Search

Objective: Ability to thrive after invasive and intensive treatment is an important parameter to assess in patients with glioblastoma multiforme (GBM). Karnofsky Performance Status (KPS) is used to identify those patients suitable for postoperative radiochemotherapy. The aim of the present study is to investigate whether machine learning (ML)-based models can reliably predict patients' KPS 6 months after surgery. Methods: A cohort of 416 patients undergoing surgery for a histopathologically confirmed GBM were collected from a multicentric database and split into a training and hold-out test set in an 80:20 ratio. Worsening of KPS at 6 months after surgery (compared with preoperative KPS) occurred in 138 patients (33.2%). Relevant preoperative, intraoperative, and immediately postoperative variables were selected by a recursive features selection algorithm (Boruta) and used to build 2 ML-based predictive models. Results: A random forest classifier and a random forest regressor were trained to predict 6 months postoperative KPS as a categorical (worsening vs. stable/improving) and continuous variables; they achieved, respectively, an area under the curve of 0.81 (95% confidence interval, 0.76-0.84) and a mean absolute error of 4.4 (95% confidence interval, 4.0-4.7). Leveraging the predictive value resulting from the combination of independent variables, the random forest classifier outperformed conventional statistics (area under the curve improvement of +21%). Conclusions: Two robust ML-based prediction models were successfully trained and internally validated. Considerable effort remains to improve the interpretation of the results when these predictions are used in a patient-centered care context.

Background: Trans-sphenoidal endoscopic surgery has drawn huge benefits from advances in surgical visualization. The Ultra-HD "4K" endoscope has improved 4-fold image resolution compared with HD, but its actual advantages are unclear. Aim of the present study was to assess its usefulness in the early outcome of trans-sphenoidal surgery. Methods: We analyzed a series of 199 trans-sphenoidal pituitary adenoma procedures performed by an experienced team using alternatively HD (n=102) or 4K (n=97) endoscopes. We evaluated extent of resection both subjectively, based on intraoperative surgeon's impression, and objectively based on post-operative MR scan. Results: Baseline patients' characteristics were balanced. Objective near-total and total resection rates were comparable between 4K and HD groups (91.5% vs 86.3% and 64.9% vs 56.9%, respectively). 4K endoscope slightly improved resection rate in recurrent adenoma. At multivariate analysis, the only independent prognosticator of total resection was cavernous sinus invasion. Importantly, 4K endoscope enhanced the reliability of intraoperative judgement on extent of resection, significantly reducing unexpected residuals (12.8% vs 33.3% for HD). Operative features and clinical outcomes were similar. Conclusions: The HD endoscope remains the standard-of-care for pituitary surgery. The 4K enhanced, "immersive" visualization significantly improved the reliability of surgeon's judgment on resection and might be useful in surgically difficult cases.