Neurocritical care
-
Big data (BD) and artificial intelligence (AI) have increasingly been used in neurocritical care. "BD" can be operationally defined as extremely large datasets that are so large and complex that they cannot be analyzed by using traditional statistical modeling. "AI" means the ability of machines to perform tasks similar to those performed by human intelligence. We present a brief overview of the most commonly applied AI techniques to perform BD analytics and discuss some of the recent promising examples in the field of neurocritical care. The latter include the following: cognitive motor dissociation in disorders of consciousness, hypoxic-ischemic injury following cardiac arrest, delayed cerebral ischemia and vasospasm after subarachnoid hemorrhage, and monitoring of intracranial pressure. ⋯ These collaborations will allow us to share data, combine predictive algorithms, and analyze multiple and cumulative sources of data retrospectively and prospectively. Once AI algorithms are validated at multiple centers, they should be tested in randomized controlled trials investigating their impact on clinical outcome. The neurocritical care community must work to ensure that AI incorporates standards to ensure fairness and health equity rather than reflect our biases present in our collective conscience.
-
Hyperventilation resulting in hypocapnic alkalosis (HA) is frequently encountered in spontaneously breathing patients with acute cerebrovascular conditions. The underlying mechanisms of this respiratory response have not been fully elucidated. The present study describes, applying the physical-chemical approach, the acid-base characteristics of cerebrospinal fluid (CSF) and arterial plasma of spontaneously breathing patients with aneurismal subarachnoid hemorrhage (SAH) and compares these results with those of control patients. Moreover, it investigates the pathophysiologic mechanisms leading to HA in SAH. ⋯ Patients with SAH have a reduction of CSF SID due to an increased lactate concentration. The resulting localized acidifying effect is compensated by CSF hypocapnia, yielding normal CSF pH values and resulting in a higher incidence of arterial HA.
-
Delayed cerebral ischemia increases mortality and morbidity after aneurysmal subarachnoid hemorrhage (aSAH). Various techniques are applied to detect cerebral vasospasm and hypoperfusion. Contrast-enhanced ultrasound perfusion imaging (UPI) is able to detect cerebral hypoperfusion in acute ischemic stroke. This prospective study aimed to evaluate the use of UPI to enable detection of cerebral hypoperfusion after aSAH. ⋯ UPI is feasible to enable detection of cerebral tissue hypoperfusion after aSAH, and the left-right difference of TTP values is the most indicative result of this finding.
-
Sex-related differences in patients with spontaneous, non-traumatic intracerebral hemorrhage (ICH) are poorly investigated so far. This study elucidates whether sex-related differences in ICH care in a neurocritical care setting exist, particularly regarding provided care, while also taking patient characteristics, and outcomes into account. ⋯ Sex-related differences in patients with ICH regarding to provided neurosurgical care exist. We provide evidence that insertion of EVD is associated with male sex, disregarding clear reasoning. A sex-bias as well as social factors may play a significant role in decision-making for the insertion of an EVD.
-
Dysfunctional cerebral autoregulation often precedes delayed cerebral ischemia (DCI). Currently, there are no data-driven techniques that leverage this information to predict DCI in real time. Our hypothesis is that information using continuous updated analyses of multimodal neuromonitoring and cerebral autoregulation can be deployed to predict DCI. ⋯ A TTSAM algorithm using multimodal neuromonitoring and cerebral autoregulation calculations shows promise to classify DCI in real time.