2022
DOI: 10.3389/fped.2022.818061
|View full text |Cite
|
Sign up to set email alerts
|

Artificial Intelligence–Assisted Bone Age Assessment to Improve the Accuracy and Consistency of Physicians With Different Levels of Experience

Abstract: BackgroundThe accuracy and consistency of bone age assessments (BAA) using standard methods can vary with physicians' level of experience.MethodsTo assess the impact of information from an artificial intelligence (AI) deep learning convolutional neural network (CNN) model on BAA, specialists with different levels of experience (junior, mid-level, and senior) assessed radiographs from 316 children aged 4–18 years that had been randomly divided into two equal sets-group A and group B. Bone age (BA) was assessed … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

2
1
0
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 10 publications
(4 citation statements)
references
References 24 publications
2
1
0
1
Order By: Relevance
“…Another goal of this study was to evaluate the efficiency and accuracy of BAA performed with the aid of AI. The results showed that not only could AI help to save time and increase the efficiency of BAA, which was a finding in common with previous studies (10, 14), but that the accuracy of both raters significantly improved after the assistance of an AI system (8.36% vs. 91.72%, 13.45% vs. 91.03%). The results of this study agreed with that of previous research where an automatic BAA system was used to rate the BA of Iranian children, which yielded an accuracy within a 1-year range of 95.32% for radiographs of female patients, and 96.51% for radiographs of male patients, respectively (19).…”
Section: Discussionsupporting
confidence: 89%
See 1 more Smart Citation
“…Another goal of this study was to evaluate the efficiency and accuracy of BAA performed with the aid of AI. The results showed that not only could AI help to save time and increase the efficiency of BAA, which was a finding in common with previous studies (10, 14), but that the accuracy of both raters significantly improved after the assistance of an AI system (8.36% vs. 91.72%, 13.45% vs. 91.03%). The results of this study agreed with that of previous research where an automatic BAA system was used to rate the BA of Iranian children, which yielded an accuracy within a 1-year range of 95.32% for radiographs of female patients, and 96.51% for radiographs of male patients, respectively (19).…”
Section: Discussionsupporting
confidence: 89%
“…This study demonstrated that the deployment of an AI assistance system decreased variations in inter-rater and intrarater consistency. The results also built on recent data by Xi Wang et al, which demonstrated that an AI system based on CH05 BAA improved the performance of specialists with different levels of experience, thus increasing the ICC (14). The result also resonates with another study, which implied that an AI-assisted system could reduce variation in BAA by different raters, as well as the time required to read one radiograph (15).…”
Section: Discussionsupporting
confidence: 77%
“…Например, хорошо известная программа BoneXpert© [12] может быть недоступна для отечественных врачей вследствие ее высокой стоимости. Тем не менее, есть надежда, что разработки из союзных государств и отечественные разработки станут более доступными в будущем, что положительно повлияет на использование этих методов [20][21][22][23][24][25][26][27][28][29][30] СПИСОК ИСТОЧНИКОВ…”
Section: клинические исследованияunclassified
“…Given the above, potential racial bias in these radiology procedures may alter their precision and accuracy based on the racial group to which children belong [4]. Systematic use of standard radiological methods for BA assessment may lead to incorrect decisions by experts, such as pediatricians caring for children with advanced or delayed growth, or forensic estimation of CA among migrant children [30,31]. Therefore, it is essential for experts to obtain up-to-date and reliable information on the metric properties of radiological methods used for BA assessment, not only to resolve medical but also ethical and legal issues.…”
Section: Introductionmentioning
confidence: 99%