EUVIMEDEUVIMED entdecken
Crossref

Beyond diagnosis: deep-learning-based analysis of hospitalization using abdominal radiographs in the emergency department

Yeo Eun Han iD, Yongwon Cho iD, Beom Jin Park iD, Ki Choon Sim iD, Na Yeon Han iD, Min Ju Kim iD, Deuk Jae Sung iD, Suk Keu Yeom iD

Abdominal Radiology · 2025

DOI: 10.1007/s00261-025-05347-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Abdominal Radiology, 2025. Verfasst von Yeo Eun Han und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology and Advanced Medical Imaging Institute, Korea University Anam Hospital, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Emergency Service, Hospital, Radiography, Abdominal, Hospitalization. Die Arbeit nennt 22 Literaturangaben. Gefördert von: National Research Foundation of Korea (NRF), funded by the Ministry of Education, Republic of Korea, Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Ko….

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: Abdominal radiography (AXR) is routinely performed in emergency departments (ED) but has limited clinical utility. Thus, this study developed deep-learning models using AXR to predict hospitalization in ED patients with abdominal symptoms. METHODS: This retrospective study included 1,585 adult ED patients with abdominal symptoms who underwent AXR between August and December 2021. External validation included 112 patients. Three prediction models were developed using random forest classifiers: an image model, a clinical model, and a fusion model combining both image and clinical features. DenseNet201 extracted image features, and early clinical information obtainable by non-physician staff was incorporated. The performances of the two radiologists were compared with those of a deep-learning model. RESULTS: The fusion model achieved an area under the receiver operating characteristic curve (AUROC) of 0.70 (95% confidence interval: 0.65-0.76), sensitivity of 0.82, and an F1-score of 0.75 in internal validation. Human readers showed high specificity (0.80-0.95) but low sensitivity (0.13-0.52) and F1-scores (0.23-0.55). Deep-learning models achieved substantially higher sensitivity and F1-scores than human readers, but with lower specificity (0.43), making them suitable for screening. In the external validation, the performance of the fusion model decreased (AUROC, 0.60), but image-based models maintained a higher sensitivity than human readers. Of all the radiographs, 11.1% showed abnormal findings, and 5.8% were specific to the final diagnosis. CONCLUSION: Deep learning significantly improved the clinical utility of AXR in screening for hospitalization risk, achieving higher sensitivity and F1-scores than radiologists. While these models require further improvement for clinical implementation, they can potentially extract predictive patterns from traditionally limited imaging studies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningEmergency Service, HospitalRadiography, AbdominalHospitalizationHumansRetrospective StudiesFemaleMaleMiddle AgedSensitivity and SpecificityAdultAgedPredictive Learning Models

Stichwörter der Autor:innen

Abdominal radiographyArtificial intelligenceDeep learningEmergency departmentHospitalization prediction

Autor:innen und Institutionen

  • Department of Radiology and Advanced Medical Imaging Institute, Korea University Anam Hospital, Seoul, Republic of Korea.
  • Department of Computer Science and Engineering, Soonchunhyang University, Asan-si, Republic of Korea.
  • Department of Radiology and Advanced Medical Imaging Institute, Korea University Anam Hospital, Seoul, Republic of Korea. radiolbj226@gmail.com.
  • Department of Radiology, Korea University Ansan Hospital, Ansan-si, Republic of Korea.

ORCID-Profile: Yeo Eun Han, Yongwon Cho, Beom Jin Park, Ki Choon Sim, Na Yeon Han, Min Ju Kim, Deuk Jae Sung, Suk Keu Yeom

Förderung

  • National Research Foundation of Korea (NRF), funded by the Ministry of Education, Republic of Korea
  • Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Ko…

Zitieren

APA

Han, Y. E., Cho, Y., Park, B. J., Sim, K. C., Han, N. Y., Kim, M. J., Sung, D. J., & Yeom, S. K. (2025). Beyond diagnosis: deep-learning-based analysis of hospitalization using abdominal radiographs in the emergency department. Abdominal Radiology. https://doi.org/10.1007/s00261-025-05347-3

Vancouver

Han YE, Cho Y, Park BJ, Sim KC, Han NY, Kim MJ, et al. Beyond diagnosis: deep-learning-based analysis of hospitalization using abdominal radiographs in the emergency department. Abdominal Radiology. 2025. doi:10.1007/s00261-025-05347-3

BibTeX
@article{Han2025,
  author = {Han, Yeo Eun and Cho, Yongwon and Park, Beom Jin and Sim, Ki Choon and Han, Na Yeon and Kim, Min Ju and Sung, Deuk Jae and Yeom, Suk Keu},
  title = {Beyond diagnosis: deep-learning-based analysis of hospitalization using abdominal radiographs in the emergency department},
  journal = {Abdominal Radiology},
  year = {2025},
  doi = {10.1007/s00261-025-05347-3}
}
Kostenlos starten →