Dataset Information

Machine learning predicts cerebral vasospasm in patients with subarachnoid haemorrhage.

ABSTRACT:

Background

Cerebral vasospasm (CV) is a feared complication which occurs after 20-40% of subarachnoid haemorrhage (SAH). It is standard practice to admit patients with SAH to intensive care for an extended period of resource-intensive monitoring. We used machine learning to predict CV requiring verapamil (CVRV) in the largest and only multi-center study to date.

Methods

Patients with SAH admitted to UCLA from 2013 to 2022 and a validation cohort from VUMC from 2018 to 2023 were included. For each patient, 172 unique intensive care unit (ICU) variables were extracted through the primary endpoint, namely first verapamil administration or no verapamil. At each institution, a light gradient boosting machine (LightGBM) was trained using five-fold cross validation to predict the primary endpoint at various hospitalization timepoints.

Findings

A total of 1750 patients were included from UCLA, 125 receiving verapamil. LightGBM achieved an area under the ROC (AUC) of 0.88 > 1 week in advance and ruled out 8% of non-verapamil patients with zero false negatives. Our models predicted "no CVRV" vs "CVRV within three days" vs "CVRV after three days" with AUCs = 0.88, 0.83, and 0.88, respectively. From VUMC, 1654 patients were included, 75 receiving verapamil. VUMC predictions averaged within 0.01 AUC points of UCLA predictions.

Interpretation

We present an accurate and early predictor of CVRV using machine learning with multi-center validation. This represents a significant step towards optimized clinical management and resource allocation in patients with SAH.

Funding

Robert E. Freundlich is supported by National Center for Advancing Translational Sciences federal grant UL1TR002243 and National Heart, Lung, and Blood Institute federal grant K23HL148640; these funders did not play any role in this study. The National Institutes of Health supports Vanderbilt University Medical Center which indirectly supported these research efforts. Neither this study nor any other authors personally received financial support for the research presented in this manuscript. No support from pharmaceutical companies was received.

SUBMITTER: Zarrin DA

PROVIDER: S-EPMC11245940 | biostudies-literature | 2024 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning predicts cerebral vasospasm in patients with subarachnoid haemorrhage.

Zarrin David A DA Suri Abhinav A McCarthy Karen K Gaonkar Bilwaj B Wilson Bayard R BR Colby Geoffrey P GP Freundlich Robert E RE Gabel Eilon E

EBioMedicine 20240619

<h4>Background</h4>Cerebral vasospasm (CV) is a feared complication which occurs after 20-40% of subarachnoid haemorrhage (SAH). It is standard practice to admit patients with SAH to intensive care for an extended period of resource-intensive monitoring. We used machine learning to predict CV requiring verapamil (CVRV) in the largest and only multi-center study to date.<h4>Methods</h4>Patients with SAH admitted to UCLA from 2013 to 2022 and a validation cohort from VUMC from 2018 to 2023 were in ...[more]

PMID: 38901147

Similar Datasets

Project description:The diagnosis of cerebral vasospasm after Subarachnoid-Hemorrhage is currently very difficult, additional tools such as blood biomarkers are necessary. We tested the ability of gene expression profiles of blood cells to predict vasospasm. 32 patients suffering subarachnoid-hemorrhage were included in this prospective monocentre study. They were grouped according to have a complicated cerebral vasospasm (Vasospasm) or not (Control) and Paired according to age (+/- 10 years), sex, Fisher grade (+/- 1), location, smoking (at least 3 first parameters). Gene expression profiles of blood cells were determined using 25,000~gene microarray. Blood sample: 2.5 mL harvested in PAXgene® Blood RNA tubes (PreAnalytix) RNA extraction: PAXgene® Blood RNA kit (Qiagen). We used a Universel Reference RNA (Stratagene). RNA amplification and labelling: kit Amino Allyl MessageAmp II (Ambion). We hybridized 4 microarrays per patient using pangenomic microarrays from the "Réseau National des Génopôles" (Illkirch, France). 2 slides were hybridized with reference RNA labelled Cy3 and patient RNA labelled Cy5, and 2 slides were hybridized with reference RNA labelled Cy5 and patient RNA labelled Cy3. Hybridation : Agilent protocol with few modifications : 750 ng of each labelled RNA were hubriddized at 60°C during 17 hours in an Aglient hybridization oven. After washings, Slides were scanned with a GenePix 4000B scanner (Molecular Devices). Image intensity data were extracted with GenePix Pro 6.0 analysis software. Quantification of Cy3 and Cy5 and selection of good spots were performed using the MAIA software (Novikov E and Barillot E. Software package for automatic microarray image analysis (MAIA). The ACUITY software was then used to normalize log ratios Cy3/Cy5 with Lowess non linear normalization, to filter out genes not present in at least 3 slides out of 4, to evaluate the reproducibility of the 4 microarrays of each patient (hierarchical clustering, Self Organizing Maps). Statistical analyses to insure reproducibility was performed using Excel (correlation coefficients, ANOVA). Only slides that passed all reprocubility tests were validated.

Project description:BackgroundCerebral vasospasm is a major contributor to disability and mortality after aneurysmal subarachnoid hemorrhage. Oxidation of cell-free hemoglobin plays an integral role in neuroinflammation and is a suggested source of tissue injury after aneurysm rupture. This study sought to determine whether patients with subarachnoid hemorrhage and cerebral vasospasm were more likely to have been exposed to early hyperoxemia than those without vasospasm.MethodsThis single-center retrospective cohort study included adult patients presenting with aneurysmal subarachnoid hemorrhage to Vanderbilt University Medical Center between January 2007 and December 2017. Patients with an ICD-9/10 diagnosis of aneurysmal subarachnoid hemorrhage were initially identified (N = 441) and subsequently excluded if they did not have intracranial imaging, arterial PaO2 values or died within 96 h post-rupture (N = 96). The final cohort was 345 subjects. The degree of hyperoxemia was defined by the highest PaO2 measured within 72 h after aneurysmal rupture. The primary outcome was development of cerebral vasospasm, which included asymptomatic vasospasm and delayed cerebral ischemia (DCI). Secondary outcomes were mortality and modified Rankin Scale.ResultsThree hundred and forty five patients met inclusion criteria; 218 patients (63%) developed vasospasm. Of those that developed vasospasm, 85 were diagnosed with delayed cerebral ischemia (DCI, 39%). The average patient age of the cohort was 55 ± 13 years, and 68% were female. Ninety percent presented with Fisher grade 3 or 4 hemorrhage (N = 310), while 42% presented as Hunt-Hess grade 4 or 5 (N = 146). In univariable analysis, patients exposed to higher levels of PaO2 by quintile of exposure had a higher mortality rate and were more likely to develop vasospasm in a dose-dependent fashion (P = 0.015 and P = 0.019, respectively). There were no statistically significant predictors that differentiated asymptomatic vasospasm from DCI and no significant difference in maximum PaO2 between these two groups. In multivariable analysis, early hyperoxemia was independently associated with vasospasm (OR = 1.15 per 50 mmHg increase in PaO2 [1.03, 1.28]; P = 0.013), but not mortality (OR = 1.10 [0.97, 1.25]; P = 0.147) following subarachnoid hemorrhage.ConclusionsHyperoxemia within 72 h post-aneurysmal rupture is an independent predictor of cerebral vasospasm, but not mortality in subarachnoid hemorrhage. Hyperoxemia is a variable that can be readily controlled by adjusting the delivered FiO2 and may represent a modifiable risk factor for vasospasm.

Dataset Information

Machine learning predicts cerebral vasospasm in patients with subarachnoid haemorrhage.

Background

Methods

Findings

Interpretation

Funding

Publications

Machine learning predicts cerebral vasospasm in patients with subarachnoid haemorrhage.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets