EUVIMEDEUVIMED entdecken
Crossref

A multiregional multimodal machine learning model for predicting outcome of surgery for symptomatic hemorrhagic brainstem cavernous malformations

Xuchen Dong, Haohuai Gui, Kai Quan, Zongze Li, Ying Xiao, Jiaxi Zhou, Yuchuan Zhao, Dongdong Wang, Mingjian Liu, Haojing Duan, Shaoxuan Yang, Xiaolei Lin und 4 weitere

Neurosurgical Focus · 2025

DOI: 10.3171/2025.4.focus24778 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neurosurgical Focus, 2025. Verfasst von Xuchen Dong und 15 weiteren Autor:innen. Beteiligte Einrichtung: 1Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai. Hauptthemen laut MEDLINE: Machine Learning, Hemangioma, Cavernous, Central Nervous System, Brain Stem Neoplasms, Brain Stem. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 26 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE Given that resection of brainstem cavernous malformations (BSCMs) ends hemorrhaging but carries a high risk of neurological deficits, it is necessary to develop and validate a model predicting surgical outcomes. This study aimed to construct a BSCM surgery outcome prediction model based on clinical characteristics and T2-weighted MRI-based radiomics. METHODS Two separate cohorts of patients undergoing BSCM resection were included as discovery and validation sets. Patient characteristics and imaging data were analyzed. An unfavorable outcome was defined as a modified Rankin Scale score > 2 at the 12-month follow-up. Image features were extracted from regions of interest within lesions and adjacent brainstem. A nomogram was constructed using the risk score from the optimal model. RESULTS The discovery and validation sets comprised 218 and 49 patients, respectively (mean age 40 ± 14 years, 127 females); 63 patients in the discovery set and 35 in the validation set had an unfavorable outcome. The eXtreme Gradient Boosting imaging model with selected radiomics features achieved the best performance (area under the receiver operating characteristic curve [AUC] 0.82). Patients were stratified into high- and low-risk groups based on risk scores computed from this model (optimal cutoff 0.37). The final integrative multimodal prognostic model attained an AUC of 0.90, surpassing both the imaging and clinical models alone. CONCLUSIONS Inclusion of BSCM and brainstem subregion imaging data in machine learning models yielded significant predictive capability for unfavorable postoperative outcomes. The integration of specific clinical features enhanced prediction accuracy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningHemangioma, Cavernous, Central Nervous SystemBrain Stem NeoplasmsBrain StemNeurosurgical ProceduresHumansFemaleMaleAdultMiddle AgedTreatment OutcomeMagnetic Resonance ImagingCohort StudiesPredictive Value of TestsRetrospective StudiesYoung Adult

Stichwörter der Autor:innen

brainstem cavernous malformationsmachine learningradiomicssurgical outcome

Autor:innen und Institutionen

  • 1Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai.
  • 5Shanghai Clinical Medical Center of Neurosurgery, Shanghai.
  • 6School of Information Science and Technology, Fudan University, Shanghai.
  • 7Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention (MICCAI) of Shanghai.
  • 8Department of Radiology, Huashan Hospital, Fudan University, Shanghai.
  • 9Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai.

Zitieren

APA

Dong, X., Gui, H., Quan, K., Li, Z., Xiao, Y., Zhou, J., Zhao, Y., Wang, D., Liu, M., Duan, H., Yang, S., Lin, X., Dong, J., Wang, L., Ma, Y., & Zhu, W. (2025). A multiregional multimodal machine learning model for predicting outcome of surgery for symptomatic hemorrhagic brainstem cavernous malformations. Neurosurgical Focus. https://doi.org/10.3171/2025.4.focus24778

Vancouver

Dong X, Gui H, Quan K, Li Z, Xiao Y, Zhou J, et al. A multiregional multimodal machine learning model for predicting outcome of surgery for symptomatic hemorrhagic brainstem cavernous malformations. Neurosurgical Focus. 2025. doi:10.3171/2025.4.focus24778

BibTeX
@article{Dong2025,
  author = {Dong, Xuchen and Gui, Haohuai and Quan, Kai and Li, Zongze and Xiao, Ying and Zhou, Jiaxi and Zhao, Yuchuan and Wang, Dongdong and Liu, Mingjian and Duan, Haojing and Yang, Shaoxuan and Lin, Xiaolei and Dong, Jun and Wang, Lin and Ma, Yu and Zhu, Wei},
  title = {A multiregional multimodal machine learning model for predicting outcome of surgery for symptomatic hemorrhagic brainstem cavernous malformations},
  journal = {Neurosurgical Focus},
  year = {2025},
  doi = {10.3171/2025.4.focus24778}
}
Kostenlos starten →