Intensive care medicine
-
Intensive care medicine · Mar 2020
Review Meta AnalysisMachine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy.
Early clinical recognition of sepsis can be challenging. With the advancement of machine learning, promising real-time models to predict sepsis have emerged. We assessed their performance by carrying out a systematic review and meta-analysis. ⋯ This systematic review and meta-analysis show that on retrospective data, individual machine learning models can accurately predict sepsis onset ahead of time. Although they present alternatives to traditional scoring systems, between-study heterogeneity limits the assessment of pooled results. Systematic reporting and clinical implementation studies are needed to bridge the gap between bytes and bedside.
-
Scorpion envenomation is common in the tropical and subtropical regions. It poses a major public health problem with some patients having serious clinical manifestations and severe complications including death. Old World and New World scorpions are usually contrasted because of differences in venom composition, clinical presentation and severity, and, accordingly, different therapeutic approaches. ⋯ The standard intensive-care treatment (when available) overcomes envenomation's consequences such as acute pulmonary edema and cardiogenic shock. Even though it continues to inspire many evaluative studies, immunotherapy seems less attractive because of the major role held by mediators in the pathogenesis of envenomation, and unfavorable pharmacokinetic properties to existing sera compared to venom. Meta-analyses of controlled trials of immunotherapy in severe scorpion envenomation reached similar conclusions: there is an acceptable level of evidence in favor of the use of scorpion antivenom (Fab'2) against Centruroides sp. in USA/Mexico, while there is still a need for a higher level of evidence for immunotherapy in the Old World envenomation.