Background and Purpose—: The prediction of long-term outcomes in ischemic stroke patients may be useful in treatment decisions. Machine learning techniques are being increasingly adapted for use in the medical field because of their high accuracy. This study investigated the applicability of machine learning techniques to predict long-term outcomes in ischemic stroke patients. Methods—: This was a retrospective study using a prospective cohort that enrolled patients with acute ischemic stroke. Favorable outcome was defined as modified Rankin Scale score 0, 1, or 2 at 3 months. We developed 3 machine learning models (deep neural network, random forest, and logistic regression) and compared their predictability. To evaluate the accuracy of the machine learning models, we also compared them to the Acute Stroke Registry and Analysis of Lausanne (ASTRAL) score. Results—: A total of 2604 patients were included in this study, and 2043 (78%) of them had favorable outcomes. The area under the curve for the deep neural network model was significantly higher than that of the ASTRAL score (0.888 versus 0.839; P <0.001), while the areas under the curves of the random forest (0.857; P =0.136) and logistic regression (0.849; P =0.413) models were not significantly higher than that of the ASTRAL score. Using only the 6 variables that are used for the ASTRAL score, the performance of the machine learning models did not significantly differ from that of the ASTRAL score. Conclusions—: Machine learning algorithms, particularly the deep neural network, can improve the prediction of long-term outcomes in ischemic stroke patients.

Importance: Optimal blood pressure (BP) control after successful reperfusion with endovascular thrombectomy (EVT) for patients with acute ischemic stroke is unclear.Objective: To determine whether intensive BP management during the first 24 hours after successful reperfusion leads to better clinical outcomes than conventional BP management in patients who underwent EVT.Design, Setting, and Participants: Multicenter, randomized, open-label trial with a blinded end-point evaluation, conducted across 19 stroke centers in South Korea from June 2020 to November 2022 (final follow-up, March 8, 2023). It included 306 patients with large vessel occlusion acute ischemic stroke treated with EVT and with a modified Thrombolysis in Cerebral Infarction score of 2b or greater (partial or complete reperfusion).Interventions: Participants were randomly assigned to receive intensive BP management (systolic BP target <140 mm Hg; n = 155) or conventional management (systolic BP target 140-180 mm Hg; n = 150) for 24 hours after enrollment.Main Outcomes and Measures: The primary outcome was functional independence at 3 months (modified Rankin Scale score of 0-2). The primary safety outcomes were symptomatic intracerebral hemorrhage within 36 hours and death related to the index stroke within 3 months.Results: The trial was terminated early based on the recommendation of the data and safety monitoring board, which noted safety concerns. Among 306 randomized patients, 305 were confirmed eligible and 302 (99.0%) completed the trial (mean age, 73.0 years; 122 women [40.4%]). The intensive management group had a lower proportion achieving functional independence (39.4%) than the conventional management group (54.4%), with a significant risk difference (−15.1% [95% CI, −26.2% to −3.9%]) and adjusted odds ratio (0.56 [95% CI, 0.33-0.96]; P = .03). Rates of symptomatic intracerebral hemorrhage were 9.0% in the intensive group and 8.1% in the conventional group (risk difference, 1.0% [95% CI, −5.3% to 7.3%]; adjusted odds ratio, 1.10 [95% CI, 0.48-2.53]; P = .82). Death related to the index stroke within 3 months occurred in 7.7% of the intensive group and 5.4% of the conventional group (risk difference, 2.3% [95% CI, −3.3% to 7.9%]; adjusted odds ratio, 1.73 [95% CI, 0.61-4.92]; P = .31).Conclusions and Relevance: Among patients who achieved successful reperfusion with EVT for acute ischemic stroke with large vessel occlusion, intensive BP management for 24 hours led to a lower likelihood of functional independence at 3 months compared with conventional BP management. These results suggest that intensive BP management should be avoided after successful EVT in acute ischemic stroke.Trial Registration: ClinicalTrials.gov Identifier: NCT04205305

Background and Purpose: The hospital-based stroke registry is a well-established method useful for understanding diverse clinical characteristics of stroke related to geographical, racial or environmental differences. We analyzed the data from 1,000 patients with acute cerebral infarctions registered with the Yonsei Stroke Registry (YSR) which is the first prospective hospital-based observational study in Korea. Methods: All patients had cerebral infarctions and presented within 7 days of onset. CT or MRI was performed in all patients and a vascular imaging study (digital subtraction or magnetic resonance angiography) was conducted in 53.9% of the patients. Subtype classification was made through a consensus approach based on the strict application of TOAST criteria. Results: The mean age of patients was 62 ± 12 years, and 60.8% were males. Undetermined cause (UD) was the most frequent subtype (40.6%), which was followed by lacunar stroke (LS 21.5%), cardiac embolism (CE 18.3%), large-artery atherosclerosis (LAA 16.5%) and other determined causes (3.1%). Hypertension was found in 64.3%, smoking in 35.2%, diabetes mellitus in 26.9%, hypercholesterolemia in 24.1%, high hematocrit (≧50%) in 21.8%, clinically identified potential cardiac sources of embolism in 18.3%, a history of previous stroke in 22.0% and a history of previous transient ischemic attack in 4.7%. Recurrent stroke was associated with a higher number of risk factors (p < 0.001) and a higher incidence of LAA (p = 0.003) than the first stroke. Vertebrobasilar artery territorial infarction was found in 39.8%, which was associated with higher incidences of LAA and LS and a lower incidence of CE than carotid artery territorial lesions (p = 0.001). The 30-day mortality rate was 5.3% and cerebral herniation caused early death in 52%. Conclusion: The distribution of stroke subtypes in the YSR was largely comparable with that of western registries. The highest incidence of UD might be related to the strict application of TOAST criteria.

Background and Purpose—: Endovascular treatment for acute intracranial atherosclerosis–related large vessel occlusion (ICAS [+]-LVO) is one of the challenging issues in modern mechanical thrombectomy era. We evaluated procedural and clinical outcomes of endovascular treatment for the ICAS (+)-LVO. We also compared their outcomes with those of large vessel occlusion not associated with intracranial atherosclerosis (ICAS [−]-LVO). Methods—: We retrospectively reviewed consecutive patients with acute stroke who underwent endovascular treatment for LVO. Patients were assigned to the ICAS (+)-LVO group or the ICAS (−)-LVO group primarily based on catheter angiogram. Procedural and clinical outcomes were compared between the ICAS (+)-LVO and ICAS (−)-LVO groups. Results—: The present study included 318 patients. Fifty-six patients (17.6%) had an ICAS (+)-LVO. Recanalization was achieved in 45 patients in the ICAS (+)-LVO group (80.4%), which was comparable with the ICAS (−)-LVO group (88.5%; P =0.097). However, recanalization using a stent retriever was less successful in the ICAS (+)-LVO (28.9%) than the ICAS (−)-LVO group (93.5%). Of the remaining patients in the ICAS (+)-LVO group, 84.3% of patients required specific rescue treatments appropriate for ICAS, including balloon angioplasty, stenting, and intra-arterial glycoprotein IIb/IIIa inhibitor infusion. The rates of favorable outcomes (46.4% versus 46.9%), death, and symptomatic intracranial hemorrhage were not significantly different between the 2 groups. Glycoprotein IIb/IIIa inhibitor use was not significantly associated with symptomatic intracranial hemorrhage. Conclusions—: ICAS (+)-LVO was often refractory to mechanical thrombectomy. With specific rescue treatments appropriate for ICAS, patients in the ICAS (+)-LVO group had a recanalization rate comparable with patients in the ICAS (−)-LVO. With comparable recanalization rate, the clinical outcomes did not differ between patients with ICAS (+)-LVO and ICAS (−)-LVO.