A supervised machine-learning algorithm predicts intraoperative CSF leak in endoscopic transsphenoidal surgery for pituitary adenomas.

BACKGROUND: Despite advances in endoscopic transnasal transsphenoidal surgery (E-TNS) for pituitary adenomas (PAs), cerebrospinal fluid (CSF) leakage remains a life-threatening complication predisposing to major morbidity and mortality. In the current study we developed a supervised ML model able to predict the risk of intraoperative CSF leakage by comparing different machine learning (ML) methods and explaining the functioning and the rationale of the best performing algorithm. METHODS: A retrospective cohort of 238 patients treated via E-TNS for PAs was selected. A customized pipeline of several ML models was programmed and trained; the best five models were tested on a hold-out test and the best classifier was then prospectively validated on a cohort of 35 recently treated patients. RESULTS: Intraoperative CSF leak occurred in 54 (22,6%) of 238 patients. The most important risk's predictors were: non secreting status, older age, x-, y- and z-axes diameters, ostedural invasiveness, volume, ICD and R-ratio. The random forest (RF) classifier outperformed other models, with an AUC of 0.84, high sensitivity (86%) and specificity (88%). Positive predictive value and negative predictive value were 88% and 80% respectively. F1 score was 0.84. Prospective validation confirmed outstanding performance metrics: AUC (0.81), sensitivity (83%), specificity (79%), negative predictive value (95%) and F1 score (0.75). CONCLUSIONS: The RF classifier showed the best performance across all models selected. RF models might predict surgical outcomes in heterogeneous multimorbid and fragile populations outperforming classical statistical analyses and other ML models (SVM, ANN etc.), improving patient management and reducing preventable morbidity and additional costs.

Interpretable Machine Learning-Based Prediction of Intraoperative Cerebrospinal Fluid Leakage in Endoscopic Transsphenoidal Pituitary Surgery: A Pilot Study.

Purpose Transsphenoidal surgery (TSS) for pituitary adenomas can be complicated by the occurrence of intraoperative cerebrospinal fluid (CSF) leakage (IOL). IOL significantly affects the course of surgery predisposing to the development of postoperative CSF leakage, a major source of morbidity and mortality in the postoperative period. The authors trained and internally validated the Random Forest (RF) prediction model to preoperatively identify patients at high risk for IOL. A locally interpretable model-agnostic explanations (LIME) algorithm is employed to elucidate the main drivers behind each machine learning (ML) model prediction. Methods The data of 210 patients who underwent TSS were collected; first, risk factors for IOL were identified via conventional statistical methods (multivariable logistic regression). Then, the authors trained, optimized, and audited a RF prediction model. Results IOL reported in 45 patients (21.5%). The recursive feature selection algorithm identified the following variables as the most significant determinants of IOL: Knosp's grade, sellar Hardy's grade, suprasellar Hardy's grade, tumor diameter (on X, Y, and Z axes), intercarotid distance, and secreting status (nonfunctioning and growth hormone [GH] secreting). Leveraging the predictive values of these variables, the RF prediction model achieved an area under the curve (AUC) of 0.83 (95% confidence interval [CI]: 0.78; 0.86), significantly outperforming the multivariable logistic regression model (AUC = 0.63). Conclusion A RF model that reliably identifies patients at risk for IOL was successfully trained and internally validated. ML-based prediction models can predict events that were previously judged nearly unpredictable; their deployment in clinical practice may result in improved patient care and reduced postoperative morbidity and healthcare costs.

Molecular Analysis in a Glioblastoma Cohort-Results of a Prospective Analysis.

The prognostic role of epidermal growth factor receptor variant III (EGFRvIII), a constitutively activated oncogenic receptor, in glioblastoma is controversial. We performed a prospective study enrolling 355 patients operated on for de novo glioblastoma at a large academic center. The molecular profile, including EGFRvIII status, MGMT promoter methylation, and VEGF expression, was assessed. Standard parameters (age, clinical status and extent of surgical resection) were confirmed to hold prognostic value. MGMT promoter methylation portended a slightly improved survival. In the whole series, confirming previous results, EGFRvIII was not associated with worsened prognosis. Interestingly, female sex was associated with a better outcome. Such findings are of interest for the design of future trials.

A Deep Learning Model for Preoperative Differentiation of Glioblastoma, Brain Metastasis and Primary Central Nervous System Lymphoma: A Pilot Study.

Background: Neuroimaging differentiation of glioblastoma, primary central nervous system lymphoma (PCNSL) and solitary brain metastasis (BM) remains challenging in specific cases showing similar appearances or atypical features. Overall, advanced MRI protocols have high diagnostic reliability, but their limited worldwide availability, coupled with the overlapping of specific neuroimaging features among tumor subgroups, represent significant drawbacks and entail disparities in the planning and management of these oncological patients. Objective: To evaluate the classification performance metrics of a deep learning algorithm trained on T1-weighted gadolinium-enhanced (T1Gd) MRI scans of glioblastomas, atypical PCNSLs and BMs. Materials and Methods: We enrolled 121 patients (glioblastoma: n=47; PCNSL: n=37; BM: n=37) who had undergone preoperative T1Gd-MRI and histopathological confirmation. Each lesion was segmented, and all ROIs were exported in a DICOM dataset. The patient cohort was then split in a training and hold-out test sets following a 70/30 ratio. A Resnet101 model, a deep neural network (DNN), was trained on the training set and validated on the hold-out test set to differentiate glioblastomas, PCNSLs and BMs on T1Gd-MRI scans. Results: The DNN achieved optimal classification performance in distinguishing PCNSLs (AUC: 0.98; 95%CI: 0.95 - 1.00) and glioblastomas (AUC: 0.90; 95%CI: 0.81 - 0.97) and moderate ability in differentiating BMs (AUC: 0.81; 95%CI: 0.70 - 0.95). This performance may allow clinicians to correctly identify patients eligible for lesion biopsy or surgical resection. Conclusion: We trained and internally validated a deep learning model able to reliably differentiate ambiguous cases of PCNSLs, glioblastoma and BMs by means of T1Gd-MRI. The proposed predictive model may provide a low-cost, easily-accessible and high-speed decision-making support for eligibility to diagnostic brain biopsy or maximal tumor resection in atypical cases.

Artificial intelligence-enhanced intraoperative neurosurgical workflow: current knowledge and future perspectives.

INTRODUCTION: Artificial intelligence (AI) and machine learning (ML) augment decision-making processes and productivity by supporting surgeons over a range of clinical activities: from diagnosis and preoperative planning to intraoperative surgical assistance. We reviewed the literature to identify current AI platforms applied to neurosurgical perioperative and intraoperative settings and describe their role in multiple subspecialties. EVIDENCE ACQUISITION: A systematic review of the literature was conducted following the PRISMA guidelines. PubMed, EMBASE, and Scopus databases were searched from inception to December 31st, 2020. Original articles were included if they: presented AI platforms implemented in perioperative, intraoperative settings and reported ML models' performance metrics. Due to the heterogeneity in neurosurgical applications, a qualitative synthesis was deemed appropriate. The risk of bias and applicability of predicted outcomes were assessed using the PROBAST tool. EVIDENCE SYNTHESIS: Forty-one articles were included. All studies evaluated a supervised learning algorithm. A total of 10 ML models were described; the most frequent were neural networks (N.=15) and tree-based models (N.=13). Overall, the risk of bias was medium-high, but applicability was considered positive for all studies. Articles were grouped into four categories according to the subspecialty of interest: neuro-oncology, spine, functional and other. For each category, different prediction tasks were identified. CONCLUSIONS: In this review, we summarize the state-of-art applications of AI for the intraoperative augmentation of neurosurgical workflows across multiple subspecialties. ML models may boost surgical team performances by reducing human errors and providing patient-tailored surgical plans, but further and higher-quality studies need to be conducted.

A systematic review and meta-analysis of factors affecting the outcome of the epidural blood patching in spontaneous intracranial hypotension.

Spontaneous intracranial hypotension (SIH) is an often misdiagnosed condition resulting from non-iatrogenic cerebrospinal fluid (CSF) hypovolemia, typically secondary to spinal CSF leakage. Patients commonly present with posture-related headache, nausea, and vomiting. Following failure of conservative measures, epidural blood patching (EBP) is the most commonly performed intervention for spinal CSF leaks. The authors performed a systematic review and meta-analysis of existing literature to evaluate the role of different factors possibly affecting the efficacy of the EBP procedure. In accordance with the PRISMA guidelines, PubMed/Medline and SCOPUS databases were searched. Six eligible articles were retrieved. Five hundred patients were treated for SIH with EBP, of which 300 reported good response defined as complete remission of symptoms within 48 h after the first EBP requiring no further invasive treatment. Among the factors available for meta-analysis, none was found to be statistically significant in affecting the efficacy of the EBP procedure. A largely symmetrical funnel plot is reported for all the variables evaluated, indicating that publication bias did not play a significant role in the observed effects. The current knowledge about SIH and the EBP is scarce. The existing literature is contradictory and insufficient to aid in clinical practice. More studies are needed to draw significant conclusions that may help in the identification of patients at higher risk of EBP failure, who may benefit from different approaches.