EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Comparative accuracy of two commercial AI algorithms for musculoskeletal trauma detection in emergency radiographs

Jarno T Huhtanen, Mikko Nyman, Roberto Blanco Sequeiros, Seppo K Koskinen, Tomi K Pudas, Sami Kajander, Pekka Niemi, Hannu J Aronen, Jussi Hirvonen

Emergency Radiology · 09.06.2025 · 32 (4) · 569-580

DOI: 10.1007/s10140-025-02353-2 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Emergency Radiology, online erschienen am 09.06.2025. Verfasst von Jarno T Huhtanen und 8 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Health and Well-being, Turku University of Applied Sciences, Joukahaisenkatu, Turku, 20520, Finland. jarno.huhtanen@turkuamk.fi. Hauptthemen laut MEDLINE: Algorithms, Fractures, Bone, Artificial Intelligence, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Turku.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Missed fractures are the primary cause of interpretation errors in emergency radiology, and artificial intelligence has recently shown great promise in radiograph interpretation. This study compared the diagnostic performance of two AI algorithms, BoneView and RBfracture, in detecting traumatic abnormalities (fractures and dislocations) in MSK radiographs.

Methods

AI algorithms analyzed 998 radiographs (585 normal, 413 abnormal), against the consensus of two MSK specialists. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and interobserver agreement (Cohen’s Kappa) were calculated. 95% confidence intervals (CI) assessed robustness, and McNemar’s tests compared sensitivity and specificity between the AI algorithms.

Results

BoneView demonstrated a sensitivity of 0.893 (95% CI: 0.860–0.920), specificity of 0.885 (95% CI: 0.857–0.909), PPV of 0.846, NPV of 0.922, and accuracy of 0.889. RBfracture demonstrated a sensitivity of 0.872 (95% CI: 0.836–0.901), specificity of 0.892 (95% CI: 0.865–0.915), PPV of 0.851, NPV of 0.908, and accuracy of 0.884. No statistically significant differences were found in sensitivity ( p = 0.151) or specificity ( p = 0.708). Kappa was 0.81 (95% CI: 0.77–0.84), indicating almost perfect agreement between the two AI algorithms. Performance was similar in adults and children. Both AI algorithms struggled more with subtle abnormalities, which constituted 66% and 70% of false negatives but only 20% and 18% of true positives for the two AI algorithms, respectively ( p < 0.001).

Conclusions

BoneView and RBfracture exhibited high diagnostic performance and almost perfect agreement, with consistent results across adults and children, highlighting the potential of AI in emergency radiograph interpretation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsFractures, BoneArtificial IntelligenceRadiographic Image Interpretation, Computer-AssistedHumansMaleFemaleSensitivity and SpecificityAdultChildMiddle AgedEmergency Service, HospitalChild, PreschoolAdolescentAgedRetrospective StudiesInfant

Stichwörter der Autor:innen

Appendicular skeletonArtificial intelligenceFractureRadiograph

Autor:innen und Institutionen

  • Faculty of Health and Well-being, Turku University of Applied Sciences, Joukahaisenkatu, Turku, 20520, Finland. jarno.huhtanen@turkuamk.fi.
  • Department of Radiology, University of Turku, Turku, Finland. jarno.huhtanen@turkuamk.fi.
  • Department of Radiology, University of Turku, Turku University Hospital, Turku, Finland.
  • Terveystalo Inc, Jaakonkatu 3, Helsinki, Finland.
  • Department of Radiology, University of Turku, Turku, Finland.
  • Department of Radiology, Faculty of Medicine and Health Technology, Tampere University, Tampere University Hospital, Tampere, Finland.

Förderung

  • University of Turku

Zitieren

APA

Huhtanen, J. T., Nyman, M., Blanco Sequeiros, R., Koskinen, S. K., Pudas, T. K., Kajander, S., Niemi, P., Aronen, H. J., & Hirvonen, J. (2025). Comparative accuracy of two commercial AI algorithms for musculoskeletal trauma detection in emergency radiographs. Emergency Radiology, 32(4), 569-580. https://doi.org/10.1007/s10140-025-02353-2

Vancouver

Huhtanen JT, Nyman M, Blanco Sequeiros R, Koskinen SK, Pudas TK, Kajander S, et al. Comparative accuracy of two commercial AI algorithms for musculoskeletal trauma detection in emergency radiographs. Emergency Radiology. 2025;32(4):569-580. doi:10.1007/s10140-025-02353-2

BibTeX
@article{Huhtanen2025,
  author = {Huhtanen, Jarno T and Nyman, Mikko and Blanco Sequeiros, Roberto and Koskinen, Seppo K and Pudas, Tomi K and Kajander, Sami and Niemi, Pekka and Aronen, Hannu J and Hirvonen, Jussi},
  title = {Comparative accuracy of two commercial AI algorithms for musculoskeletal trauma detection in emergency radiographs},
  journal = {Emergency Radiology},
  year = {2025},
  volume = {32},
  number = {4},
  pages = {569--580},
  doi = {10.1007/s10140-025-02353-2}
}
Kostenlos starten →