Construction of a Predictive Model for Cerebrospinal Fluid Leakage After Endoscopic Transsphenoidal Pituitary Tumor Surgery Based on Machine Learning Algorithm
Journal of Neurological Surgery Part B: Skull Base · 2026-12 · 87 (06) · 669-677
DOI: 10.1055/a-2775-5314 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neurological Surgery Part B: Skull Base, online erschienen am 06.01.2026. Verfasst von Shirong Shao und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurosurgery, Deyang People's Hospital, DeyangChina. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Medical Science and Technology Program of the Sichuan Provincial Health and Health Commission of the Sichuan Provincial Health.
Abstract (Originalsprache)
To develop ML models predicting postoperative CSF leakage after endoscopic transsphenoidal pituitary adenectomy (TSPA). Four hundred and twenty patients from five hospitals (January 2021–December 2022) comprised the training cohort; 140 from another hospital were the validation cohort. The training cohort included 60 CSF leak and 360 nonleak cases. Risk factors were analyzed. Decision tree, logistic regression, and SMOTE-based models were built and their diagnostic value compared. Significant differences (p < 0.05) existed in tumor diameter, tumor texture, operative time, intraoperative diaphragma sellae rupture, reoperation, and intraoperative CSF leakage grade. Logistic regression identified tumor texture, reoperation, intraoperative CSF leakage grade, and diaphragma sellae rupture as risk factors. All models had high AUCs in training: logistic regression (0.792), decision tree (0.835), and SMOTE (0.839). The Delong test showed a decision tree, and SMOTE outperformed logistic regression. SMOTE had the highest sensitivity/specificity. Validation cohort AUCs were: logistic regression (0.775), decision tree (0.809), and SMOTE (0.831), with SMOTE superior. Calibration curves indicated good agreement between predicted and actual values. Prediction models for CSF leakage postendoscopic TSPA were developed using decision trees, SMOTE, and logistic regression. Model efficacy was evaluated via AUC, specificity, and sensitivity. Comparing algorithms reduced single-algorithm bias, with SMOTE demonstrating the best performance.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurosurgery, Deyang People's Hospital, DeyangChina.
- Department of Neurosurgery, The First Affiliated Hospital of Chengdu Medical College, ChengduChina.
- Department of General Practice, Sichuan Provincial People's Hospital, Chengdu, SichuanChina.
- Neurology Department, Affiliated Hospital of Chengdu University, Chengdu, SichuanChina.
- Department of Neurosurgery, Sichuan Cancer Hospital, Chengdu, SichuanChina.
Förderung
- Medical Science and Technology Program of the Sichuan Provincial Health and Health Commission of the Sichuan Provincial Health
Zitieren
APA
Shao, S., Ye, C., Du, Y., Liu, T., Wu, Y., Chen, M., & Wu, J. (2026). Construction of a Predictive Model for Cerebrospinal Fluid Leakage After Endoscopic Transsphenoidal Pituitary Tumor Surgery Based on Machine Learning Algorithm. Journal of Neurological Surgery Part B: Skull Base, 87(06), 669-677. https://doi.org/10.1055/a-2775-5314
Vancouver
Shao S, Ye C, Du Y, Liu T, Wu Y, Chen M, et al. Construction of a Predictive Model for Cerebrospinal Fluid Leakage After Endoscopic Transsphenoidal Pituitary Tumor Surgery Based on Machine Learning Algorithm. Journal of Neurological Surgery Part B: Skull Base. 2026;87(06):669-677. doi:10.1055/a-2775-5314
BibTeX
@article{Shao2026,
author = {Shao, Shirong and Ye, Changqing and Du, Yuyang and Liu, Tianheng and Wu, Yunjun and Chen, Min and Wu, Jijun},
title = {Construction of a Predictive Model for Cerebrospinal Fluid Leakage After Endoscopic Transsphenoidal Pituitary Tumor Surgery Based on Machine Learning Algorithm},
journal = {Journal of Neurological Surgery Part B: Skull Base},
year = {2026},
volume = {87},
number = {06},
pages = {669--677},
doi = {10.1055/a-2775-5314}
}
EUVIMED