文献速递创伤骨科骨肿瘤

深度学习模型基于髋部X线片鉴别肿瘤性病理性骨折与非病理性骨折

Deep Learning Model for Differentiating Between Neoplastic Pathologic Fracture and Nonpathologic Fracture Using Hip Radiographs.
PubMed 文献 · J Bone Joint Surg Am · 2025-11-26

这项回顾性多中心研究分析了4家机构急诊患者的髋关节正位X线片,开发并评估用于鉴别肿瘤性病理性骨折与非病理性骨折的深度学习模型。模型在单中心338例患者数据上训练和测试,内部测试集总体准确率0.880、敏感度0.882、特异度0.879,并在另外3家机构488例患者中外部验证,准确率0.848、敏感度0.910、特异度0.786,性能与普通骨科医生相当。

要点

  • 内部测试集准确率0.880,敏感度0.882,特异度0.879。
  • 外部验证集准确率0.848,敏感度0.910,特异度0.786。
  • 模型性能与普通骨科医生相当,已公开可用。

核心结论

  • 所开发的深度学习模型是鉴别髋部X线片上肿瘤性病理性骨折与非病理性骨折的可靠且有效的工具。
  • 该模型有潜力在资源有限环境中辅助骨科医生,在这些环境中优化X线片判读对患者照护至关重要。

研究设计与样本

  • 回顾性多中心研究,分析4家不同机构急诊就诊患者的髋关节正位X线片。
  • 深度学习模型在单中心338例患者数据上训练和测试,并在另外3家机构488例患者数据上外部验证。

主要发现

  • 内部测试集:总体准确率0.880,敏感度0.882,特异度0.879。
  • 外部验证集(488例患者,其中肿瘤性病理性骨折67例、非病理性骨折421例):总体准确率0.848,敏感度0.910,特异度0.786。
  • 模型性能与普通骨科医生相当。

关键数值与推荐

  • 内部测试集总体准确率0.880、敏感度0.882、特异度0.879。
  • 外部验证集总体准确率0.848、敏感度0.910、特异度0.786。
  • 证据等级为诊断性研究III级。

临床怎么用

  • 模型已公开可用,网址为https://pathfxdx.org。
  • 模型有潜力在资源有限环境中辅助骨科医生优化X线片判读。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Although radiographs are the first-line imaging modality, differentiating between neoplastic pathologic fractures and nonpathologic fractures on radiographs can sometimes be challenging. In this study, we aimed to develop and evaluate a deep learning model capable of distinguishing neoplastic pathologic fractures from nonpathologic fractures on hip radiographs to enhance diagnostic accuracy. METHODS: This retrospective, multicenter study analyzed anteroposterior hip radiographs from patients who visited the emergency department at 4 different institutions. The deep learning model was trained on, and tested using, data from 338 patients at a single institution and externally validated on data from 488 patients across 3 additional institutions. RESULTS: The model achieved an overall accuracy of 0.880, with a sensitivity of 0.882 and a specificity of 0.879, on the internal test set. It was then externally validated using the data of 488 patients (67 with neoplastic pathologic fracture and 421 with nonpathologic fracture) from institutions separate from where the model was developed. The model achieved an overall accuracy of 0.848, sensitivity of 0.910, and specificity of 0.786. Its performance was comparable with that of general orthopaedic surgeons. CONCLUSIONS: The developed deep learning model is a reliable and valid tool for distinguishing neoplastic pathologic fractures from nonpathologic fractures on hip radiographs. It has the potential to assist orthopaedic surgeons in resource-limited settings, where optimizing the interpretation of radiographs is critical for patient care. The model is publicly available at https://pathfxdx.org . LEVEL OF EVIDENCE: Diagnostic Level III . See Instructions for Authors for a complete description of levels of evidence.

来源:J Bone Joint Surg Am,查看原文。版权归原作者所有。

引用

  1. Kim S, Shin K, Kim HS, et al. Deep Learning Model for Differentiating Between Neoplastic Pathologic Fracture and Nonpathologic Fracture Using Hip Radiographs. J Bone Joint Surg Am. 2025. PMID: 41296822. doi:10.2106/JBJS.25.00344

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。