Prediction of Thrombectomy Functional Outcomes using Multimodal Data
This addresses the problem of personalized treatment prediction for stroke patients, representing an incremental improvement with specific domain application.
The paper tackled the challenge of predicting individual patient outcomes for endovascular thrombectomy in ischemic stroke by proposing a novel deep learning approach using multimodal data, achieving 0.75 AUC for dichotomised scores and 0.35 accuracy for individual scores.
Recent randomised clinical trials have shown that patients with ischaemic stroke {due to occlusion of a large intracranial blood vessel} benefit from endovascular thrombectomy. However, predicting outcome of treatment in an individual patient remains a challenge. We propose a novel deep learning approach to directly exploit multimodal data (clinical metadata information, imaging data, and imaging biomarkers extracted from images) to estimate the success of endovascular treatment. We incorporate an attention mechanism in our architecture to model global feature inter-dependencies, both channel-wise and spatially. We perform comparative experiments using unimodal and multimodal data, to predict functional outcome (modified Rankin Scale score, mRS) and achieve 0.75 AUC for dichotomised mRS scores and 0.35 classification accuracy for individual mRS scores.