人工智能辅助诊断骨质疏松性椎体压缩骨折的效能分析

doi:10.3969/j.issn.1006-7795.2025.05.003

首都医科大学学报 ›› 2025, Vol. 46 ›› Issue (5): 777-783.doi: 10.3969/j.issn.1006-7795.2025.05.003

• 智慧骨科及手术机器人临床应用 • 上一篇下一篇

人工智能辅助诊断骨质疏松性椎体压缩骨折的效能分析

王永杰,崔利宾,袁鑫,路茜,陈学明,刘亮*

首都医科大学附属北京潞河医院骨中心，北京 101149

收稿日期:2025-07-07 修回日期:2025-08-02 出版日期:2025-10-21 发布日期:2025-10-22
通讯作者: 刘亮 E-mail:liuliang@medmail.com.cn
基金资助:
北京市通州区科技计划项目（KJ2023CX032）。

Efficacy analysis of artificial intelligence-assisted diagnosis for osteoporotic vertebral compression fracture

Wang Yongjie,Cui Libin,Yuan Xin, Lu Qian, Chen Xueming, Liu Liang^*

Department of Orthopedics, Beijing Luhe Hospital, Capital Medical University, Beijing 101149, China

Received:2025-07-07 Revised:2025-08-02 Online:2025-10-21 Published:2025-10-22
Supported by:
This study was supported by Tongzhou District Health Development Research Project (KJ2023CX032).

摘要/Abstract

摘要： 目的对比分析人工智能阅片与人工阅片在诊断骨质疏松性椎体压缩骨折中的效能。方法连续收集了2023年1月至2023年12月80例骨质疏松性椎体压缩骨折患者及20例无骨折但存在非特异性腰疼的患者的资料纳入了该项研究。根据患者的计算机断层扫描（computed tomography，CT）影像分别进行人工智能软件诊断和3名不同年资的脊柱外科临床医生（高级职称、中级职称、初级职称各1人）人工阅片诊断。比较不同检测方法的诊断效能。结果各组灵敏度、特异度、阳性预测值、阴性预测值、受试者工作特征（receiver operating characteristic，ROC）曲线下面积(area under the curve，AUC)、Kappa值分别为AI 阅片：0. 975、0. 900、0. 975、0. 900、0. 938、0. 875；高级职称：0. 950、0. 900、0. 974、0. 818、0. 925、0. 819；中级职称：0. 825、0. 850、0. 957、0. 548、0. 837、0. 560；初级职称：0. 750、0. 750、0. 923、0. 429、0. 751、0. 390。结论人工智能的诊断水平与高年资医生诊断水平相当，明显高于中级及初级临床医生的诊断水平。

关键词: 人工智能, 深度学习, 骨质疏松性椎体压缩骨折, 辅助诊断, 诊断效能, 金标准

Abstract: Objective To compare the efficacy of artificial intelligence (AI) diagnostic group and artificial reading group in the diagnosis for osteoporotic vertebral compression fractures. Methods From January 2023 to December 2023, 80 patients with osteoporotic vertebral compression fractures and 20 patients without fractures but with nonspecific low back pain were included in the study. According to the patient 's computed tomography(CT) image, the AI software diagnosis and physicians of different seniority (one senior physician, one intermediate physician and one junior physician) diagnosis were performed. The diagnostic efficacy of different detection methods was compared. Results The sensitivity, specificity, positive predictive value, negative predictive value and area under the receiver operating characteristic(ROC) curve ( AUC ) and Kappa value of each group were as follows: AI image interpretation: 0.975,0.900,0.975,0.900,0.938, 0.875; senior physician: 0.950, 0.900, 0.974, 0.818, 0.925, 0.819; intermediate physician: 0.825, 0.850, 0.957, 0.548， 0.837, 0.560; and junior physician: 0.750, 0.750, 0.923, 0.429, 0.751, 0.390. Conclusion The diagnostic performance of AI was comparable to that of senior physician, and significantly higher than that of intermediate and primary physicians.

Key words: artificial intelligence, deep learning, osteoporotic vertebral compression fracture, auxiliary diagnosis, diagnostic efficacy, gold standard

中图分类号:

R683.2

王永杰, 崔利宾, 袁鑫, 路茜, 陈学明, 刘亮. 人工智能辅助诊断骨质疏松性椎体压缩骨折的效能分析[J]. 首都医科大学学报, 2025, 46(5): 777-783.

Wang Yongjie, Cui Libin, Yuan Xin, Lu Qian, Chen Xueming, Liu Liang. Efficacy analysis of artificial intelligence-assisted diagnosis for osteoporotic vertebral compression fracture[J]. Journal of Capital Medical University, 2025, 46(5): 777-783.

参考文献

［1］ Cummings S R, Melton L J. Epidemiology and outcomes of osteoporotic fractures［J］. Lancet, 2002, 359(9319): 1761－1767.
［2］朱洁云, 高敏, 宋秋韵, 等. 中国老年人骨质疏松症患病率的Meta分析［J］. 中国全科医学, 2022, 25(3): 346-353.
［3］中国康复医学会骨质疏松预防与康复专业委员会. 骨质疏松性椎体压缩骨折诊治专家共识(2021版)［J］. 中华医学杂志, 2021, 101(41): 3371-3379.
［4］ Shah L M, Jennings J W, Kirsch C F E, et al. ACR appropriateness criteria management of vertebral compression fractures［J］. J Am Coll Radiol, 2018, 15(11S): S347-S364.
［5］ Piazzolla A, Solarino G, Lamartina C, et al. Vertebral bone marrow edema (VBME) in conservatively treated acute vertebral compression fractures (VCFs): evolution and clinical correlations［J］. Spine, 2015, 40(14): E842-E848.
［6］ Liao H F, Mesfin A, Luo J B. Joint vertebrae identification and localization in spinal CT images by combining short-and long-range contextual information［J］. IEEE Trans Med Imaging, 2018, 37(5): 1266-1275.
［7］ VandenBerg J, Cullison K, Fowler S A, et al. Blunt thoracolumbar-spine trauma evaluation in the emergency department: a meta-analysis of diagnostic accuracy for history, physical examination, and imaging［J］. J Emerg Med, 2019, 56(2): 153-165.
［8］ Hom J, Kaplan C, Fowler S, et al. Evidence-based diagnostic test accuracy of history, physical examination, and imaging for intussusception: a systematic review and meta-analysis［J］. Pediatr Emerg Care, 2022, 38(1): e225-e230.
［9］ Mao H Q, Zou J, Geng D C, et al. Osteoporotic vertebral fractures without compression: key factors of diagnosis and initial outcome of treatment with cement augmentation［J］. Neuroradiology, 2012, 54(10): 1137-1143.
［10］ Armato S G 3rd. Deep learning demonstrates potential for lung cancer detection in chest radiography［J］. Radiology, 2020, 297(3): 697－698.
［11］ Harmon S A, Sanford T H, Xu S, et al. Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets［J］. Nat Commun, 2020, 11(1): 4080.
［12］ Liu Y, Jain A, Eng C, et al. A deep learning system for differential diagnosis of skin diseases［J］. Nat Med, 2020, 26(6): 900-908.
［13］王煜宁,张颐. 人工智能在子宫内膜异位症诊断中的应用［J］. 中国医科大学学报, 2025, 54(5): 385-389+413.
［14］康林,刘喜,程浩,等. 人工智能在早期食管癌内镜诊断中的应用进展［J］. 空军军医大学学报, 2024, 45(4): 465-471.
［15］张舒婉,张文川,张喆,等. 人工智能在宫颈病变初步筛查中的应用［J］. 中国医科大学学报, 2023, 52(8): 694-698.
［16］钟宇,周姝,张立波,等. 人工智能肺结节筛查系统结合能谱CT比较不同性质肺结节的检测效能［J］. 中国医科大学学报, 2023, 52(7): 624-627+632.
［17］薛文欣,宋宏萍,常婉英,等. 人工智能在乳腺癌影像筛查领域的应用进展［J］. 空军军医大学学报, 2024, 45(8): 949-952.
［18］ Wang Y J, Su F, Lu Q, et al. Deep learning-driven diagnosis of multi-type vertebra diseases based on computed tomography images［J］. Quant Imaging Med Surg, 2024, 14(1): 800-813.
［19］印平, 马远征, 马迅, 等. 骨质疏松性椎体压缩性骨折的治疗指南［J］. 中国骨质疏松杂志, 2015, 21(6): 643－648.
［20］胡子昂, 范顺武.骨质疏松性椎体压缩骨折的诊治现状［J］.中国骨伤,2022,35(5):405-408.
［21］ Wong C C, McGirt M J. Vertebral compression fractures: a review of current management and multimodal therapy［J］. J Multidiscip Healthc, 2013, 6: 205-214.
［22］ Delmas P D, Van De Langerijt L, Watts N B, et al. Underdiagnosis of vertebral fractures is a worldwide problem: the IMPACT study［J］. J Bone Miner Res, 2005, 20(4): 557-563.
［23］ Malik A T, Retchin S, Phillips F M, et al. Declining trend in osteoporosis management and screening following vertebral compression fractures-a national analysis of commercial insurance and medicare advantage beneficiaries［J］. Spine J, 2020, 20: 538-546.［24］ Singh S, Patil S, Thein M, et al. A retrospective audit of osteoporosis management following fragility fractures in a hospital setting［J］. Cureus, 2024, 16(12): e76047.
［25］ Azevedo S F, Mazeda C, Silva S P, et al. Two-year mortality predictors in fragility fractures-a medical records review study［J］. J Clin Rheumatol, 2024, 30(6): 239-242.
［26］ Tan C W, Cameron M, Arlachov Y, et al. The Acute VertEbRal AugmentaTion (AVERT) study: protocol for a randomised controlled, feasibility trial of spinal medial branch nerve block in hospitalised older patients with vertebral fragility fractures［J］. BMJ Open, 2022, 12(6): e059194.
［27］ Tomita N, Cheung Y Y, Hassanpour S. Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans［J］. Comput Biol Med, 2018, 98: 8-15.
［28］ Kolanu N, Silverstone E J, Ho B H, et al. Clinical utility of computer-aided diagnosis of vertebral fractures from computed tomography images［J］. J Bone Miner Res, 2020, 35(12): 2307-2312.
［29］史丹迪, 张忠伟, 胡铁波, 等. 人工智能辅助放射科住院医师诊断肋骨新鲜骨折的应用价值［J］. 现代实用医学, 2022, 34(10): 1308-1310.
［30］韩康恩, 王洪伟, 顾洪闻, 等. 人工智能影像组学辅助X射线诊断腰椎骨质疏松性椎体压缩性骨折的效能［J］. 局解手术学杂志, 2024, 33(7): 579-583.

[1]	刘彦怡, 张岩岩, 李宏军. 影像组学联合多组学在肝细胞癌的研究进展[J]. 首都医科大学学报, 2025, 46(5): 934-939.
[2]	刘红蕾, 杨迎亮, 李荣浩, 朱丛敏, 张旭. 人工智能在肿瘤诊疗研究中的应用[J]. 首都医科大学学报, 2025, 46(3): 395-400.
[3]	王拥军, 刘涛, 刘子阳, 熊云云, 荆京, 谢雪微, 李子孝. 人工智能在脑血管病领域中的应用[J]. 首都医科大学学报, 2025, 46(2): 177-183.
[4]	张婉婉, 董晓, 于尔澜, 吉训明, 吴川杰. 人工智能在脑血管病诊疗中的应用[J]. 首都医科大学学报, 2025, 46(1): 6-10.
[5]	屈俊达, 杨敏福, 李春林, 孙立伟, 高赫, 张旭. 心外膜脂肪影像分割量化方法及其临床应用的研究进展[J]. 首都医科大学学报, 2025, 46(1): 99-105.
[6]	魏兴梅, 薛书锦, 高振橙, 李永新. 人工智能在人工耳蜗植入中的应用[J]. 首都医科大学学报, 2024, 45(6): 931-937.
[7]	裴友娟, 阮祥燕, 鞠蕊, 王月姣, 蒋玲玲, 马郡. 人工智能在生殖内分泌领域中的应用[J]. 首都医科大学学报, 2024, 45(4): 566-572.
[8]	张达谦, 张晓欣, 叶子晨, 谢芷兰, 杨继春, 江宇. 人工智能辅助诊断系统对急性白血病诊断价值 Meta 分析[J]. 首都医科大学学报, 2024, 45(4): 693-700.
[9]	赵金铭, 王向东, 张罗. 人工智能在耳鼻咽喉头颈外科的应用[J]. 首都医科大学学报, 2024, 45(2): 175-180.
[10]	罗艺, 秦齐, 王沛豪, 郭康顺, 张鑫平, 崔永. 人工智能结合光谱诊断技术在肺癌组织鉴别领域的应用与研究进展[J]. 首都医科大学学报, 2023, 44(6): 1095-1102.

人工智能辅助诊断骨质疏松性椎体压缩骨折的效能分析

Efficacy analysis of artificial intelligence-assisted diagnosis for osteoporotic vertebral compression fracture

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价