Guillermo Droppelmann, Constanza Rodríguez, Dali Smague, Carlos Jorquera, Felipe Feijoo
{"title":"用于腱鞘炎检测的深度学习模型:诊断测试的系统回顾和荟萃分析。","authors":"Guillermo Droppelmann, Constanza Rodríguez, Dali Smague, Carlos Jorquera, Felipe Feijoo","doi":"10.1530/EOR-24-0016","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Different deep-learning models have been employed to aid in the diagnosis of musculoskeletal pathologies. The diagnosis of tendon pathologies could particularly benefit from applying these technologies. The objective of this study is to assess the performance of deep learning models in diagnosing tendon pathologies using various imaging modalities.</p><p><strong>Methods: </strong>A meta-analysis was conducted, with searches performed on MEDLINE/PubMed, SCOPUS, Cochrane Library, Lilacs, and SciELO. The QUADAS-2 tool was employed to assess the quality of the studies. Diagnostic measures, such as sensitivity, specificity, diagnostic odds ratio, positive and negative likelihood ratios, area under the curve, and summary receiver operating characteristic, were included using a random-effects model. Heterogeneity and subgroup analyses were also conducted. All statistical analyses and plots were generated using the R software package. The PROSPERO ID is CRD42024506491.</p><p><strong>Results: </strong>Eleven deep-learning models from six articles were analyzed. In the random effects models, the sensitivity and specificity of the algorithms for detecting tendon conditions were 0.910 (95% CI: 0.865; 0.940) and 0.954 (0.909; 0.977). The PLR, NLR, lnDOR, and AUC estimates were found to be 37.075 (95%CI: 4.654; 69.496), 0.114 (95%CI: 0.056; 0.171), 5.160 (95% CI: 4.070; 6.250) with a (P < 0.001), and 96%, respectively.</p><p><strong>Conclusion: </strong>The deep-learning algorithms demonstrated a high level of accuracy level in detecting tendon anomalies. The overall robust performance suggests their potential application as a valuable complementary tool in diagnosing medical images.</p>","PeriodicalId":48598,"journal":{"name":"Efort Open Reviews","volume":"9 10","pages":"941-952"},"PeriodicalIF":4.3000,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11457807/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deep learning models for tendinopathy detection: a systematic review and meta-analysis of diagnostic tests.\",\"authors\":\"Guillermo Droppelmann, Constanza Rodríguez, Dali Smague, Carlos Jorquera, Felipe Feijoo\",\"doi\":\"10.1530/EOR-24-0016\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>Different deep-learning models have been employed to aid in the diagnosis of musculoskeletal pathologies. The diagnosis of tendon pathologies could particularly benefit from applying these technologies. The objective of this study is to assess the performance of deep learning models in diagnosing tendon pathologies using various imaging modalities.</p><p><strong>Methods: </strong>A meta-analysis was conducted, with searches performed on MEDLINE/PubMed, SCOPUS, Cochrane Library, Lilacs, and SciELO. The QUADAS-2 tool was employed to assess the quality of the studies. Diagnostic measures, such as sensitivity, specificity, diagnostic odds ratio, positive and negative likelihood ratios, area under the curve, and summary receiver operating characteristic, were included using a random-effects model. Heterogeneity and subgroup analyses were also conducted. All statistical analyses and plots were generated using the R software package. The PROSPERO ID is CRD42024506491.</p><p><strong>Results: </strong>Eleven deep-learning models from six articles were analyzed. In the random effects models, the sensitivity and specificity of the algorithms for detecting tendon conditions were 0.910 (95% CI: 0.865; 0.940) and 0.954 (0.909; 0.977). The PLR, NLR, lnDOR, and AUC estimates were found to be 37.075 (95%CI: 4.654; 69.496), 0.114 (95%CI: 0.056; 0.171), 5.160 (95% CI: 4.070; 6.250) with a (P < 0.001), and 96%, respectively.</p><p><strong>Conclusion: </strong>The deep-learning algorithms demonstrated a high level of accuracy level in detecting tendon anomalies. The overall robust performance suggests their potential application as a valuable complementary tool in diagnosing medical images.</p>\",\"PeriodicalId\":48598,\"journal\":{\"name\":\"Efort Open Reviews\",\"volume\":\"9 10\",\"pages\":\"941-952\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-10-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11457807/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Efort Open Reviews\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1530/EOR-24-0016\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ORTHOPEDICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Efort Open Reviews","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1530/EOR-24-0016","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ORTHOPEDICS","Score":null,"Total":0}
Deep learning models for tendinopathy detection: a systematic review and meta-analysis of diagnostic tests.
Purpose: Different deep-learning models have been employed to aid in the diagnosis of musculoskeletal pathologies. The diagnosis of tendon pathologies could particularly benefit from applying these technologies. The objective of this study is to assess the performance of deep learning models in diagnosing tendon pathologies using various imaging modalities.
Methods: A meta-analysis was conducted, with searches performed on MEDLINE/PubMed, SCOPUS, Cochrane Library, Lilacs, and SciELO. The QUADAS-2 tool was employed to assess the quality of the studies. Diagnostic measures, such as sensitivity, specificity, diagnostic odds ratio, positive and negative likelihood ratios, area under the curve, and summary receiver operating characteristic, were included using a random-effects model. Heterogeneity and subgroup analyses were also conducted. All statistical analyses and plots were generated using the R software package. The PROSPERO ID is CRD42024506491.
Results: Eleven deep-learning models from six articles were analyzed. In the random effects models, the sensitivity and specificity of the algorithms for detecting tendon conditions were 0.910 (95% CI: 0.865; 0.940) and 0.954 (0.909; 0.977). The PLR, NLR, lnDOR, and AUC estimates were found to be 37.075 (95%CI: 4.654; 69.496), 0.114 (95%CI: 0.056; 0.171), 5.160 (95% CI: 4.070; 6.250) with a (P < 0.001), and 96%, respectively.
Conclusion: The deep-learning algorithms demonstrated a high level of accuracy level in detecting tendon anomalies. The overall robust performance suggests their potential application as a valuable complementary tool in diagnosing medical images.
期刊介绍:
EFORT Open Reviews publishes high-quality instructional review articles across the whole field of orthopaedics and traumatology. Commissioned, peer-reviewed articles from international experts summarize current knowledge and practice in orthopaedics, with the aim of providing systematic coverage of the field. All articles undergo rigorous scientific editing to ensure the highest standards of accuracy and clarity.
This continuously published online journal is fully open access and will provide integrated CME. It is an authoritative resource for educating trainees and supports practising orthopaedic surgeons in keeping informed about the latest clinical and scientific advances.
One print issue containing a selection of papers from the journal will be published each year to coincide with the EFORT Annual Congress.
EFORT Open Reviews is the official journal of the European Federation of National Associations of Orthopaedics and Traumatology (EFORT) and is published in partnership with The British Editorial Society of Bone & Joint Surgery.