Search

Background Baseline anemia is associated with poor intracerebral hemorrhage (ICH) outcomes. However, underlying drivers for anemia and whether anemia development after ICH impacts clinical outcomes are unknown. We hypothesized that inflammation drives anemia development after ICH and assessed their relationship to outcomes. Methods and Results Patients with serial hemoglobin and iron biomarker concentrations from the HIDEF (High‐Dose Deferoxamine in Intracerebral Hemorrhage) trial were analyzed. Adjusted linear mixed models assessed laboratory changes over time. Of 42 patients, significant decrements in hemoglobin occurred with anemia increasing from 19% to 45% by day 5. Anemia of inflammation iron biomarker criteria was met in 88%. A separate cohort of 521 patients with ICH with more granular serial hemoglobin and long‐term neurological outcome data was also investigated. Separate regression models assessed whether (1) systemic inflammatory response syndrome (SIRS) scores related to hemoglobin changes over time and (2) hemoglobin changes related to poor 90‐day outcome. In this cohort, anemia prevalence increased from 30% to 71% within 2 days of admission yet persisted beyond this time. Elevated systemic inflammatory response syndrome was associated with greater hemoglobin decrements over time (adjusted parameter estimate: −0.27 [95% CI, −0.37 to −0.17]) and greater hemoglobin decrements were associated with poor outcomes (adjusted odds ratio per 1 g/dL increase, 0.76 [95% CI, 0.62–0.93]) independent to inflammation and ICH severity. Conclusions We identified novel findings that acute anemia development after ICH is common, rapid, and related to inflammation. Because anemia development is associated with poor outcomes, further work is required to clarify if anemia, or its underlying drivers, are modifiable treatment targets that can improve ICH outcomes. Registration https://www.clinicaltrials.gov Unique identifier: NCT01662895

PurposeAccurate prediction of delayed cerebral ischemia (DCI) after subarachnoid hemorrhage (SAH) can be critical for planning interventions to prevent poor neurological outcome. This paper presents a model using convolution dictionary learning to extract features from physiological data available from bedside monitors. We develop and validate a prediction model for DCI after SAH, demonstrating improved precision over standard methods alone.Methods488 consecutive SAH admissions from 2006 to 2014 to a tertiary care hospital were included. Models were trained on 80%, while 20% were set aside for validation testing. Modified Fisher Scale was considered the standard grading scale in clinical use; baseline features also analyzed included age, sex, Hunt–Hess, and Glasgow Coma Scales. An unsupervised approach using convolution dictionary learning was used to extract features from physiological time series (systolic blood pressure and diastolic blood pressure, heart rate, respiratory rate, and oxygen saturation). Classifiers (partial least squares and linear and kernel support vector machines) were trained on feature subsets of the derivation dataset. Models were applied to the validation dataset.ResultsThe performances of the best classifiers on the validation dataset are reported by feature subset. Standard grading scale (mFS): AUC 0.54. Combined demographics and grading scales (baseline features): AUC 0.63. Kernel derived physiologic features: AUC 0.66. Combined baseline and physiologic features with redundant feature reduction: AUC 0.71 on derivation dataset and 0.78 on validation dataset.ConclusionCurrent DCI prediction tools rely on admission imaging and are advantageously simple to employ. However, using an agnostic and computationally inexpensive learning approach for high-frequency physiologic time series data, we demonstrated that we could incorporate individual physiologic data to achieve higher classification accuracy.

Acute ischemic stroke is a devastating disease that is often complicated by hemorrhagic transformation. While significant advances have been made over the past two decades with regard to emergent treatment of AIS, many of these therapeutic options are limited by an increased risk of hemorrhage. Here, we sought to review the rates of hemorrhagic transformation in the major clinical trials of AIS intervention. Since the reviewed clinical trials vary significantly with regard to study design, eligibility criteria, stroke severity and baseline demographic data, direct comparisons between the various trials is not valid. Nevertheless, this review is intended to consolidate the pertinent data on hemorrhagic transformation in order to call attention to any patterns that may warrant further investigation.