Safety and Clinical Effects of Switching From Intravenous to Oral Nimodipine Administration in Aneurysmal Subarachnoid Hemorrhage

Early prediction of ventricular peritoneal shunt dependency in aneurysmal subarachnoid haemorrhage patients by recurrent neural network-based machine learning using routine intensive care unit data

Aneurysmal subarachnoid haemorrhage (aSAH) can lead to complications such as acute hydrocephalic congestion. Treatment of this acute condition often includes establishing an external ventricular drainage (EVD). However, chronic hydrocephalus develops in some patients, who then require placement of a permanent ventriculoperitoneal (VP) shunt. The aim of this study was to employ recurrent neural network (RNN)-based machine learning techniques to identify patients who require VP shunt placement at an early stage. This retrospective single-centre study included all patients who were diagnosed with aSAH and treated in the intensive care unit (ICU) between November 2010 and May 2020 (n = 602). More than 120 parameters were analysed, including routine neurocritical care data, vital signs and blood gas analyses. Various machine learning techniques, including RNNs and gradient boosting machines, were evaluated for their ability to predict VP shunt dependency. VP-shunt dependency could be predicted using an RNN after just one day of ICU stay, with an AUC-ROC of 0.77 (CI: 0.75-0.79). The accuracy of the prediction improved after four days of observation (Day 4: AUC-ROC 0.81, CI: 0.79-0.84). At that point, the accuracy of the prediction was 76% (CI: 75.98-83.09%), with a sensitivity of 85% (CI: 83-88%) and a specificity of 74% (CI: 71-78%). RNN-based machine learning has the potential to predict VP shunt dependency on Day 4 after ictus in aSAH patients using routine data collected in the ICU. The use of machine learning may allow early identification of patients with specific therapeutic needs and accelerate the execution of required procedures.

Clinical effectiveness of nimodipine for the prevention of poor outcome after aneurysmal subarachnoid hemorrhage: A systematic review and meta-analysis

Objective

In clinical practice, nimodipine is used to control cerebral vasospasm (CVS), which is one of the major causes of severe disability and mortality in patients with aneurysmal subarachnoid hemorrhage (aSAH). However, the exact efficacy of nimodipine use for patients with aSAH is still controversial due to the lack of sufficient and up-to-date evidence.

Methods

In this meta-analysis, the latest databases of the Cochrane Central Register of Controlled Trials, PubMed-Medline, Web of Science, Embase, Scopus, and OVID-Medline were comprehensively searched for retrieving all randomized controlled trials (RCTs) regarding the efficacy of nimodipine in patients with aSAH. The primary outcome was a poor outcome, and the secondary outcomes were mortality and cerebral vasospasm (CVS). After detailed statistical analysis of different outcome variables, further evidence quality evaluation and recommendation grade assessment were carried out.

Results

Approximately 13 RCTs met the inclusion criteria, and a total of 1,727 patients were included. Meta-analysis showed that a poor outcome was significantly reduced in the nimodipine group [RR, 0.69 (0.60–0.78); I² = 29%]. Moreover, nimodipine also dramatically decreased the mortality [RR, 0.50 (0.32–0.78); I² = 62%] and the incidence of CVS [RR, 0.68 (0.46–0.99); I² = 57%]. Remarkably, we found a poor outcome and mortality were both significantly lower among patients with aSAH, with the mean age < 50 than that mean age ≥ 50 by subgroup analysis. Furthermore, the evidence grading of a poor outcome and its age subgroup in this study was assessed as high.

Conclusion

Nimodipine can significantly reduce the incidence of a poor outcome, mortality, and CVS in patients with aSAH. Moreover, we strongly recommend that patients with aSAH, especially those younger than 50 years old, should use nimodipine as early as possible in order to achieve a better clinical outcome, whether oral medication or endovascular direct medication.

Systematic review registration

www.york.ac.uk/inst/crd, identifier: CRD42022334619.