Outcome prediction and individualized treatment effect estimation in patients with large vessel occlusion stroke

TL;DR

This study develops interpretable deep learning models integrating clinical and imaging data to predict outcomes and estimate individualized treatment effects in large vessel occlusion stroke patients, achieving state-of-the-art prediction accuracy.

Contribution

The paper introduces novel foundation models that combine clinical variables with advanced imaging to predict functional outcomes and estimate treatment effects in stroke patients.

Findings

Clinical variables predicted outcomes with AUC of 0.719.

Adding CTA imaging slightly improved prediction (AUC 0.737).

Estimated ITEs were well calibrated but had limited discriminatory ability.

Abstract

Mechanical thrombectomy has become the standard of care in patients with stroke due to large vessel occlusion (LVO). However, only 50% of successfully treated patients show a favorable outcome. We developed and evaluated interpretable deep learning models to predict functional outcomes in terms of the modified Rankin Scale score alongside individualized treatment effects (ITEs) using data of 449 LVO stroke patients from a randomized clinical trial. Besides clinical variables, we considered non-contrast CT (NCCT) and angiography (CTA) scans which were integrated using novel foundation models to make use of advanced imaging information. Clinical variables had a good predictive power for binary functional outcome prediction (AUC of 0.719 [0.666, 0.774]) which could slightly be improved when adding CTA imaging (AUC of 0.737 [0.687, 0.795]). Adding NCCT scans or a combination of NCCT and CTA scans to clinical features yielded no improvement. The most important clinical predictor for functional outcome was pre-stroke disability. While estimated ITEs were well calibrated to the average treatment effect, discriminatory ability was limited indicated by a C-for-Benefit statistic of around 0.55 in all models. In summary, the models allowed us to jointly integrate CT imaging and clinical features while achieving state-of-the-art prediction performance and ITE estimates. Yet, further research is needed to particularly improve ITE estimation.