Dual-outcome Prediction of Post-Ischemic Stroke Epilepsy and Mortality Using Multimodal Quantitative Biomarkers
Discuss this preprint
Start a discussion What are Sciety discussions?Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background and Objectives
Post-ischemic stroke epilepsy (PISE) reduces quality of life, and early risk prediction can guide prevention strategies and anti-epileptogenesis treatment trials. Stroke severity predicts both PISE and mortality, and ignoring mortality can overestimate epilepsy risk. We sought to enhance PISE risk stratification by modeling death as a competing outcome, integrating quantitative clinical, neuroimaging, and electroencephalography (EEG) biomarkers to distinguish shared and distinct predictors of epilepsy and mortality.
Methods
We developed a PISE prediction model using retrospective data from Yale-New Haven Hospital. The training cohort included patients from 2014–2020; the testing cohort from 2021–2022. Eligible patients were adults with acute ischemic stroke who underwent neuroimaging and EEG monitoring <7 days post-stroke and had follow-up >7 days.
Results
Of 280 patients, 53 developed PISE first, 104 died first, and the rest were censored. Quantitative PISE biomarkers included greater 72h stroke severity (HR Δ3 [95%CI], 1.2 [1.1-1.4]), infarct volume (HR Δ10mL , 1.06 [1.04-1.08]), EEG epileptiform abnormality burden (HR Δ10% , 1.2 [1.1-1.3]), and EEG power asymmetries (HR Δ10% , 2.0 [1.4-2.9]). Death predictors included older age (HR Δ10years , 1.7 [1.4-2.0]), worse pre-stroke functional status (HR, 1.4 [1.2-1.7]), atrial fibrillation history (HR, 2.4 [1.6-3.7]), cardioembolism etiology (HR, 1.9 [1.2-3.0]), anterior cerebral artery involvement (HR, 2.2 [1.2-3.7]), and greater EEG global theta-band powers (HR Δ10µV , 6.2 [2.3-17]). Our model, CRIME PISE , integrating these features, allows prediction of PISE-first and death-first risk scores with AUC of 0.72 (95%CI, 0.60-0.83) and 0.79 (0.72-0.85), respectively. Compared with the benchmark SeLECT model, CRIME PISE better predicted PISE in patients with ≥4 SeLECT points (AUC, 0.72 vs 0.58) but not those with <4 points (AUC, 0.33 vs 0.52). In the testing cohort, CRIME PISE identified a more selective group (n=18 vs 44 per SeLECT) with a higher PISE rate (39% vs 20%) and a lower mortality rate (22% vs 45%).
Discussion
CRIME PISE enhances PISE prediction by accounting for mortality as a competing outcome and incorporating multimodal quantitative biomarkers. Because its benefits over SeLECT are most pronounced in high-risk patients, a two-stage approach—SeLECT screening followed by CRIME PISE in SeLECT-positive cases—may better target candidates for anti-epileptogenesis trials by prioritizing patients likely to survive long-term and develop epilepsy.
