Development and Validation of Nomogram to Preoperatively Predict Intraoperative Cerebrospinal Fluid Leakage in Endoscopic Pituitary Surgery: A Retrospective Cohort Study

Clinical Application of Artificial Intelligence in Prediction of Intraoperative Cerebrospinal Fluid Leakage in Pituitary Surgery: A Systematic Review and Meta-Analysis

BACKGROUND

Postoperative cerebrospinal fluid (CSF) leakage is the leading adverse event in transsphenoidal surgery. Intraoperative CSF (ioCSF) leakage is one of the most important predictive factors for postoperative CSF leakage. This systematic review and meta-analysis aimed to evaluate the effectiveness of artificial intelligence (AI) models in predicting ioCSF.

METHODS

Literature records were retrieved on June 13, 2024, using the relevant key terms without filters in PubMed, Embase, Scopus, and Web of Science. Records were screened according to the eligibility criteria, and the data from the included studies were extracted. The quality assessment was performed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. The meta-analysis, sensitivity analysis, and meta-regression were conducted using R software.

RESULTS

Our results demonstrate that the AI models achieved a pooled sensitivity of 93.4% (95% confidence interval [CI]: 74.8%-98.6%) and specificity of 91.7% (95% CI: 75%-97.6%). The subgroup analysis revealed that the pooled sensitivities in machine learning and deep learning were 86.2% (95% CI: 83%-88.8%) and 99% (95% CI: 93%-99%), respectively (P < 0.01). The subgroup analysis demonstrated a pooled specificity of 92.1% (95% CI: 63.1%-98.7%) for machine learning and 90.6% (95% CI: 78.2%-96.3%) for deep learning models (P = 0.87). The diagnostic odds ratio meta-analysis revealed an odds ratio 114.6 (95% CI: 17.6-750.9). The summary receiver operating characteristic curve demonstrated that the overall area under the curve of the studies was 0.955, which is a considerable performance.

CONCLUSIONS

AI models have demonstrated promising performance for predicting the ioCSF leakage in pituitary surgery and can optimize the treatment strategy.

Preoperatively Predicting Ki67 Expression in Pituitary Adenomas Using Deep Segmentation Network and Radiomics Analysis Based on Multiparameter MRI

RATIONALE AND OBJECTIVES

Ki67 proliferation index is associated with more aggressive tumor behavior and recurrence of pituitary adenomas (PAs). Recently, radiomics and deep learning have been introduced into the study of pituitary tumors. The present study aimed to investigate the feasibility of predicting the Ki67 proliferation index of PAs using the deep segmentation network and radiomics analysis based on multiparameter MRI.

MATERIALS AND METHODS

First, the cfVB-Net autosegmentation model was trained; subsequently, its performance was evaluated in terms of the dice similarity coefficient (DSC). In the present study, 1214 patients were classified into the high Ki67 expression group (HG) and the low Ki67 expression group (LG). Analyses of three classification models based on radiomics features were performed to distinguish HG from LG. Clinical factors, imaging features, and Radscores were collectively used to create a nomogram in order to effectively predict Ki67 expression.

RESULTS

The cfVB-Net segmentation model demonstrated good performance (DSC: 0.723-0.930). Overall, 18, 15, and 11 optimal features in contrast-enhanced (CE) T1WI, T1WI, and T2WI were obtained for differentiating between HG and LG, respectively. Notably, the best results were presented in the bagging decision tree when CE T1WI and T1WI were combined (area under the receiver operating characteristic curve: training set, 0.927; validation set, 0.831; and independent testing set, 0.825). In the nomogram, age, Hardy' grade, and Radscores were identified as risk predictors of high Ki67 expression.

CONCLUSION

The deep segmentation network and radiomics analysis based on multiparameter MRI exhibited good performance and clinical application value in predicting the expression of Ki67 in PAs.

Risk factors of cerebrospinal fluid leakage after neuroendoscopic transsphenoidal pituitary adenoma resection: a systematic review and meta-analysis

Introduction

Cerebro spinal fluid (CSF) leakage is common and might lead to severe postoperative complications after endoscopic transsphenoidal pituitary adenoma resection. However, the risk factors of postoperative CSF leakage are still controversial. This article presents a systematic review to explore the explicit risk factors of CSF leakage after endoscopic transsphenoidal pituitary adenomere section.

Methods

PRISMA and AMSTAR guidelines were followed to assess the methodological quality of the systematic review. PubMed, Medline, Embase, Web of Science, Cochrane, Clinical Trails, CNKI, CBM, Wan Fang, and VIP databases were searched for all studies on postoperative CSF leak risk factors. The quality of the included studies was assessed by the Newcastle-Ottawa scale. Review Manager 5.4 software was used to calculate the pooled effect size of potential factors with statistical significance.

Results

A total of 6775 patients with pituitary adenoma across 18 articles were included, containing 482 cases of postoperative CSF leakage (accounting for 7.11%). All of the articles had a quality score > 5, indicating good quality. Meta-analysis showed that an increased risk of CSF leak was found for higher levels of BMI (MD=1.91, 95% CI (0.86,2.96), bigger tumor size [OR=4.93, 95% CI (1.41,17.26)], greater tumor invasion (OR=3.01, 95% CI (1.71, 5.31), the harder texture of tumor [OR=2.65, 95% CI (1.95,3.62)], intraoperative cerebrospinal fluid leakage [OR=5.61, 95% CI (3.53,8.90)], multiple operations [OR=2.27, 95% CI (1.60,3.23)].

Conclusion

BMI, multiple operations, tumor size, tumor invasion, hard texture, and intraoperative cerebrospinal fluid leakage are the risk factors of postoperative CSF leakage. Clinical doctors should pay attention to these risk factors, and conduct strict skull base reconstruction and careful postoperative management.

Machine learning driven prediction of cerebrospinal fluid rhinorrhoea following endonasal skull base surgery: A multicentre prospective observational study

Background

Cerebrospinal fluid rhinorrhoea (CSFR) is a common complication following endonasal skull base surgery, a technique that is fundamental to the treatment of pituitary adenomas and many other skull base tumours. The CRANIAL study explored CSFR incidence and related risk factors, particularly skull base repair techniques, via a multicentre prospective observational study. We sought to use machine learning to leverage this complex multicentre dataset for CSFR prediction and risk factor analysis.

Methods

A dataset of 865 cases - 725 transsphenoidal approach (TSA) and 140 expanded endonasal approach (EEA) - with cerebrospinal fluid rhinorrhoea as the primary outcome, was used. Relevant variables were extracted from the data, and prediction variables were divided into two categories, preoperative risk factors; and repair techniques, with 6 and 11 variables respectively. Three types of machine learning models were developed in order to predict CSFR: logistic regression (LR); decision tree (DT); and neural network (NN). Models were validated using 5-fold cross-validation, compared via their area under the curve (AUC) evaluation metric, and key prediction variables were identified using their Shapley additive explanations (SHAP) score.

Results

CSFR rates were 3.9% (28/725) for the transsphenoidal approach and 7.1% (10/140) for the expanded endonasal approach. NNs outperformed LR and DT for CSFR prediction, with a mean AUC of 0.80 (0.70-0.90) for TSA and 0.78 (0.60-0.96) for EEA, when all risk factor and intraoperative repair data were integrated into the model. The presence of intraoperative CSF leak was the most prominent risk factor for CSFR. Elevated BMI and revision surgery were also associated with CSFR for the transsphenoidal approach. CSF diversion and gasket sealing appear to be strong predictors of the absence of CSFR for both approaches.

Conclusion

Neural networks are effective at predicting CSFR and uncovering key CSFR predictors in patients following endonasal skull base surgery, outperforming traditional statistical methods. These models will be improved further with larger and more granular datasets, improved NN architecture, and external validation. In the future, such predictive models could be used to assist surgical decision-making and support more individualised patient counselling.