EUVIMEDEUVIMED entdecken
Multizentrische Studie

Deep Learning Model for Differentiating Between Neoplastic Pathologic Fracture and Nonpathologic Fracture Using Hip Radiographs

Shinn Kim, Kyoungseob Shin, Han-Soo Kim iD, Yongsung Kim iD, June Hyuk Kim iD, Min Wook Joo iD, Wanlim Kim iD, Jay Hoon Park iD, Yoon Joo Cho iD, Minsu Kim iD, Sunghoon Kwon iD, Ilkyu Han iD

Journal of Bone and Joint Surgery · 2026

DOI: 10.2106/jbjs.25.00344 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of Bone and Joint Surgery, 2026. Verfasst von Shinn Kim und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopaedic Surgery, Seoul National University Hospital, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Fractures, Spontaneous, Hip Fractures, Bone Neoplasms. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningFractures, SpontaneousHip FracturesBone NeoplasmsHumansRetrospective StudiesFemaleDiagnosis, DifferentialMaleAgedRadiographyMiddle AgedSensitivity and SpecificityAged, 80 and overAdult

Autor:innen und Institutionen

  • Department of Orthopaedic Surgery, Seoul National University Hospital, Seoul, Republic of Korea.
  • Interdisciplinary Program in Bioengineering, Seoul National University, Seoul, Republic of Korea.
  • Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea.
  • Department of Orthopaedic Surgery, Seoul National University College of Medicine, Seoul, Republic of Korea.
  • Department of Orthopaedic Surgery, Seoul National University Bundang Hospital, Seongnam, Republic of Korea.
  • Orthopaedic Oncology Clinic, National Cancer Center, Goyang, Republic of Korea.

ORCID-Profile: Han-Soo Kim, Yongsung Kim, June Hyuk Kim, Min Wook Joo, Wanlim Kim, Jay Hoon Park, Yoon Joo Cho, Minsu Kim, Sunghoon Kwon, Ilkyu Han

Zitieren

APA

Kim, S., Shin, K., Kim, H. S., Kim, Y., Kim, J. H., Joo, M. W., Kim, W., Park, J. H., Cho, Y. J., Kim, M., Kwon, S., & Han, I. (2026). Deep Learning Model for Differentiating Between Neoplastic Pathologic Fracture and Nonpathologic Fracture Using Hip Radiographs. Journal of Bone and Joint Surgery. https://doi.org/10.2106/jbjs.25.00344

Vancouver

Kim S, Shin K, Kim HS, Kim Y, Kim JH, Joo MW, et al. Deep Learning Model for Differentiating Between Neoplastic Pathologic Fracture and Nonpathologic Fracture Using Hip Radiographs. Journal of Bone and Joint Surgery. 2026. doi:10.2106/jbjs.25.00344

BibTeX
@article{Kim2026,
  author = {Kim, Shinn and Shin, Kyoungseob and Kim, Han-Soo and Kim, Yongsung and Kim, June Hyuk and Joo, Min Wook and Kim, Wanlim and Park, Jay Hoon and Cho, Yoon Joo and Kim, Minsu and Kwon, Sunghoon and Han, Ilkyu},
  title = {Deep Learning Model for Differentiating Between Neoplastic Pathologic Fracture and Nonpathologic Fracture Using Hip Radiographs},
  journal = {Journal of Bone and Joint Surgery},
  year = {2026},
  doi = {10.2106/jbjs.25.00344}
}
Kostenlos starten →