Quantitative Serial CT Imaging-Derived Features Improve Prediction of Malignant Cerebral Edema after Ischemic Stroke

Abstract

Introduction: Malignant cerebral edema develops in a small subset of patients with hemispheric strokes, precipitating deterioration and death if decompressive hemicraniectomy (DHC) is not performed in a timely manner. Predicting which stroke patients will develop malignant edema is imprecise based on clinical data alone. Head computed tomography (CT) imaging is often performed at baseline and 24-h. We determined the incremental value of incorporating imaging-derived features from serial CTs to enhance prediction of malignant edema. Methods: We identified hemispheric stroke patients at three sites with NIHSS ≥ 7 who had baseline as well as 24-h clinical and CT imaging data. We extracted quantitative imaging features from baseline and follow-up CTs, including CSF volume, intracranial reserve (CSF/cranial volume), as well as midline shift (MLS) and infarct-related hypodensity volume. Potentially lethal malignant edema was defined as requiring DHC or dying with MLS over 5-mm. We built machine-learning models using logistic regression first with baseline data and then adding 24-h data including reduction in CSF volume (ΔCSF). Model performance was evaluated with cross-validation using metrics of recall (sensitivity), precision (predictive value), as well as area under receiver-operating-characteristic and precision-recall curves (AUROC, AUPRC). Results: Twenty of 361 patients (6%) died or underwent DHC. Baseline clinical variables alone had recall of 60% with low precision (7%), AUROC 0.59, AUPRC 0.15. Adding baseline intracranial reserve improved recall to 80% and AUROC to 0.82 but precision remained only 16% (AUPRC 0.28). Incorporating ΔCSF improved AUPRC to 0.53 (AUROC 0.91) while all imaging features further improved prediction (recall 90%, precision 38%, AUROC 0.96, AUPRC 0.66). Conclusion: Incorporating quantitative CT-based imaging features from baseline and 24-h CT enhances identification of patients with malignant edema needing DHC. Further refinements and external validation of such imagingbased machine-learning models are required.

Response

“…That is, greater intracranial reserve may certainly reflect cerebral atrophy and biologic aging, serving as a marker of impaired resiliency with respect to eventual functional recovery after large-vessel stroke [1]. In parallel but conversely, lower intracranial reserve was a clear marker of higher risk for malignant cerebral edema in our and two other recent studies [2][3][4]. We would argue that one concern, however valid, does not negate the other.…”

Commentary on “Midline Shift Greater than 3 mm Independently Predicts Outcome After Ischemic Stroke”

“…It can therefore be insensitive to malignant edema when measured too early, despite significant early swelling (as assessed by other volumetric or densitometric biomarkers) and patients still being at risk for subsequent deterioration. Although relatively rare, we found that 3 of 20 patients who developed malignant edema resulting in death or requiring decompressive surgery in one cohort had no measurable midline shift at 24 h but had significant edema measurable by volumetric CSF tools [19].…”

The Stroke Neuro-Imaging Phenotype Repository: An Open Data Science Platform for Stroke Research

“…The SNIPR user interface provides tools to monitor pipeline progress and review pipeline output, enabling an interactive workflow to check output quality, tune parameters, and relaunch pipeline steps. The pipeline is being used in the large SNIPR patient cohorts to study how dynamic change in brain volumetric values can predict trajectory of edema ( Mohammadian Foroushan et al, 2020b ).…”