Application of artificial intelligence in diagnosis of osteoporosis using medical images: a systematic review and meta-analysis

被引：19
作者：
Gao, L. [1 ,2 ]
Jiao, T. [1 ]
Feng, Q. [1 ]
Wang, W. [1 ]
机构：
[1] Beijing Univ Chinese Med, Beijing 100029, Peoples R China
[2] Univ Toronto, St Michaels Hosp, Li Ka Shing Knowledge Inst, Appl Hlth Res Ctr AHRC, Toronto, ON M5B 1W8, Canada
来源：
OSTEOPOROSIS INTERNATIONAL | 2021年 / 32卷 / 07期
基金：
中国博士后科学基金;
关键词：
Artificial intelligence; Diagnosis; Meta-analysis; Osteoporosis;
D O I：
10.1007/s00198-021-05887-6
中图分类号：
R5 [内科学];
学科分类号：
1002 ; 100201 ;
摘要：
Artificial intelligence (AI) is a potentially reliable assistant in the diagnosis of osteoporosis. This meta-analysis aims to assess the diagnostic accuracy of the AI-based systems using medical images. We searched PubMed and Web of Science from inception to June 15, 2020, for eligible articles that applied AI approaches to diagnosing osteoporosis using medical images. Quality and bias of the included studies were evaluated with the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. The main outcome was the sensitivity and specificity of the performance of the AI-based systems. The data analysis utilized the R Foundation packages of "meta" for univariate analysis and Stata for bivariate analysis. Random effects model was utilized. Seven studies with 3186 patients were included in the meta-analysis. The overall risk of bias of the included studies was assessed as low. The pooled sensitivity was 0.96 (95% CI 0.93-1.00), and the pooled specificity was 0.95 (95% CI 0.91-0.99). However, high heterogeneity was found in this meta-analysis. The results supported that the AI-based systems had good accuracy in diagnosing osteoporosis. However, the high risk of bias in patient selection and high heterogeneity in the meta-analysis made the conclusion less convincing. The application of AI-based systems in osteoporosis diagnosis needs to be further confirmed by more prospective studies in multi-centers including more random samples from complete patient types.
引用
收藏
页码：1279 / 1286
页数：8
相关论文
共 23 条
[11]   Preferred Reporting Items for a Systematic Review and Meta-analysis of Diagnostic Test Accuracy Studies The PRISMA-DTA Statement [J].
McInnes, Matthew D. F. ;
Moher, David ;
Thombs, Brett D. ;
McGrath, Trevor A. ;
Bossuyt, Patrick M. .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2018, 319 (04) :388-396
[12]   Artificial Intelligence to Detect Papilledema from Ocular Fundus Photographs [J].
Milea, D. ;
Najjar, R. P. ;
Zhubo, J. ;
Ting, D. ;
Vasseneix, C. ;
Xu, X. ;
Fard, M. Aghsaei ;
Fonseca, P. ;
Vanikieti, K. ;
Lagreze, W. A. ;
La Morgia, C. ;
Cheung, C. Y. ;
Hamann, S. ;
Chiquet, C. ;
Sanda, N. ;
Yang, H. ;
Mejico, L. J. ;
Rougier, M-B ;
Kho, R. ;
Thi Ha Chau, T. ;
Singhal, S. ;
Gohier, P. ;
Clermont-Vignal, C. ;
Cheng, C-Y ;
Jonas, J. B. ;
Yu-Wai-Man, P. ;
Fraser, C. L. ;
Chen, J. J. ;
Ambika, S. ;
Miller, N. R. ;
Liu, Y. ;
Newman, N. J. ;
Wong, T. Y. ;
Biousse, V .
NEW ENGLAND JOURNAL OF MEDICINE, 2020, 382 (18) :1687-1695
[13]   Machine Learning Model to Predict Osteoporotic Spine with Hounsfield Units on Lumbar Computed Tomography [J].
Nam, Kyoung Hyup ;
Seo, Il ;
Kim, Dong Hwan ;
Lee, Jae It ;
Choi, Byung Kwan ;
Han, In Ho .
JOURNAL OF KOREAN NEUROSURGICAL SOCIETY, 2019, 62 (04) :442-449
[14]   Diagnosis of urinary tract infection based on artificial intelligence methods [J].
Ozkan, Ilker Ali ;
Koklu, Murat ;
Sert, Ibrahim Unal .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2018, 166 :51-59
[15]   Automatic opportunistic osteoporosis screening using low-dose chest computed tomography scans obtained for lung cancer screening [J].
Pan, Yaling ;
Shi, Dejun ;
Wang, Hanqi ;
Chen, Tongtong ;
Cui, Deqi ;
Cheng, Xiaoguang ;
Lu, Yong .
EUROPEAN RADIOLOGY, 2020, 30 (07) :4107-4116
[16]   Artificial Intelligence in Diabetic Retinopathy: Insights from a Meta-Analysis of Deep Learning [J].
Poly, Tahmina Nasrin ;
Islam, Md Mohaimenul ;
Yang, Hsuan Chia ;
Nguyen, Phung-Anh ;
Wu, Chieh Chen ;
Li, Yu-Chuan .
MEDINFO 2019: HEALTH AND WELLBEING E-NETWORKS FOR ALL, 2019, 264 :1556-1557
[17]   Artificial intelligence methods for the diagnosis of breast cancer by image processing: a review [J].
Sadoughi, Farahnaz ;
Kazemy, Zahra ;
Hamedan, Farahnaz ;
Owji, Leila ;
Rahmanikatigari, Meysam ;
Azadboni, Tahere Talebi .
BREAST CANCER-TARGETS AND THERAPY, 2018, 10 :219-230
[18]   Artificial intelligence in endoscopy [J].
Sharma, Prateek ;
Pante, Anjali ;
Gross, Seth A. .
GASTROINTESTINAL ENDOSCOPY, 2020, 91 (04) :925-931
[19]   Diagnostic test accuracy:application and practice using R software [J].
Shim, Sung Ryul ;
Kim, Seong-Jang ;
Lee, Jonghoo .
EPIDEMIOLOGY AND HEALTH, 2019, 41
[20]   Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study [J].
Wang, Pu ;
Berzin, Tyler M. ;
Brown, Jeremy Romek Glissen ;
Bharadwaj, Shishira ;
Becq, Aymeric ;
Xiao, Xun ;
Liu, Peixi ;
Li, Liangping ;
Song, Yan ;
Zhang, Di ;
Li, Yi ;
Xu, Guangre ;
Tu, Mengtian ;
Liu, Xiaogang .
GUT, 2019, 68 (10) :1813-1819
123