Neurocritical care
-
Seizures are a harmful complication of acute intracerebral hemorrhage (ICH). "Early" seizures in the first week after ICH are a risk factor for deterioration, later seizures, and herniation. Ideally, seizure medications after ICH would only be administered to patients with a high likelihood to have seizures. We developed and validated machine learning (ML) models to predict early seizures after ICH. ⋯ Early seizures after ICH are predictable. Models using cortical hematoma location, age less than 65 years, and hematoma volume greater than 10 mL had a good accuracy rate, and performance improved with more independent variables. Additional methods to predict seizures could improve patient selection for monitoring and prophylactic seizure medications.
-
Intracranial hemorrhage (ICH) is a frequent complication in patients with an implanted left ventricular assist device (LVAD) for advanced heart failure. Bloodstream infection is known to be associated with ICH in patients with LVAD, but its effects on ICH-associated mortality are unknown. We compared characteristics and mortality of infection-associated, traumatic, and spontaneous hemorrhages. ⋯ Although spontaneous ICH occurred earlier after LVAD implantation than infection-associated ICH, no difference in mortality was seen between the different causes of ICH.
-
Delayed cerebral ischemia (DCI), a complication of subarachnoid hemorrhage (SAH), is linked to cerebral vasospasm and associated with poor long-term outcome. We implemented a structured cerebral microdialysis (CMD) based protocol using the lactate/pyruvate ratio (LPR) as an indicator of the cerebral energy metabolic status in the neurocritical care decision making, using an LPR ≥ 30 as a cutoff suggesting an energy metabolic disturbance. We hypothesized that CMD monitoring could contribute to active, protocol-driven therapeutic interventions that may lead to the improved management of patients with SAH. ⋯ Active interventions were initiated in a majority of LPR events based on CMD monitoring. A low DCI incidence was observed, which may be associated with the active interventions. The potential aid of CMD in the clinical decision-making targeting DCI needs confirmation in additional SAH studies.
-
To compare three computer-assisted quantitative electroencephalography (EEG) prediction models for the outcome prediction of comatose patients after cardiac arrest regarding predictive performance and robustness to artifacts. ⋯ A deep learning model outperformed logistic regression and random forest models for reliable, robust, EEG-based outcome prediction of comatose patients after cardiac arrest.
-
We evaluated the feasibility and discriminability of recently proposed Clinical Performance Measures for Neurocritical Care (Neurocritical Care Society) and Quality Indicators for Traumatic Brain Injury (Collaborative European NeuroTrauma Effectiveness Research in TBI; CENTER-TBI) extracted from electronic health record (EHR) flowsheet data. ⋯ Electronic health record-derived reporting of neurocritical care performance measures is feasible and demonstrates site-specific variation. Future efforts should examine whether performance or documentation drives these measures, what outcomes are associated with performance, and whether EHR-derived measures of performance measures and quality indicators are modifiable.