Download PDF
J Neurol Surg B Skull Base
DOI: 10.1055/a-2775-5314
Original Article

Construction of a Predictive Model for Cerebrospinal Fluid Leakage After Endoscopic Transsphenoidal Pituitary Tumor Surgery Based on Machine Learning Algorithm

Authors

  • Shirong Shao

    1   Department of Neurosurgery, Deyang People's Hospital, Deyang, China

  • Changqing Ye

    2   Department of Neurosurgery, The First Affiliated Hospital of Chengdu Medical College, Chengdu, China

  • Yuyang Du

    3   Department of General Practice, Sichuan Provincial People's Hospital, Chengdu, Sichuan, China

  • Tianheng Liu

    4   Neurology Department, Affiliated Hospital of Chengdu University, Chengdu, Sichuan, China

  • Yunjun Wu

    5   Department of Neurosurgery, Sichuan Cancer Hospital, Chengdu, Sichuan, China

  • Min Chen

    1   Department of Neurosurgery, Deyang People's Hospital, Deyang, China

  • Jijun Wu

    1   Department of Neurosurgery, Deyang People's Hospital, Deyang, China

Funding Information This study was supported by the Medical Science and Technology Program of the Sichuan Provincial Health and Health Commission of the Sichuan Provincial Health (21PJ171).
Further Information
Also available at
   Permissions and Reprints

Abstract

Objective

To develop ML models predicting postoperative CSF leakage after endoscopic transsphenoidal pituitary adenectomy (TSPA).

Methods

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.

Results

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.

Conclusion

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.

Keywords

machine learning algorithm - endoscopic transsphenoidal pituitary tumor surgery - postoperative cerebrospinal fluid leak - predictive modeling

Data Availability Statement

All data generated or analyzed during this study are included in this published article.


Ethical Approval and Consent to Participate

The study was approved by the Medical Ethics Membership of Deyang People's Hospital (2021-04-059-K01).


Informed Consent

All participants were informed about the study protocol and provided written informed consent to participate in the study. I confirm that all methods were performed in accordance with the relevant guidelines. All procedures were performed in accordance with the ethical standards laid down in the 1964 Declaration of Helsinki and its later amendments.




Publication History

Received: 01 August 2025

Accepted: 16 December 2025

Accepted Manuscript online:
22 December 2025

Article published online:
06 January 2026

© 2026. Thieme. All rights reserved.

Georg Thieme Verlag KG
Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany