Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists

Nguyen, Toan; Maarek, Richard; Hermann, Anne-Laure; Kammoun, Amina; Marchi, Antoine; Khelifi-Touhami, Mohamed R; Collin, Mégane; Jaillard, Aliénor; Kompel, Andrew J.; Hayashi, Daichi; Guermazi, Ali; Pointe, Hubert Ducou Le

doi:10.1007/s00247-022-05496-3

Cited by 21 publications

(26 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A separate study on pediatric patients (2–21 years of age) found a per patient sensitivity of 91.3% with a specificity of 90%, with a low sensitivity of the AI for avulsion fractures [ 11 ]. Nguyen et al were able to find an increase in sensitivity in a retrospective dataset of pediatric patients for fracture detection (73.3% without AI, 82.8% with assistance), with an increase of 10.3% for junior radiologists and 8.2% for senior radiologists [ 12 ]. In our study a small subset of pediatric patients is included, representing the patients that presented to our institution’s emergency department.…”

Section: Discussionmentioning

confidence: 99%

A Prospective Approach to Integration of AI Fracture Detection Software in Radiographs into Clinical Workflow

Oppenheimer

Lüken

Hamm

et al. 2023

Life

View full text Add to dashboard Cite

Gleamer BoneView© is a commercially available AI algorithm for fracture detection in radiographs. We aim to test if the algorithm can assist in better sensitivity and specificity for fracture detection by residents with prospective integration into clinical workflow. Radiographs with inquiry for fracture initially reviewed by two residents were randomly assigned and included. A preliminary diagnosis of a possible fracture was made. Thereafter, the AI decision on presence and location of possible fractures was shown and changes to diagnosis could be made. Final diagnosis of fracture was made by a board-certified radiologist with over eight years of experience, or if available, cross-sectional imaging. Sensitivity and specificity of the human report, AI diagnosis, and assisted report were calculated in comparison to the final expert diagnosis. 1163 exams in 735 patients were included, with a total of 367 fractures (31.56%). Pure human sensitivity was 84.74%, and AI sensitivity was 86.92%. Thirty-five changes were made after showing AI results, 33 of which resulted in the correct diagnosis, resulting in 25 additionally found fractures. This resulted in a sensitivity of 91.28% for the assisted report. Specificity was 97.11, 84.67, and 97.36%, respectively. AI assistance showed an increase in sensitivity for both residents, without a loss of specificity.

show abstract

Section: Discussionmentioning

confidence: 99%

A Prospective Approach to Integration of AI Fracture Detection Software in Radiographs into Clinical Workflow

Oppenheimer

Lüken

Hamm

et al. 2023

Life

View full text Add to dashboard Cite

show abstract

“…Seven studies reported accuracy for diagnoses made by radiologists with and without the assistance of AI, including for lung-related abnormalities [28,[32][33][34], breast cancer [7,35], thyroid nodules [36], ETT placement [39], and fractures [37]. Measures of accuracy included the sensitivity, specificity, PPV, NPV, area under the receiver operating characteristic curve, F1 score, detection rate, and κ coefficient for inter-rater or reliability assessment.…”

Section: Effect Of Ai In Improving Accuracymentioning

confidence: 99%

“…AI-assisted radiologists had improved sensitivity by 6.2%, 4.6%, 0.6%, and 17.3% for each subgroup, respectively [28]. Nguyen et al divided radiologists into two subgroups based on their experience and found an improvement in sensitivity of 10.3% for residents and 8.2% for imaging experts [37]. Although no statistically significant results were found for specificity, some studies suggested increased specificity with AI assistance, including in the study by Calisto et al [35], the resident group in the study by Nguyen et al [37], and the pleural effusion group in the study by Ahn et al [28].…”

Section: Effect Of Ai In Improving Accuracymentioning

confidence: 99%

“…Nguyen et al divided radiologists into two subgroups based on their experience and found an improvement in sensitivity of 10.3% for residents and 8.2% for imaging experts [37]. Although no statistically significant results were found for specificity, some studies suggested increased specificity with AI assistance, including in the study by Calisto et al [35], the resident group in the study by Nguyen et al [37], and the pleural effusion group in the study by Ahn et al [28]. According to Wong et al [39]., the PPV of the AI system in practical clinical application was found to be comparable to that observed in previous experiments, both at 42%.…”

Section: Effect Of Ai In Improving Accuracymentioning

confidence: 99%

“…Whereas junior radiologists benefited significantly from AI assistance, senior radiologists with high accuracy levels experienced limited benefits. The latter group may even face the risk of an increased workload owing to AI's potential for misdiagnosis [37].…”

Section: Effect Of Ai On Radiology Practice By Improving Accuracymentioning

confidence: 99%

See 2 more Smart Citations

Efficiency, accuracy, and health professional's perspectives regarding artificial intelligence in radiology practice: A scoping review

He,

Liu,

et al. 2024

iRADIOLOGY

View full text Add to dashboard Cite

In this scoping review, we evaluated the performance of artificial intelligence (AI) in clinical radiology practice and examined health professionals' perspectives regarding AI use in radiology. This review followed the Joanna Briggs Institute (JBI) methodological guidelines. We searched multiple databases and the gray literature from March 15, 2016 to December 31, 2023. Of 49 articles reviewed, 13 assessed the performance of AI in radiology clinical practice, and 36 examined the attitudes of health professionals toward the use of AI in radiology. In four separate studies, AI significantly improved the diagnostic sensitivity or detection rate. Furthermore, six articles emphasized a significant reduction in case reading times with AI use. Although three studies suggested an increase in specificity with the assistance of AI, these findings did not reach statistical significance. Health professionals expressed the belief that AI would have a significant impact on radiology but would not replace radiologists in the near future. Limited knowledge of AI was observed among health professionals, who supported increased education and explicit regulations and guidelines related to AI. Overall, AI can enhance diagnostic efficiency and accuracy in clinical radiology practice. However, knowledge gaps and the concerns of health professionals should be addressed by prioritizing education and reinforcing ethical and legal regulations to facilitate the advancement of AI use in radiology. This scoping review provides evidence toward a comprehensive understanding of AI's potential in clinical radiology practice, promoting its use and stimulating further discussion on related challenges and implications.

show abstract

Re: ‘Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists’

et al. 2022

View full text Add to dashboard Cite

Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists

Cited by 21 publications

References 20 publications

A Prospective Approach to Integration of AI Fracture Detection Software in Radiographs into Clinical Workflow

A Prospective Approach to Integration of AI Fracture Detection Software in Radiographs into Clinical Workflow

Efficiency, accuracy, and health professional's perspectives regarding artificial intelligence in radiology practice: A scoping review

Re: ‘Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists’

Contact Info

Product

Resources

About