Automated detection of severe cerebral edema using explainable deep transfer learning after hypoxic ischemic brain injury.

BACKGROUND

Substantial gaps exist in the neuroprognostication of cardiac arrest patients who remain comatose after the restoration of spontaneous circulation. Most studies focus on predicting survival, a measure confounded by the withdrawal of life-sustaining treatment decisions. Severe cerebral edema (SCE) may serve as an objective proximal imaging-based surrogate of neurologic injury.

METHODS

We retrospectively analyzed data from 288 patients to automate SCE detection with machine learning (ML) and to test the hypothesis that the quantitative values produced by these algorithms (ML_SCE) can improve predictions of neurologic outcomes. Ground-truth SCE (GT_SCE) classification was based on radiology reports.

RESULTS

The model attained a cross-validated testing accuracy of 87% [95% CI: 84%, 89%] for detecting SCE. Attention maps explaining SCE classification focused on cisternal regions (p < 0.05). Multivariable analyses showed that older age (p < 0.001), non-shockable initial cardiac rhythm (p = 0.004), and greater ML_SCE values (p < 0.001) were significant predictors of poor neurologic outcomes, with GT_SCE (p = 0.064) as a non-significant covariate.

CONCLUSION

Our results support the feasibility of automated SCE detection. Future prospective studies with standardized neurologic assessments are needed to substantiate the utility of quantitative ML_SCE values to improve neuroprognostication.