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 independently by each specialist without additional information (group A) and with information from the model (group B). With the mean assessment of four experts as the reference standard, mean absolute error (MAE), and intraclass correlation coefficient (ICC) were calculated to evaluate accuracy and consistency. Individual assessments of 13 bones (radius, ulna, and short bones) were also compared between group A and group B with the rank-sum test.ResultsThe accuracies of senior, mid-level, and junior physicians were significantly better (all P < 0.001) with AI assistance (MAEs 0.325, 0.344, and 0.370, respectively) than without AI assistance (MAEs 0.403, 0.469, and 0.755, respectively). Moreover, for senior, mid-level, and junior physicians, consistency was significantly higher (all P < 0.001) with AI assistance (ICCs 0.996, 0.996, and 0.992, respectively) than without AI assistance (ICCs 0.987, 0.989, and 0.941, respectively). For all levels of experience, accuracy with AI assistance was significantly better than accuracy without AI assistance for assessments of the first and fifth proximal phalanges.ConclusionsInformation from an AI model improves both the accuracy and the consistency of bone age assessments for physicians of all levels of experience. The first and fifth proximal phalanges are difficult to assess, and they should be paid more attention.

Clinical application of artificial intelligence in longitudinal image analysis of bone age among GHD patients

“…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).…”

“…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).…”

Comparison of bone age assessment methods using a hand radiography in patients with active growth plate and anteromedial knee instability

“…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…”

Precision and Accuracy of Radiological Bone Age Assessment in Children among Different Ethnic Groups: A Systematic Review

“…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.…”