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.
-
Large and complex data sets are increasingly available for research in critical care. To analyze these data, researchers use techniques commonly referred to as statistical learning or machine learning (ML). The latter is known for large successes in the field of diagnostics, for example, by identification of radiological anomalies. ⋯ To conclude, there are important opportunities but also pitfalls to consider when performing clustering or predictive studies with ML techniques. We advocate careful valuation of new data-driven findings. More interaction is needed between the engineer mindset of experts in ML methods, the insight in bias of epidemiologists, and the probabilistic thinking of statisticians to extract as much information and knowledge from data as possible, while avoiding harm.
-
Review Meta Analysis
Perihematomal Edema and Clinical Outcome After Intracerebral Hemorrhage: A Systematic Review and Meta-Analysis.
Perihematomal edema (PHE) has been proposed as a radiological marker of secondary injury and therapeutic target in intracerebral hemorrhage (ICH). We conducted a systematic review and meta-analysis to assess the prognostic impact of PHE on functional outcome and mortality in patients with ICH. ⋯ This meta-analysis demonstrates that PHE volume within the first 72 h after ictus has a weak effect on functional outcome and mortality after ICH, whereas PHE growth might have a slightly larger impact during this time frame. Definitive conclusions are limited by the large variability of PHE measures, heterogeneity, and different evaluation time points between studies.