Suchergebnisse

Background and Study Aims
Symptomatic cerebral vasospasms are deleterious complication of the rupture of a cerebral aneurysm and potentially lethal. The existing scales used to classify the initial presentation of a subarachnoid haemorrhage (SAH), offer a blink of the outcome and the possibility of occurrence of symptomatic cerebral vasospasms. Altogether, they are neither sufficient to predict outcome or occurrence of events reliably nor do they offer a unite front. This study tests the common grading scales and factors, that otherwise effect the outcome, in an artificial-intelligent based algorithm in order to create a reliable prediction model for the occurrence of cerebral vasospasms.

Material and Methods
Applying the R environment an easy to operate command line was programmed to prognosticate the occurrence of vasospasms. Eighty-seven patients with aneurysmal SAH during a 24 months-period of time were included for study purposes. The Holdout and the Cross-Validation methods were used to evaluate the algorithm (65 patients validation set. 22 patients test set). The Support Vector Machines (ksvm) classification method provided a high accuracy. The medical data set included demographic data, the Hunt & Hess scale, Fisher grade, BNI scale, length of intervention for aneurysmal repair, etc.

Results
Our prediction model based on the AI algorithm demonstrated an accuracy of 61%-86% for the event of symptomatic vasospasms. For the subgroup analysis, patients of the surgical cohort 28,8% (n=13) developed symptomatic vasospasm, whereas admitted with Fisher scale grade 4 50% (n=7), with H&H 5 37,5% (n=5) and 28,5% (n=4) with BNI 5. Respectively, in the endovascular cohort vasospasms occurred in 31,8% (n=14) patients, with Fisher grade 4 69% (n=9), H&H 5 23% (n=3) and 7% (n=1) with BNI 5.

Conclusion
From our data, we may believe that the algorithm presented can help in identifying patients with SAH being at 'high' or 'low risk' for the development of symptomatic vasospasms. This risk balancing might further allow the treating physician to go for an early intervention trying to prevent permanent sequelae. Certainly, accuracy will improve with a higher caseload and more statistical coefficients.

Abstract
Background We assess the impact of lockdown in Germany due to the COVID-19 pandemic on the incidence and outcome of neurotrauma emergencies at a tertiary medical center.
Methods All neurosurgical emergencies from March 16, 2020 (first lockdown in Germany) to January 31, 2021 were included and compared with a longitudinal case-cohort. Cases were descriptively recorded and retrospectively analyzed with respect to incidence and outcome.
Results All emergencies defined as polytrauma referred to our center decreased by 10% during the pandemic (n = 226), whereas neurosurgical emergencies increased by 18.4% (764 vs. 905 cases). The number of specific neurotrauma emergencies increased by 44.4% (63 vs. 91 cases), yet statistically not significant (p = 0.245). The duration of treatment in the intensive care unit (ICU) extended from 621 to 1,056 days (p = 0.34).
Conclusion The reasons for the increase in the number of neurotrauma emergencies were the following: (1) many surrounding smaller care providers were canceled during this time and (2) there was a lack of free intensive care capacities in other hospitals, urging primarily maximum care providers to deal with more referrals. Both these facts and the prolonged treatment on ICUs strengthen the necessity for maximum care providers to keep ICU capacities for non-COVID patients. Specialized neurosurgical expertise should maintain in tertiary medical centers, even or particularly in exceptional circumstances such as the current pandemic.