Uncertainty-aware deep learning for trustworthy prediction of long-term outcome after endovascular thrombectomy.

Acute ischemic stroke (AIS) is a leading global cause of mortality and morbidity. Improving long-term outcome predictions after thrombectomy can enhance treatment quality by supporting clinical decision-making. With the advent of interpretable deep learning methods in recent years, it is now possible to develop trustworthy, high-performing prediction models. This study introduces an uncertainty-aware, graph deep learning model that predicts endovascular thrombectomy outcomes using clinical features and imaging biomarkers. The model targets long-term functional outcomes, defined by the three-month modified Rankin Score (mRS), and mortality rates. A sample of 220 AIS patients in the anterior circulation who underwent endovascular thrombectomy (EVT) was included, with 81 (37%) demonstrating good outcomes (mRS ≤ 2). The performance of the different algorithms evaluated was comparable, with the maximum validation under the curve (AUC) reaching 0.87 using graph convolutional networks (GCN) for mRS prediction and 0.86 using fully connected networks (FCN) for mortality prediction. Moderate performance was obtained at admission (AUC of 0.76 using GCN), which improved to 0.84 post-thrombectomy and to 0.89 a day after stroke. Reliable uncertainty prediction of the model could be demonstrated.

Extended Multimodal Flat Detector CT Imaging in Acute Ischemic Stroke: A Pilot Study.

By using Flat detector computed tomography (FD-CT), a one-stop-shop approach in the diagnostic workup of acute ischemic stroke (AIS) might be achieved. Although information on upstream vessels is warranted, dedicated FD-CT protocols which include the imaging of the cervical vasculature are still lacking. We aimed to prospectively evaluate the implementation of a new multimodal FD-CT protocol including cervical vessel imaging in AIS patients. In total, 16 patients were included in this study. Eight patients with AIS due to large vessel occlusion (LVO) prospectively received a fully multimodal FD-CT imaging, including non-enhanced flat detector computed tomography (NE-FDCT), dynamic perfusion flat detector computed tomography (FD-CTP) and flat detector computed tomography angiography (FD-CTA) including cervical imaging. For comparison of time metrics and image quality, eight AIS patients, which received multimodal CT imaging, were included retrospectively. Although image quality of NE-FDCT and FD-CTA was rated slightly lower than NE-CT and CTA, all FD-CT datasets were of diagnostic quality. Intracerebral hemorrhage exclusion and LVO detection was reliably possible. Median door-to-image time was comparable for the FD-CT group and the control group (CT:30 min, IQR27-58; FD-CT:44.5 min, IQR31-55, p = 0.491). Door-to-groin-puncture time (CT:79.5 min, IQR65-90; FD-CT:59.5 min, IQR51-67; p = 0.016) and image-to-groin-puncture time (CT:44 min, IQR30-50; FD-CT:14 min, IQR12-18; p < 0.001) were significantly shorter, when patients were directly transferred to the angiosuite, where FD-CT took place. Our study indicates that using a new fully multimodal FD-CT approach including imaging of cervical vessels for first-line imaging in AIS patients is feasible and comparable to multimodal CT imaging with substantial potential to streamline the stroke workflow.

Management of Stroke in Patients with Left Ventricular Assist Devices.

INTRODUCTION: The number of patients with left ventricular assist devices (LVAD) is rapidly growing in industrialized countries. While cerebrovascular events comprise a significant complication, data on stroke etiology, clinical management and functional outcome are scarce. METHODS: Consecutive LVAD patients with ischemic or hemorrhagic stroke receiving treatment at an university stroke center between 2010 and 2018 were included into an institutional registry. Clinical characteristics, causes, management and functional outcome of stroke occurring within this cohort are reported. Acceptable functional outcome was defined as mRS 0-3. RESULTS: N = 30 acute strokes occurred in 20 patients (77% ischemic, 23% hemorrhagic, mean age 57 ± 13 years, 10% female, 8 patients (40%) had more than one event). 87% of all events happened with non-pulsatile devices, on average 9 (IQR 3-22) months after the implantation. All patients used oral anticoagulation with a Vitamin-K antagonist in combination with anti-platelets. The international normalized ratio (INR)-values were outside the therapeutic range in 39% of ischemic strokes and in 57% of hemorrhagic strokes. Ischemic strokes were predominantly of cardioembolic origin (92%) and of mild to moderate clinical severity (median NIHSS 6 (IQR 4-10). None qualified to receive intravenous thrombolysis or intra-arterial endovascular therapy. 61% of IS-patients showed an acceptable functional outcome after three months. 4/7 patients with hemorrhagic stroke received immediate reversal of anticoagulation without any thrombotic complications. CONCLUSION: The majority of LVAD patients with ischemic stroke had an acceptable functional outcome after three months. Future clinical research is warranted to improve therapeutic strategies for acute care and stroke prevention.

Cooling in intracerebral hemorrhage (CINCH) trial: protocol of a randomized German-Austrian clinical trial.

BACKGROUND: Intracerebral hemorrhage accounts for up to 15% of all strokes and is frequently associated with poor functional outcome and high mortality. So far, there is no clear evidence for a specific therapy, apart from general stroke unit or neurointensive care and management of secondary complications. Promising experimental and pilot clinical data support the use of therapeutic hypothermia after intracerebral hemorrhage. AIMS: The study aims to determine if therapeutic hypothermia improves survival rates and reduces cerebral lesion volume after large intracerebral hemorrhage compared with conventional treatment. MATERIAL AND METHODS: The Cooling in IntraCerebral Hemorrhage trial is a prospective, multicenter, interventional, randomized, parallel, two-arm (1 : 1) phase II trial with blinded end-point adjudication. Enrolment: 50 patients (age: 18 to 65 years) with large (25 to 64 ml on cranial computertomography), primary intracerebral hemorrhage of the basal ganglia or thalamus within 6 to 18 h after symptom onset are randomly allocated to therapeutic hypothermia for eight-days or conventional temperature management. In the therapeutic hypothermia group, a target temperature of 35.0°C is achieved by endovascular catheters and followed by slow controlled rewarming. Data analysis is based on the intent-to-treat population. The primary outcome measure of the study is the development in total lesion volume on cranial computertomography (intracerebral hemorrhage plus perihemorrhagic edema on day 8 ± 0.5 and day 1 ± 0.5 after intracerebral hemorrhage) and the mortality after 30 days. Secondary end-points are the in-hospital mortality, mortality, and functional outcome (modified Rankin Scale and Barthel-Index) after 90 and 180 days. Safety measures include any adverse events associated with therapeutic hypothermia. DISCUSSION: In the face of a lack of evidence-based therapies for patients with large intracerebral hemorrhage, new promising approaches are desperately needed, but need evaluation in randomized controlled trials. CONCLUSION: The results of Cooling in IntraCerebral Hemorrhage trial are believed to directly influence future therapy of large intracerebral hemorrhage.