EUVIMEDEUVIMED entdecken
Multizentrische Studie

Interpretable machine learning model for predicting hemorrhage following ultrasound-guided percutaneous renal biopsy: a multicenter study

Liyang Su, Jinliang Nie, Qiaojie Xie, Shilin Li, Qingquan Zhang

Abdominal Radiology · 28.05.2026 · 51 (12) · 6409-6419

DOI: 10.1007/s00261-026-05582-2 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Abdominal Radiology, online erschienen am 28.05.2026. Verfasst von Liyang Su und 4 weiteren Autor:innen. Beteiligte Einrichtung: Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou, China. Hauptthemen laut MEDLINE: Ultrasonography, Interventional, Machine Learning, Image-Guided Biopsy, Kidney. Die Arbeit nennt 24 Literaturangaben. Gefördert von: the Joint funds for the innovation of science and technology, Fujian province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: This study aims to develop and validate an interpretable machine learning (ML) model for predicting post-procedural hemorrhage (PH) after ultrasound-guided percutaneous renal biopsy (PRB), aiding perioperative management. MATERIALS AND METHODS: A retrospective analysis was conducted using data from 664 patients to develop and internally validate the predictive model. Key ultrasound parameters and clinical data were collected. The Boruta algorithm selected predictive factors. Eight ML models underwent hyperparameter tuning with 5-fold cross-validation, using the area under the curve (AUC) to determine the best model, which was further validated externally (n = 137). Model interpretation was enhanced using SHAP values. RESULTS: Important predictive factors identified included renal parenchymal thickness (RPT), distance from the puncture point to the lower edge of the kidney (D1), and the ratio of D1 to the Renal length (R1), disease course, eGFR and prothrombin time (PT). The random forest model outperformed others with AUCs of 0.831, 0.784, and 0.776 for the training, internal validation, and external validation sets, respectively, displaying an accuracy of 0.742, sensitivity of 0.675, specificity of 0.805, and F1 score of 0.691. SHAP analysis highlighted prolonged PT, thinner RPT, smaller D1, lower eGFR, and extended disease course as increasing PH risk. CONCLUSION: The random forest model effectively predicts PH post-PRB, supporting early diagnosis and decision-making.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Ultrasonography, InterventionalMachine LearningImage-Guided BiopsyKidneyPostoperative HemorrhageKidney DiseasesHemorrhageHumansRetrospective StudiesFemaleMaleMiddle AgedPredictive Learning ModelsAgedRandom ForestSensitivity and SpecificityPredictive Value of Tests

Stichwörter der Autor:innen

Interventional ultrasonographyMachine learningPostoperative hemorrhagePredictive modelsRandom forestRenal insufficiency

Autor:innen und Institutionen

  • Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou, China.
  • The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China.
  • The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China. lslqz@fjmu.edu.cn.
  • Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou, China. zhangqq200900353@163.com.

Förderung

  • the Joint funds for the innovation of science and technology, Fujian province

Zitieren

APA

Su, L., Nie, J., Xie, Q., Li, S., & Zhang, Q. (2026). Interpretable machine learning model for predicting hemorrhage following ultrasound-guided percutaneous renal biopsy: a multicenter study. Abdominal Radiology, 51(12), 6409-6419. https://doi.org/10.1007/s00261-026-05582-2

Vancouver

Su L, Nie J, Xie Q, Li S, Zhang Q. Interpretable machine learning model for predicting hemorrhage following ultrasound-guided percutaneous renal biopsy: a multicenter study. Abdominal Radiology. 2026;51(12):6409-6419. doi:10.1007/s00261-026-05582-2

BibTeX
@article{Su2026,
  author = {Su, Liyang and Nie, Jinliang and Xie, Qiaojie and Li, Shilin and Zhang, Qingquan},
  title = {Interpretable machine learning model for predicting hemorrhage following ultrasound-guided percutaneous renal biopsy: a multicenter study},
  journal = {Abdominal Radiology},
  year = {2026},
  volume = {51},
  number = {12},
  pages = {6409--6419},
  doi = {10.1007/s00261-026-05582-2}
}
Kostenlos starten →