Development of Machine Learning-Based Predictor Algorithm for Conversion of an Ommaya Reservoir to a Permanent Cerebrospinal Fluid Shunt in Preterm Posthemorrhagic Hydrocephalus.

BACKGROUND: An Ommaya reservoir can be used to treat posthemorrhagic hydrocephalus secondary to intraventricular hemorrhage of prematurity until an acceptable weight can be obtained to place a permanent shunt. Identifying newborns at higher risk of developing shunt conversion may improve the management of these patients. This study aimed to develop a predictive algorithm for conversion of an Ommaya reservoir to a permanent shunt using artificial intelligence techniques and classical statistics. METHODS: A database of 43 preterm patients weighing ≤1500 g with posthemorrhagic hydrocephalus (Papile grades III and IV with Levene ventricular index >4 mm above the 97th percentile) managed with an Ommaya reservoir at our institution between 2002 and 2017 was used to train a k-nearest neighbor algorithm. Validation of results was done with cross-validation technique. Three scenarios were calculated: 1) considering all features regardless whether or not they are correlated with the output variable; 2) considering the features as predictors if they have a correlation >30% with the output variable; 3) considering the output of the previous analysis. RESULTS: When considering the outputs of a previous multivariate analysis, the algorithm reached 86% of cross-validation accuracy. CONCLUSIONS: The use of machine learning-based algorithms can help in early identification of patients with permanent need of a shunt. We present a predictive algorithm for a permanent shunt with an accuracy of 86%; accuracy of the algorithm can be improved with larger volume of data and previous analysis.

Volumetric Study of Nonfunctioning Pituitary Adenomas: Predictors of Gross Total Resection.

OBJECTIVE: Despite the efforts made to determine the achieved resection grade after pituitary adenoma surgery, there is a high level of disagreement among all the available classifications and measurement methods used. Our objective is to identify the factors that preoperatively could predict a gross total resection (GTR) of a clinically nonfunctioning pituitary adenoma through an endoscopic endonasal approach. METHODS: Across 100 surgeries, we analyzed epidemiologic and clinical data, radiologic relevant data, extent of resection (EOR), and postoperative outcomes. The EOR was measured objectively through an accurate volumetric analysis. RESULTS: The median presurgical volume was 8.58 cm3 (range, 0.5-58 cm3), the median maximum diameter was 27.3 mm (range, 7-67 mm), and the Knosp grade was 0 in 1 patient, 1 in 23%, 2 in 31%, 3 in 23% and 4 in 22% of patients. In the multivariate logistic regression analysis, we found 3 factors that significantly predicted the chances of a successful GTR: previous sellar surgery, Knosp grade, and tumor signal in the T2-weighted magnetic resonance imaging scan. Another 10 radiologic variables were analyzed and had no effect on the EOR. CONCLUSIONS: Knosp grade (P < 0.001; odds ratio [OR], 25.65; 95% confidence interval, 7.19-91.52) is the most predictive factor for performing a GTR of nonfunctioning pituitary adenoma. Previous pituitary surgery (P = 0.023; OR, 5.81) and an isointense T2-weighted signal (P = 0.034; OR, 3.75) also negatively influenced the chances of GTR. We highlight the influence of T2-weighted signal in the chances of GTR.

Free Mucosal Graft for Reconstruction after Nonfunctional Pituitary Adenoma Surgery.

BACKGROUND: In the search for an effective closure without nasosinusal morbidity, we have studied the efficacy of free mucosal graft as a reconstructive technique of the sellar floor after the resection of nonfunctioning pituitary adenomas (NFPA). METHODS: In 100 endonasal endoscopic surgeries, we analyzed the personal history, radiological and intraoperative aspects that could have an impact on the risk of postoperative cerebrospinal fluid (CSF) leak. They were divided into three groups: no mucosa flap/graft, mucosal free graft, and nasoseptal pedicled flap. RESULTS: The characteristics of the patients and adenomas were the same in all three groups. Intraoperative CSF leak was observed in 1/13 cases of the group without graft/flap (7%), in 16/50 of the free mucosal graft (32%) and 12/37 (32%) of pedicle flap. The proportion of cases in which other means of reconstruction were used in addition (fat, collagen matrix, and sealant) was similar in the different groups. No CSF leaks were observed, except for a doubtful one in the free mucosal graft group, which resolved spontaneously within 24 h, without receiving any type of treatment. CONCLUSIONS: The middle turbinate free mucosal graft can be of great value in endonasal surgery: It achieves a hermetic closure in cases of low-flow CSF leaks, it can be useful as a rescue for cases where nasoseptal mucosa is not available to perform a pedicled nasoseptal flap, minimizes the nasosinusal complications of the pedicled flap by leaving a smaller surface area of the nasal cavity devoid of the mucosa, and achieves greater nasosinusal functionality because proper reepithelialization occurs in the area.

Assessment of Overall Survival in Glioma Patients as Predicted by Metabolomic Criteria.

Objective: We assess the efficacy of the metabolomic profile from glioma biopsies in providing estimates of postsurgical Overall Survival in glioma patients. Methods: Tumor biopsies from 46 patients bearing gliomas, obtained neurosurgically in the period 1992-1998, were analyzed by high resolution 1H magnetic resonance spectroscopy (HR- 1H MRS), following retrospectively individual postsurgical Overall Survival up to 720 weeks. Results: The Overall Survival profile could be resolved in three groups; Short (shorter than 52 weeks, n = 19), Intermediate (between 53 and 364 weeks, n = 19) or Long (longer than 365 weeks, n = 8), respectively. Classical histopathological analysis assigned WHO grades II-IV to every biopsy but notably, some patients with low grade glioma depicted unexpectedly Short Overall Survival, while some patients with high grade glioma, presented unpredictably Long Overall Survival. To explore the reasons underlying these different responses, we analyzed HR-1H MRS spectra from acid extracts of the same biopsies, to characterize the metabolite patterns associated to OS predictions. Poor prognosis was found in biopsies with higher contents of alanine, acetate, glutamate, total choline, phosphorylcholine, and glycine, while more favorable prognosis was achieved in biopsies with larger contents of total creatine, glycerol-phosphorylcholine, and myo-inositol. We then implemented a multivariate analysis to identify hierarchically the influence of metabolomic biomarkers on OS predictions, using a Classification Regression Tree (CRT) approach. The CRT based in metabolomic biomarkers grew up to three branches and split into eight nodes, predicting correctly the outcome of 94.7% of the patients in the Short Overall Survival group, 78.9% of the patients in the Intermediate Overall Survival group, and 75% of the patients in the Long Overall Survival group, respectively. Conclusion: Present results indicate that metabolic profiling by HR-1H MRS improves the Overall Survival predictions derived exclusively from classical histopathological gradings, thus favoring more precise therapeutic decisions.