characteristics | Osteoporosis(n=187) | Osteoporotic fractures(n=146) | χ2/Z/t | P |
|---|---|---|---|---|
| Sex | χ2=69.366 | <0.001 | ||
| Male [n(%)] | 7(10.6) | 59(89.4) | ||
| Female [n(%)] | 180(67.4) | 87(32.6) | ||
| Age(years) | 69.000(62.000,75.000) | 68.000(59.000,76.000) | Z=-1.632 | 0.103 |
| Parathyroid hormone(pg/mL) | 38.500(28.800,49.200) | 57.125(45.318,74.548) | Z=-8.230 | <0.001 |
| N-MID-OT(ng/mL) | 7.300(5.200,10.900) | 17.285(11.585,25.163) | Z=-10.855 | <0.001 |
| ALP(U/L) | 77.440(56.870,96.190) | 88.240(70.695,102.470) | Z=-4.213 | <0.001 |
| ALB(g/L) | 45.100(43.340,47.190) | 42.395(38.665,44.910) | Z=-7.852 | <0.001 |
| Ca(mmol/L) | 2.361±0.105 | 2.245±0.124 | t=9.247 | <0.001 |
| MCH(pg) | 30.400(29.300,31.200) | 30.800(29.700,31.700) | Z=-2.630 | 0.009 |
| MCHC(g/L) | 327.652±10.198 | 332.654±10.456 | t=-4.392 | <0.001 |
| Hb(g/L) | 131.000(123.340,139.000) | 128.000(118.000,138.250) | Z=-1.758 | 0.079 |
| P(mmol/L) | 1.145±0.142 | 1.036±0.202 | t=5.539 | 0.000 |
Table 4
Univariate Logistic regression analysis between the two groups
| Variables | B | P value | OR | 95% OR | |
|---|---|---|---|---|---|
| Lower | Upper | ||||
| Sex | 2.859 | <0.001 | 17.438 | 7.648 | 39.763 |
| PTH | 0.044 | <0.001 | 1.045 | 1.032 | 1.059 |
| N-MID-OT | 0.199 | <0.001 | 1.220 | 1.165 | 1.278 |
| ALP | 0.014 | 0.001 | 1.014 | 1.005 | 1.022 |
| ALB | -0.295 | <0.001 | 0.745 | 0.686 | 0.808 |
| Ca | -9.792 | <0.001 | 5.00E-05 | 0.000 | 0.001 |
| MCH | 0.177 | <0.001 | 1.194 | 1.055 | 1.351 |
| MCHC | 0.048 | <0.001 | 1.049 | 1.026 | 1.073 |
| Hb | -0.016 | 0.034 | 0.984 | 0.969 | 0.999 |
| Phosphorus | -3.790 | 0.000 | 0.023 | 0.005 | 0.093 |
Table 5
Performance of various models on the test set
| Model | Accuracy | Sensitivity | Specificity | PPV | NPV | F1 | AUC |
|---|---|---|---|---|---|---|---|
| LR | 0.919 | 0.884 | 0.946 | 0.927 | 0.914 | 0.905 | 0.963(0.926,0.999) |
| DT | 0.828 | 0.744 | 0.893 | 0.842 | 0.82 | 0.79 | 0.891(0.824,0.958) |
| RF | 0.879 | 0.884 | 0.875 | 0.844 | 0.907 | 0.864 | 0.964(0.933,0.996) |
| SVM | 0.909 | 0.907 | 0.911 | 0.886 | 0.927 | 0.897 | 0.958(0.920,0.995) |
| XGBoost | 0.899 | 0.907 | 0.893 | 0.867 | 0.926 | 0.886 | 0.974(0.950,0.998) |
| [1] | 中华人民共和国国家卫生健康委员会. 一图读懂:中国骨质疏松症流行病学调查结果[EB/OL]. (2018-10-20)[2026-06-30]. https://www.nhc.gov.cn/wjw/zcjd/201810/1aee4c12bec7415cbebfe7eacbc09552.shtml. |
| [2] |
Wang L, Yu W, Yin X, et al. Prevalence of osteoporosis and fracture in China: The China osteoporosis prevalence study[J]. JAMA Netw Open, 2021, 4(8):e2121106.
doi: 10.1001/jamanetworkopen.2021.21106 URL |
| [3] |
Kanis J A, Johnell O, Oden A, et al. FRAX™ and the assessment of fracture probability in men and women from the UK[J]. Osteoporos Int, 2008, 19(4):385-397.
doi: 10.1007/s00198-007-0543-5 pmid: 18292978 |
| [4] |
Kanis J A, Harvey N C, Cooper C, et al. A systematic review of intervention thresholds based on FRAX: A report prepared for the National Osteoporosis Guideline Group and the International Osteoporosis Foundation[J]. Arch Osteoporos, 2016, 11:25.
doi: 10.1007/s11657-016-0278-z pmid: 27465509 |
| [5] |
Kanis J A, Cooper C, Rizzoli R, et al. European guidance for the diagnosis and management of osteoporosis in postmenopausal women[J]. Osteoporos Int, 2019, 30(1):3-44.
doi: 10.1007/s00198-018-4704-5 pmid: 30324412 |
| [6] |
Schini M, Vilaca T, Gossiel F, et al. Bone turnover mar-kers: Basic biology to clinical applications[J]. Endocr Rev, 2023, 44(3):417-473.
doi: 10.1210/endrev/bnac031 URL |
| [7] |
Tian A, Ma J, Feng K, et al. Reference markers of bone turnover for prediction of fracture: A meta-analysis[J]. J Orthop Surg Res, 2019, 14(1):68.
doi: 10.1186/s13018-019-1100-6 pmid: 30819222 |
| [8] |
Greener J G, Kandathil S M, Moffat L, et al. A guide to machine learning for biologists[J]. Nat Rev Mol Cell Biol, 2022, 23(1):40-55.
doi: 10.1038/s41580-021-00407-0 |
| [9] | 倪康康, 董单, 李国庆, 等. 儿童及青少年骨质疏松症研究进展[J]. 中华内分泌代谢杂志, 2025, 41(5):430-434. |
| Ni Kangkang, Dong Dan, Li Guoqing, et al. Recent advances in osteoporosis in children and adolescents[J]. Chin J Endocrinol Metab, 2025, 41(5):430-434. | |
| [10] |
Siris E S, Adler R, Bilezikian J, et al. The clinical diagnosis of osteoporosis: A position statement from the National Bone Health Alliance Working Group[J]. Osteoporos Int, 2014, 25(5):1439-1443.
doi: 10.1007/s00198-014-2655-z pmid: 24577348 |
| [11] |
Wu Y, Chao J, Bao M, et al. Predictive value of machine learning on fracture risk in osteoporosis: A systematic review and meta-analysis[J]. BMJ Open, 2023, 13(12):e071430.
doi: 10.1136/bmjopen-2022-071430 URL |
| [12] |
Zhang D, Yang X, Wang F, et al. Comparative analysis of feature extraction methods and machine learning models for predicting osteoporosis prevalence[J]. J Med Syst, 2025, 49(1):72.
doi: 10.1007/s10916-025-02203-1 |
| [13] | 陈虹谷, 赵国阳, 马安培, 等. 健康中老年人群血清骨转换标志物与FRAX骨折风险相关性分析[J]. 中国骨质疏松杂志, 2024, 30(2):204-209. |
| Chen Honggu, Zhao Guoyang, Ma Anpei, et al. Analysis of correlation between serum bone turnover markers and FRAX in healthy middle-aged and elderly population[J]. Chin J Osteoporos, 2024, 30(2):204-209. | |
| [14] |
Komaba H, Imaizumi T, Hamano T, et al. Lower parathyroid hormone levels are associated with reduced fracture risk in Japanese patients on hemodialysis[J]. Kidney Int Rep, 2024, 9(10):2956-2969.
doi: 10.1016/j.ekir.2024.07.008 pmid: 39430172 |
| [15] |
Ying P, Gu M, Jiang X, et al. Serum calcium-phosphorus product for predicting the risk of osteoporotic vertebral compression fractures in elderly patients: A retrospective observational study[J]. J Orthop Surg Res, 2022, 17(1):57.
doi: 10.1186/s13018-022-02953-5 pmid: 35093148 |
| [16] | Deng A F, Wang F X, Wang S C, et al. Bone-organ axes: Bidirectional crosstalk[J]. Mil Med Res, 2024, 11(1):37. |
| [17] | 刘玉洁, 孙世威, 孟霞. 中老年骨质疏松性骨折危险因素及预测模型[J]. 中国骨质疏松杂志, 2026, 32(2):171-175. |
| Liu Yujie, Sun Shiwei, Meng Xia. Risk factors and a predictive model for osteoporotic fracture in the middle age and elderly patients[J]. Chin J Osteoporos, 2026, 32(2):171-175. | |
| [18] |
Qi X, Wang S, Fang C, et al. Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants[J]. Redox Biol, 2025, 79:103470.
doi: 10.1016/j.redox.2024.103470 URL |
| [19] |
Liang D, Wang L, Zhong P, et al. Perspective: Global burden of iodine deficiency: Insights and projections to 2050 using XGBoost and SHAP[J]. Adv Nutr, 2025, 16(3):100384.
doi: 10.1016/j.advnut.2025.100384 URL |
| [20] | 中华医学会骨质疏松和骨矿盐疾病分会. 骨转换生化标志物临床应用指南[J]. 中华骨质疏松和骨矿盐疾病杂志, 2021, 14(4):321-336. |
| China Society of Osteoporosis and Bone Mineral Research, China Medical Association. Guidelines for clinical application of bone turnover biomarkers[J]. Chin J Osteoporos Bone Miner Res, 2021, 14(4):321-336. | |
| [21] | 肖文金, 刘彩蕊, 朱柯雨, 等. 肥胖、2型糖尿病与骨折风险的关联及健康管理:大数据研究提示新观点[J]. 中华内分泌代谢杂志, 2025, 41(10):818-822. |
| Xiao Wenjin, Liu Cairui, Zhu Keyu, et al. Obesity, type 2 diabetes and fracture risk: New insights from large-scale data studies[J]. Chin J Endocrinol Metab, 2025, 41(10):818-822. | |
| [22] | 任春蕊, 刘建凤, 安向莲, 等. 体重指数与骨质疏松症之间的因果关系:一项孟德尔随机化研究[J]. 中华内分泌代谢杂志, 2024, 40(2):108-114. |
| Ren Chunrui, Liu Jianfeng, An Xianglian, et al. Causal relationship between body mass index and osteoporosis: A Mendelian randomization study[J]. Chin J Endocrinol Metab, 2024, 40(2):108-114. |
| [1] | YU Jin, WANG Jie, WANG Hujun, WANG Congxiao, LI Yingqi, FANG Boyan, WANG Yingpeng. Study on the recognition of early-stage Parkinson’s disease patients using functional near-infrared spectroscopy signals based on machine learning [J]. Journal of Diagnostics Concepts & Practice, 2024, 23(05): 484-493. |
| [2] | DING Jingfeng, AO Weiqun, ZHU Zhen, SUN Jing, XU Lianggen, ZHENG Shibao, YU Jingjing, HU Jinwen. The value of radiomics based on T2WI and DWI of MRI in preoperative prediction of extramural vascular invasion in rectal cancer [J]. Journal of Diagnostics Concepts & Practice, 2024, 23(01): 46-56. |
| [3] | QIAN Danye, MENG Xiangjun, ZHU Liming. Value of Kyoto gastritis score and modified prediction model in diagnosing Helicobacter pylori infection status under gastroscopy in Chinese population [J]. Journal of Diagnostics Concepts & Practice, 2023, 22(06): 555-561. |
| [4] | HE Xin, CHEN Hui, FENG Weiwei. Research progress on the application of machine learning in assisted ultrasound diagnosis of adnexal masses [J]. Journal of Diagnostics Concepts & Practice, 2022, 21(04): 541-546. |
| [5] | Chinese Society of Endocrinology,Chinese Medical Association , et al . Expert suggestion for osteoporosis management during the recent COVID-19 pandemic [J]. Journal of Diagnostics Concepts & Practice, 2022, 21(02): 133-135. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||