Literature DB >> 34117018

Diagnostic Accuracy and Failure Mode Analysis of a Deep Learning Algorithm for the Detection of Cervical Spine Fractures.

A F Voter1, M E Larson2, J W Garrett2, J-P J Yu3,4,5.   

Abstract

BACKGROUND AND
PURPOSE: Artificial intelligence decision support systems are a rapidly growing class of tools to help manage ever-increasing imaging volumes. The aim of this study was to evaluate the performance of an artificial intelligence decision support system, Aidoc, for the detection of cervical spinal fractures on noncontrast cervical spine CT scans and to conduct a failure mode analysis to identify areas of poor performance.
MATERIALS AND METHODS: This retrospective study included 1904 emergent noncontrast cervical spine CT scans of adult patients (60 [SD, 22] years, 50.3% men). The presence of cervical spinal fracture was determined by Aidoc and an attending neuroradiologist; discrepancies were independently adjudicated. Algorithm performance was assessed by calculation of the diagnostic accuracy, and a failure mode analysis was performed.
RESULTS: Aidoc and the neuroradiologist's interpretation were concordant in 91.5% of cases. Aidoc correctly identified 67 of 122 fractures (54.9%) with 106 false-positive flagged studies. Diagnostic performance was calculated as the following: sensitivity, 54.9% (95% CI, 45.7%-63.9%); specificity, 94.1% (95% CI, 92.9%-95.1%); positive predictive value, 38.7% (95% CI, 33.1%-44.7%); and negative predictive value, 96.8% (95% CI, 96.2%-97.4%). Worsened performance was observed in the detection of chronic fractures; differences in diagnostic performance were not altered by study indication or patient characteristics.
CONCLUSIONS: We observed poor diagnostic accuracy of an artificial intelligence decision support system for the detection of cervical spine fractures. Many similar algorithms have also received little or no external validation, and this study raises concerns about their generalizability, utility, and rapid pace of deployment. Further rigorous evaluations are needed to understand the weaknesses of these tools before widespread implementation.
© 2021 by American Journal of Neuroradiology.

Entities:  

Mesh:

Year:  2021        PMID: 34117018      PMCID: PMC8367597          DOI: 10.3174/ajnr.A7179

Source DB:  PubMed          Journal:  AJNR Am J Neuroradiol        ISSN: 0195-6108            Impact factor:   4.966


  20 in total

1.  Implementation of the Canadian CT Head Rule and Its Association With Use of Computed Tomography Among Patients With Head Injury.

Authors:  Adam L Sharp; Brian Z Huang; Tania Tang; Ernest Shen; Edward R Melnick; Arjun K Venkatesh; Michael H Kanter; Michael K Gould
Journal:  Ann Emerg Med       Date:  2017-07-21       Impact factor: 5.721

2.  Spinal Motion Restriction in the Trauma Patient - A Joint Position Statement.

Authors:  Peter E Fischer; Debra G Perina; Theodore R Delbridge; Mary E Fallat; Jeffrey P Salomone; Jimm Dodd; Eileen M Bulger; Mark L Gestring
Journal:  Prehosp Emerg Care       Date:  2018-08-09       Impact factor: 3.077

Review 3.  Traumatic cervical spine fractures in the adult.

Authors:  Phillip Copley; Vicky Tilliridou; Aimun Jamjoom
Journal:  Br J Hosp Med (Lond)       Date:  2016-09-02       Impact factor: 0.825

4.  Vertebral Body Compression Fractures and Bone Density: Automated Detection and Classification on CT Images.

Authors:  Joseph E Burns; Jianhua Yao; Ronald M Summers
Journal:  Radiology       Date:  2017-03-16       Impact factor: 11.105

5.  The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database.

Authors:  Stan Benjamens; Pranavsingh Dhunnoo; Bertalan Meskó
Journal:  NPJ Digit Med       Date:  2020-09-11

6.  ACR Appropriateness Criteria® Suspected Spine Trauma.

Authors:  Nicholas M Beckmann; O Clark West; Diego Nunez; Claudia F E Kirsch; Joseph M Aulino; Joshua S Broder; R Carter Cassidy; Gregory J Czuczman; Jennifer L Demertzis; Michele M Johnson; Kambiz Motamedi; Charles Reitman; Lubdha M Shah; Khoi Than; Elizabeth Ying-Kou Yung; Francesca D Beaman; Mark J Kransdorf; Julie Bykowski
Journal:  J Am Coll Radiol       Date:  2019-05       Impact factor: 5.532

7.  Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans.

Authors:  Naofumi Tomita; Yvonne Y Cheung; Saeed Hassanpour
Journal:  Comput Biol Med       Date:  2018-05-08       Impact factor: 4.589

8.  Analysis of head CT scans flagged by deep learning software for acute intracranial hemorrhage.

Authors:  Daniel T Ginat
Journal:  Neuroradiology       Date:  2019-12-11       Impact factor: 2.804

9.  A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis.

Authors:  Xiaoxuan Liu; Livia Faes; Aditya U Kale; Siegfried K Wagner; Dun Jack Fu; Alice Bruynseels; Thushika Mahendiran; Gabriella Moraes; Mohith Shamdas; Christoph Kern; Joseph R Ledsam; Martin K Schmid; Konstantinos Balaskas; Eric J Topol; Lucas M Bachmann; Pearse A Keane; Alastair K Denniston
Journal:  Lancet Digit Health       Date:  2019-09-25

10.  Design Characteristics of Studies Reporting the Performance of Artificial Intelligence Algorithms for Diagnostic Analysis of Medical Images: Results from Recently Published Papers.

Authors:  Dong Wook Kim; Hye Young Jang; Kyung Won Kim; Youngbin Shin; Seong Ho Park
Journal:  Korean J Radiol       Date:  2019-03       Impact factor: 3.500

View more
  5 in total

1.  Artificial Intelligence in "Code Stroke"-A Paradigm Shift: Do Radiologists Need to Change Their Practice?

Authors:  Achala Vagal; Luca Saba
Journal:  Radiol Artif Intell       Date:  2022-01-19

Review 2.  Current development and prospects of deep learning in spine image analysis: a literature review.

Authors:  Biao Qu; Jianpeng Cao; Chen Qian; Jinyu Wu; Jianzhong Lin; Liansheng Wang; Lin Ou-Yang; Yongfa Chen; Liyue Yan; Qing Hong; Gaofeng Zheng; Xiaobo Qu
Journal:  Quant Imaging Med Surg       Date:  2022-06

3.  Assessment of cervical spine CT scans by emergency physicians: A comparative diagnostic accuracy study in a non-clinical setting.

Authors:  Brigitta Britt Y M van der Kolk; Gabriella Gaby J van den Wittenboer; Niek Warringa; Ingrid M Nijholt; Boudewijn A A M van Hasselt; Lonneke N Buijteweg; Niels W L Schep; Mario Maas; Martijn F Boomsma
Journal:  J Am Coll Emerg Physicians Open       Date:  2022-01-20

Review 4.  Robotics and Artificial Intelligence in Endovascular Neurosurgery.

Authors:  Javier Bravo; Arvin R Wali; Brian R Hirshman; Tilvawala Gopesh; Jeffrey A Steinberg; Bernard Yan; J Scott Pannell; Alexander Norbash; James Friend; Alexander A Khalessi; David Santiago-Dieppa
Journal:  Cureus       Date:  2022-03-30

5.  Systematic analysis of the test design and performance of AI/ML-based medical devices approved for triage/detection/diagnosis in the USA and Japan.

Authors:  Mitsuru Yuba; Kiyotaka Iwasaki
Journal:  Sci Rep       Date:  2022-10-07       Impact factor: 4.996

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.