Scholarlink

Objectives <p>The aim of this study is to validate the effectiveness of an AI tool trained on Indian data in a Dutch medical center and to assess its ability to classify and localize fractures.</p> Methods <p>Conventional radiographs acquired between January 2019 and November 2022 were analyzed using a multitask deep neural network. The tool, trained on Indian data, identified and localized fractures in 17 body parts. The reference standard was based on radiology reports resulting from routine clinical workflow and confirmed by an experienced musculoskeletal radiologist. The analysis included both patient-wise and fracture-wise evaluations, employing binary and Intersection over Union (IoU) metrics to assess fracture detection and localization accuracy.</p> Results <p>In total, 14,311 radiographs (median age, 48 years (range 18–98), 7265 male) were analyzed and categorized by body parts; clavicle, shoulder, humerus, elbow, forearm, wrist, hand and finger, pelvis, hip, femur, knee, lower leg, ankle, foot and toe. 4156/14,311 (29%) had fractures. The AI tool demonstrated overall patient-wise sensitivity, specificity, and AUC of 87.1% (95% CI: 86.1–88.1%), 87.1% (95% CI: 86.4–87.7%), and 0.92 (95% CI: 0.91–0.93), respectively. Fracture detection rate was 60% overall, ranging from 7% for rib fractures to 90% for clavicle fractures.</p> Conclusions <p>This study validates a fracture detection AI tool on a Western-European dataset, originally trained on Indian data. While classification performance is robust on real clinical data, fracture-wise analysis reveals variability in localization accuracy, underscoring the need for refinement in fracture localization.</p> Critical relevance statement <p>AI may provide help by enabling optimal use of limited resources or personnel. This study evaluates an AI tool designed to aid in detecting fractures, possibly reducing reading time or optimization of radiology workflow by prioritizing fracture-positive cases.</p> Key Points <p><UnorderedList Mark="Bullet"> <ItemContent> <p>Cross-validation on a consecutive Dutch cohort confirms this AI tool’s clinical robustness.</p> </ItemContent> <ItemContent> <p>The tool detected fractures with 87% sensitivity, 87% specificity, and 0.92 AUC.</p> </ItemContent> <ItemContent> <p>AI localizes 60% of fractures, the highest for clavicle (90%) and lowest for ribs (7%).</p> </ItemContent> </UnorderedList></p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Cross-validation of an artificial intelligence tool for fracture classification and localization on conventional radiography in Dutch population

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月3日

查看全文
  • Huibert C. Ruitenbeek,
  • Sahil Sahil,
  • Aradhana Kumar,
  • Ravi Kumar Kushawaha,
  • Swetha Tanamala,
  • Saigopal Sathyamurthy,
  • Rohitashva Agrawal,
  • Subhankar Chattoraj,
  • Jasika Paramasamy,
  • Daniel Bos,
  • Roshan Fahimi,
  • Edwin H. G. Oei,
  • Jacob J. Visser

摘要

Objectives

The aim of this study is to validate the effectiveness of an AI tool trained on Indian data in a Dutch medical center and to assess its ability to classify and localize fractures.

Methods

Conventional radiographs acquired between January 2019 and November 2022 were analyzed using a multitask deep neural network. The tool, trained on Indian data, identified and localized fractures in 17 body parts. The reference standard was based on radiology reports resulting from routine clinical workflow and confirmed by an experienced musculoskeletal radiologist. The analysis included both patient-wise and fracture-wise evaluations, employing binary and Intersection over Union (IoU) metrics to assess fracture detection and localization accuracy.

Results

In total, 14,311 radiographs (median age, 48 years (range 18–98), 7265 male) were analyzed and categorized by body parts; clavicle, shoulder, humerus, elbow, forearm, wrist, hand and finger, pelvis, hip, femur, knee, lower leg, ankle, foot and toe. 4156/14,311 (29%) had fractures. The AI tool demonstrated overall patient-wise sensitivity, specificity, and AUC of 87.1% (95% CI: 86.1–88.1%), 87.1% (95% CI: 86.4–87.7%), and 0.92 (95% CI: 0.91–0.93), respectively. Fracture detection rate was 60% overall, ranging from 7% for rib fractures to 90% for clavicle fractures.

Conclusions

This study validates a fracture detection AI tool on a Western-European dataset, originally trained on Indian data. While classification performance is robust on real clinical data, fracture-wise analysis reveals variability in localization accuracy, underscoring the need for refinement in fracture localization.

Critical relevance statement

AI may provide help by enabling optimal use of limited resources or personnel. This study evaluates an AI tool designed to aid in detecting fractures, possibly reducing reading time or optimization of radiology workflow by prioritizing fracture-positive cases.

Key Points

Cross-validation on a consecutive Dutch cohort confirms this AI tool’s clinical robustness.

The tool detected fractures with 87% sensitivity, 87% specificity, and 0.92 AUC.

AI localizes 60% of fractures, the highest for clavicle (90%) and lowest for ribs (7%).

Graphical Abstract