骨质疏松风险预测机器学习模型构建与研究

廉宏宇; 沈翔; 陈广新; 国威; 孙悦

您当前的位置：

首页 >

文章列表页 >

骨质疏松风险预测机器学习模型构建与研究

更新时间：2024-06-19

- 骨质疏松风险预测机器学习模型构建与研究
- Construction and research of machine learning model for predicting osteoporosis risk
- 新一代信息技术 2024年页码：1-7
- 作者机构：
  
  1.牡丹江医学院附属红旗医院，黑龙江牡丹江，157011
  2.牡丹江医学院第一临床医学院，黑龙江牡丹江，157011
  3.牡丹江医学院医学影像学院，黑龙江牡丹江，157011
  4.牡丹江医学院生命科学学院，黑龙江牡丹江，157011
- 作者简介：
  
  廉宏宇，男，1982.12-，主治医师，研究生学历，研究方向：临床数据挖掘
  沈翔，男，1996.3-，研究生在读，研究方向：临床医学
  陈广新，男， 1978.3-，讲师，研究方向：临床大数据挖掘
  国威，男，1996.12-，研究生在读，研究方向：临床预测模型。
  ▲孙悦，女，1993.12-，初级职称，研究方向：医学人工智能。E-mail：44642581.com
- 基金信息：
  
  2022年度黑龙江省省属高等学校基本科研业务费科研项目(2022-KYYWF-0695)
- DOI：
  中图分类号： TP181;R743.3
- 网络出版日期：2024-06-19，
扫描看全文
廉宏宇,沈翔,陈广新等.骨质疏松风险预测机器学习模型构建与研究[J].新一代信息技术,

Lian Hongyu,Shen Xiang,Chen Guangxin,et al.Construction and research of machine learning model for predicting osteoporosis risk[J].New Generation of Information Technology,
廉宏宇,沈翔,陈广新等.骨质疏松风险预测机器学习模型构建与研究[J].新一代信息技术, DOI：10.3969/j.issn.2096-6091.XXXX.XX.001.

Lian Hongyu,Shen Xiang,Chen Guangxin,et al.Construction and research of machine learning model for predicting osteoporosis risk[J].New Generation of Information Technology, DOI：10.3969/j.issn.2096-6091.XXXX.XX.001.

摘要

目的

本研究旨在通过比较多种机器学习算法对骨质疏松症的预测性能，筛选出最优算法并识别关键风险因素，为骨质疏松症的精准预防和治疗提供支持。

方法

本研究采用了包括决策树、AdaBoost在内的多种机器学习算法构建骨质疏松症预测模型，并评估了各模型的性能，同时分析了模型对特征重要性的评估。

结果

XGBoost模型在所有评估指标中表现最优，包括最高的AUC、准确度、精确度和F1得分。决策树和AdaBoost模型也显示出良好的性能。我们发现年龄是一个重要特征，部分模型倾向于重视这一特征，而忽略其他特征。实验数据集和构建模型的算法有待进一步扩充和优化。

结论

在骨质疏松症预测模型性能和风险因素识别方面，集成学习算法表现优异，显示出在骨质疏松症预测中的巨大潜力。

Abstract

Objective

By comparing the predictive performance of various machine learning algorithms for osteoporosis

this study aims to screen out the optimal algorithm and identify key risk factors

so as to provide support for the precise prevention and treatment of osteoporosis.

Methods

In this study

a variety of machine learning algorithms including decision tree and AdaBoost were used to construct osteoporosis prediction models

and the performance of each model was evaluated

and the evaluation of the importance of features was analyzed.

Results

The XGBoost model performed best in all evaluation metrics

including the highest AUC

accuracy

precision and F1 scores. Decision tree and AdaBoost model also show good performance. We found that age is an important feature

and some models tend to value this feature and ignore other features. The experimental data set and the model building algorithm need to be further expanded and optimized.

Conclusion

Ensemble learning algorithm has excellent performance in predicting osteoporosis model performance and risk factor identification

which shows great potential in predicting osteoporosis.

关键词

骨质疏松机器学习集成学习特征重要性分析

Keywords

OsteoporosisMachine learningIntegrated learningFeature importance analysis

references

KELSEY J L. Risk factors for osteoporosis and associated fractures[J]. Public Health Reports, 1989, 104(Suppl): 14.

CLYNES M A, HARVEY N C,et al. The epidemiology of osteoporosis[J]. British medical bulletin, 2020, 133(1): 105-117.

EBELING P R, NGUYEN H H, et al. Secondary osteoporosis[J]. Endocrine Reviews, 2022, 43(2): 240-313.

WU X, PARK S. A prediction model for osteoporosis risk using a machine-learning approach and its validation in a large cohort[J]. Journal of Korean Medical Science, 2023, 38(21).

YAMAMOTO N, SUKEGAWA S, et al. Deep learning for osteoporosis classification using hip radiographs and patient clinical covariates[J]. Biomolecules, 2020, 10(11): 1534.

LIM H K, HA H I, et al. Prediction of femoral osteoporosis using machine-learning analysis with radiomics features and abdomen-pelvic CT: A retrospective single center preliminary study[J]. PloS one, 2021, 16(3): e0247330.

KIM S K, YOO T K, Osteoporosis risk prediction using machine learning and conventional methods[C]//2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2013: 188-191.

ZHOU Z H, WU J, TANG W. Ensembling neural networks: many could be better than all[J]. Artificial intelligence, 2002, 137(1-2): 239-263.

MAHESH B. Machine learning algorithms-a review[J]. International Journal of Science and Research (IJSR).[Internet], 2020, 9(1): 381-386.

CARLEO G, CIRAC I, et al. Machine learning and the physical sciences[J]. Reviews of Modern Physics, 2019, 91(4): 045002.

BADILLO S, BANFAI B, et al. An introduction to machine learning[J]. Clinical pharmacology & therapeutics, 2020, 107(4): 871-885.

LI W, WANG C, et al. International conference on machine learning[J]. Transactions on machine learning research, 2023.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

预测COVID-19感染风险的医疗决策机器学习方法研究

基于可解释性机器学习的新冠肺炎疾病风险预测研究

基于血流动力学与形态学特征融合的动脉瘤破裂风险机器学习预测研究

基于人工智能的无人机自组网路由算法研究进展