Koen D Oude Nijhuis, Lente H M Dankelman, Jort P Wiersma, Britt Barvelink, Frank F A IJpma, Michael H J Verhofstad, Job N Doornberg, Joost W Colaris, Mathieu M E Wijffels
{"title":"用于检测、分类和预测桡骨远端骨折失准的人工智能;系统综述。","authors":"Koen D Oude Nijhuis, Lente H M Dankelman, Jort P Wiersma, Britt Barvelink, Frank F A IJpma, Michael H J Verhofstad, Job N Doornberg, Joost W Colaris, Mathieu M E Wijffels","doi":"10.1007/s00068-024-02557-0","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Early and accurate assessment of distal radius fractures (DRFs) is crucial for optimal prognosis. Identifying fractures likely to lose threshold alignment (instability) in a cast is vital for treatment decisions, yet prediction tools' accuracy and reliability remain challenging. Artificial intelligence (AI), particularly Convolutional Neural Networks (CNNs), can evaluate radiographic images with high performance. This systematic review aims to summarize studies utilizing CNNs to detect, classify, or predict loss of threshold alignment of DRFs.</p><p><strong>Methods: </strong>A literature search was performed according to the PRISMA. Studies were eligible when the use of AI for the detection, classification, or prediction of loss of threshold alignment was analyzed. Quality assessment was done with a modified version of the methodologic index for non-randomized studies (MINORS).</p><p><strong>Results: </strong>Of the 576 identified studies, 15 were included. On fracture detection, studies reported sensitivity and specificity ranging from 80 to 99% and 73-100%, respectively; the AUC ranged from 0.87 to 0.99; the accuracy varied from 82 to 99%. The accuracy of fracture classification ranged from 60 to 81% and the AUC from 0.59 to 0.84. No studies focused on predicting loss of thresholds alignement of DRFs.</p><p><strong>Conclusion: </strong>AI models for DRF detection show promising performance, indicating the potential of algorithms to assist clinicians in the assessment of radiographs. In addition, AI models showed similar performance compared to clinicians. No algorithms for predicting the loss of threshold alignment were identified in our literature search despite the clinical relevance of such algorithms.</p>","PeriodicalId":12064,"journal":{"name":"European Journal of Trauma and Emergency Surgery","volume":null,"pages":null},"PeriodicalIF":1.9000,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"AI for detection, classification and prediction of loss of alignment of distal radius fractures; a systematic review.\",\"authors\":\"Koen D Oude Nijhuis, Lente H M Dankelman, Jort P Wiersma, Britt Barvelink, Frank F A IJpma, Michael H J Verhofstad, Job N Doornberg, Joost W Colaris, Mathieu M E Wijffels\",\"doi\":\"10.1007/s00068-024-02557-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>Early and accurate assessment of distal radius fractures (DRFs) is crucial for optimal prognosis. Identifying fractures likely to lose threshold alignment (instability) in a cast is vital for treatment decisions, yet prediction tools' accuracy and reliability remain challenging. Artificial intelligence (AI), particularly Convolutional Neural Networks (CNNs), can evaluate radiographic images with high performance. This systematic review aims to summarize studies utilizing CNNs to detect, classify, or predict loss of threshold alignment of DRFs.</p><p><strong>Methods: </strong>A literature search was performed according to the PRISMA. Studies were eligible when the use of AI for the detection, classification, or prediction of loss of threshold alignment was analyzed. Quality assessment was done with a modified version of the methodologic index for non-randomized studies (MINORS).</p><p><strong>Results: </strong>Of the 576 identified studies, 15 were included. On fracture detection, studies reported sensitivity and specificity ranging from 80 to 99% and 73-100%, respectively; the AUC ranged from 0.87 to 0.99; the accuracy varied from 82 to 99%. The accuracy of fracture classification ranged from 60 to 81% and the AUC from 0.59 to 0.84. No studies focused on predicting loss of thresholds alignement of DRFs.</p><p><strong>Conclusion: </strong>AI models for DRF detection show promising performance, indicating the potential of algorithms to assist clinicians in the assessment of radiographs. In addition, AI models showed similar performance compared to clinicians. No algorithms for predicting the loss of threshold alignment were identified in our literature search despite the clinical relevance of such algorithms.</p>\",\"PeriodicalId\":12064,\"journal\":{\"name\":\"European Journal of Trauma and Emergency Surgery\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2024-07-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Journal of Trauma and Emergency Surgery\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s00068-024-02557-0\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"EMERGENCY MEDICINE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Trauma and Emergency Surgery","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00068-024-02557-0","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"EMERGENCY MEDICINE","Score":null,"Total":0}
AI for detection, classification and prediction of loss of alignment of distal radius fractures; a systematic review.
Purpose: Early and accurate assessment of distal radius fractures (DRFs) is crucial for optimal prognosis. Identifying fractures likely to lose threshold alignment (instability) in a cast is vital for treatment decisions, yet prediction tools' accuracy and reliability remain challenging. Artificial intelligence (AI), particularly Convolutional Neural Networks (CNNs), can evaluate radiographic images with high performance. This systematic review aims to summarize studies utilizing CNNs to detect, classify, or predict loss of threshold alignment of DRFs.
Methods: A literature search was performed according to the PRISMA. Studies were eligible when the use of AI for the detection, classification, or prediction of loss of threshold alignment was analyzed. Quality assessment was done with a modified version of the methodologic index for non-randomized studies (MINORS).
Results: Of the 576 identified studies, 15 were included. On fracture detection, studies reported sensitivity and specificity ranging from 80 to 99% and 73-100%, respectively; the AUC ranged from 0.87 to 0.99; the accuracy varied from 82 to 99%. The accuracy of fracture classification ranged from 60 to 81% and the AUC from 0.59 to 0.84. No studies focused on predicting loss of thresholds alignement of DRFs.
Conclusion: AI models for DRF detection show promising performance, indicating the potential of algorithms to assist clinicians in the assessment of radiographs. In addition, AI models showed similar performance compared to clinicians. No algorithms for predicting the loss of threshold alignment were identified in our literature search despite the clinical relevance of such algorithms.
期刊介绍:
The European Journal of Trauma and Emergency Surgery aims to open an interdisciplinary forum that allows for the scientific exchange between basic and clinical science related to pathophysiology, diagnostics and treatment of traumatized patients. The journal covers all aspects of clinical management, operative treatment and related research of traumatic injuries.
Clinical and experimental papers on issues relevant for the improvement of trauma care are published. Reviews, original articles, short communications and letters allow the appropriate presentation of major and minor topics.