Project description:Background and objectiveAutomated machine learning or autoML has been widely deployed in various industries. However, their adoption in healthcare, especially in clinical settings is constrained due to a lack of clear understanding and explainability. The aim of this study is to utilize autoML for the prediction of functional outcomes in patients who underwent mechanical thrombectomy and compare it with traditional ML models with a focus on the explainability of the trained models.MethodsA total of 156 patients of acute ischemic stroke with Large Vessel Occlusion (LVO) who underwent mechanical thrombectomy within 24 h of stroke onset were included in the study. A total of 34 treatment variables including clinical, demographic, imaging, and procedure-related data were extracted. Various conventional machine learning models such as decision tree classifier, logistic regression, random forest, kNN, and SVM as well as various autoML models such as AutoGluon, MLJAR, Auto-Sklearn, TPOT, and H2O were used to predict the modified Rankin score (mRS) at the time of patient discharge and 3 months follow-up. The sensitivity, specificity, accuracy, and AUC for traditional ML and autoML models were compared.ResultsThe autoML models outperformed the traditional ML models. For the prediction of mRS at discharge, the highest testing accuracy obtained by traditional ML models for the decision tree classifier was 74.11%, whereas for autoML which was obtained through AutoGluon, it showed an accuracy of 88.23%. Similarly, for mRS at 3 months, the highest testing accuracy of traditional ML was that of the SVM classifier at 76.5%, whereas that of autoML was 85.18% obtained through MLJAR. The 24-h ASPECTS score was the most important predictor for mRS at discharge whereas for prediction of mRS at 3 months, the most important factor was mRS at discharge.ConclusionAutomated machine learning models based on multiple treatment variables can predict the functional outcome in patients more accurately than traditional ML models. The ease of clinical coding and deployment can assist clinicians in the critical decision-making process. We have developed a demo application which can be accessed at https://mrs-score-calculator.onrender.com/.
Project description:Background and purposeMechanical properties of thromboemboli play an important role in the efficacy of endovascular thrombectomy (EVT) for acute ischemic stroke. However, very limited data on mechanical properties of human stroke thrombi are available. We aimed to mechanically characterize thrombi retrieved with EVT, and to assess the relationship between thrombus composition and thrombus stiffness.MethodsForty-one thrombi from 19 patients with acute stroke who underwent EVT between July and October 2019 were mechanically analyzed, directly after EVT. We performed unconfined compression experiments and determined tangent modulus at 75% strain (Et75) as a measure for thrombus stiffness. Thrombi were histologically analyzed for fibrin/platelets, erythrocytes, leukocytes, and platelets, and we assessed the relationship between histological components and Et75 with univariable and multivariable linear mixed regression.ResultsMedian Et75 was 560 (interquartile range, 393–1161) kPa. In the multivariable analysis, fibrin/platelets were associated with increased Et75 (aβ, 9 [95% CI, 5 to 13]) kPa, erythrocytes were associated with decreased Et75% (aβ, −9 [95% CI, −5 to −13]) kPa. We found no association between leukocytes and Et75. High platelet values were strongly associated with increased Et75 (aβ, 56 [95% CI, 38–73]).ConclusionsFibrin/platelet content of thrombi retrieved with EVT for acute ischemic stroke is strongly associated with increased thrombus stiffness. For thrombi with high platelet values, there was a very strong relationship with thrombus stiffness. Our data provide a basis for future research on the development of next-generation EVT devices tailored to thrombus composition.
Project description:Ischemic stroke secondary to aortic dissection is not uncommon. We present a patient with left hemiplegia secondary to Stanford type A aortic dissection extending to the supra-aortic vessels, which was precipitated by rifle butt recoil chest injury. The diagnosis of aortic dissection was delayed due to various factors. Finally, the patient underwent successful Bentall procedure with complete resolution of symptoms. This case emphasizes the need for caution in the use of firearms for recreation and to take precautions in preventing such incidents. In addition, this case illustrates the need for prompt cardiovascular physical examination in patients presenting with stroke.
Project description:ImportanceWhether endovascular thrombectomy (EVT) efficacy for patients with acute ischemic stroke and large cores varies depending on the extent of ischemic injury is uncertain.ObjectiveTo describe the relationship between imaging estimates of irreversibly injured brain (core) and at-risk regions (mismatch) and clinical outcomes and EVT treatment effect.Design, setting, and participantsAn exploratory analysis of the SELECT2 trial, which randomized 352 adults (18-85 years) with acute ischemic stroke due to occlusion of the internal carotid or middle cerebral artery (M1 segment) and large ischemic core to EVT vs medical management (MM), across 31 global centers between October 2019 and September 2022.InterventionEVT vs MM.Main outcomes and measuresPrimary outcome was functional outcome-90-day mRS score (0, no symptoms, to 6, death) assessed by adjusted generalized OR (aGenOR; values >1 represent more favorable outcomes). Benefit of EVT vs MM was assessed across levels of ischemic injury defined by noncontrast CT using ASPECTS score and by the volume of brain with severely reduced blood flow on CT perfusion or restricted diffusion on MRI.ResultsAmong 352 patients randomized, 336 were analyzed (median age, 67 years; 139 [41.4%] female); of these, 168 (50%) were randomized to EVT, and 2 additional crossover MM patients received EVT. In an ordinal analysis of mRS at 90 days, EVT improved functional outcomes compared with MM within ASPECTS categories of 3 (aGenOR, 1.71 [95% CI, 1.04-2.81]), 4 (aGenOR, 2.01 [95% CI, 1.19-3.40]), and 5 (aGenOR, 1.85 [95% CI, 1.22-2.79]). Across strata for CT perfusion/MRI ischemic core volumes, aGenOR for EVT vs MM was 1.63 (95% CI, 1.23-2.16) for volumes ≥70 mL, 1.41 (95% CI, 0.99-2.02) for ≥100 mL, and 1.47 (95% CI, 0.84-2.56) for ≥150 mL. In the EVT group, outcomes worsened as ASPECTS decreased (aGenOR, 0.91 [95% CI, 0.82-1.00] per 1-point decrease) and as CT perfusion/MRI ischemic core volume increased (aGenOR, 0.92 [95% CI, 0.89-0.95] per 10-mL increase). No heterogeneity of EVT treatment effect was observed with or without mismatch, although few patients without mismatch were enrolled.Conclusion and relevanceIn this exploratory analysis of a randomized clinical trial of patients with extensive ischemic stroke, EVT improved clinical outcomes across a wide spectrum of infarct volumes, although enrollment of patients with minimal penumbra volume was low. In EVT-treated patients, clinical outcomes worsened as presenting ischemic injury estimates increased.Trial registrationClinicalTrials.gov Identifier: NCT03876457.
Project description:BackgroundRandomized controlled trials (RCTs) have compared mechanical endovascular therapy (MET) in addition to intravenous tissue plasminogen activator (IVtPA) to IVtPA alone for the management of acute ischemic stroke (AIS). Direct comparative studies between individual METs are not available. In lieu of head-to-head randomized control trials, we performed an adjusted indirect treatment comparison (ITC) meta-analysis to assess the comparative efficacy and safety of different METs, Solitaire+IVtPA and Penumbra+IVtPA in AIS patients.Methods and findingsWe searched MEDLINE, the Cochrane Central Register of Controlled Trials and Embase from January 1, 2005 through April 1, 2017 for RCTs in AIS patients, comparing a single MET+IVtPA to IVtPA alone and reporting shift in ordinal modified Rankin Scale (mRS) score at 90 days. Secondary endpoints included 90 day mortality and symptomatic intracranial hemorrhage (sICH). Endpoints were pooled using traditional random effects meta-analysis methods, producing odds ratios and 95% confidence intervals. Adjusted ITCs using pooled estimates were then performed. Three studies (SWIFT PRIME, EXTEND-IA, THERAPY) were included; two evaluating the Solitaire stent retriever and one the Penumbra system. Traditional meta-analysis demonstrated that each MET+IVtPA resulted in increased odds of improving ordinal mRS score vs. IVtPA alone, but did not alter the odds of death or sICH. Adjusted ITC showed no significant difference between the METs for any outcome.ConclusionNo significant difference in efficacy or safety between the Solitaire and Penumbra devices was observed.
Project description:The development of the endovascular thrombectomy (EVT) technique has revolutionized acute stroke management for patients with large vessel occlusions (LVOs). The impact of successful recanalization using an EVT on autoregulatory profiles is unknown. A more complete understanding of cerebral autoregulation in the context of EVT may assist with post-procedure hemodynamic optimization to prevent complications. We examined cerebral autoregulation in 107 patients with an LVO in the anterior circulation (proximal middle cerebral artery (M1/2) and internal cerebral artery (ICA) terminus) who had been treated using an EVT. Dynamic cerebral autoregulation was assessed at multiple time points, ranging from less than 24 hours to 5 days following last seen well (LSW) time, using transcranial Doppler ultrasound recordings and transfer function analysis. Complete (Thrombolysis in Cerebral Infarction (TICI) 3) recanalization was associated with a more favorable autoregulation profile compared with TICI 2b or poorer recanalization (p < 0.05), which is an effect that was present after accounting for differences in the infarct volumes. Less effective autoregulation in the first 24 h following the LSW time was associated with increased rates of parenchymal hematoma types 1 and 2 hemorrhagic transformations (PH1-PH2). These data suggest that patients with incomplete recanalization and poor autoregulation (especially within the first 24 h post-LSW time) may warrant closer blood pressure monitoring and control in the first few days post ictus.
Project description:Although uncommon, acute aortic dissections are a life-threatening, cannot miss diagnosis for the emergency medicine clinician. Point of care ultrasound can play an integral role in the initial work up of the undifferentiated patient. While not initially utilized to make the diagnosis of aortic dissection, the ultrasound images obtained in this case describe key findings on ultrasound vital for an emergency clinician to recognize. It is essential for emergency medicine clinicians to differentiate an aortic dissection from other causes of chest pain and abdominal pain because the quick mobilization of resources plays a key role in the management and outcome of such patients.TopicsAortic dissection, vascular, dissection flap, back pain, point of care ultrasound, POCUS.
Project description:Acute ischemic stroke (AIS) due to thrombo-embolic occlusion in the cerebral vasculature is a major cause of morbidity and mortality in the United States and throughout the world. Although the prognosis is poor for many patients with AIS, a variety of strategies and devices are now available for achieving recanalization in patients with this disease. Here, we review the treatment options for cerebrovascular thromboembolic occlusion with a focus on the evolution of strategies and devices that are utilized for achieving endovascular clot extraction. In order to demonstrate the progression of this treatment strategy over the past decade, we will also present a single-center case series of AIS patients treated with endovascular thrombectomy.
Project description:Background and purposeRescue therapies are increasingly used in the setting of endovascular therapy for large-vessel occlusion strokes. Among these, cangrelor, a new P2Y12 inhibitor, offers promising pharmacologic properties to join the reperfusion strategies in acute stroke. We assessed the safety and efficacy profiles of cangrelor combined with endovascular therapy in patients with large-vessel-occlusion stroke.Materials and methodsWe performed a retrospective patient data analysis in the ongoing prospective multicenter observational Endovascular Treatment in Ischemic Stroke Registry in France from July 2018 to December 2020 and conducted a systematic review and meta-analysis using several data bases. Indications for cangrelor administration were rescue strategy in case of refractory intracranial occlusion with or without intracranial rescue stent placement, and cervical carotid artery stent placement in case of cervical occlusion (tandem occlusion or isolated cervical carotid occlusion).ResultsIn the clinical registry, 44 patients were included (median initial NIHSS score, 12; prior intravenous thrombolysis, 29.5%). Intracranial stent placement was performed in 54.5% (n = 24/44), and cervical stent placement, in 27.3% (n = 12/44). Adjunctive aspirin and heparin were administered in 75% (n = 33/44) and 40.9% (n = 18/44), respectively. Rates of symptomatic intracerebral hemorrhage, parenchymal hematoma, and 90-day mortality were 9.5% (n = 4/42), 9.5% (n = 4/42), and 24.4% (n = 10/41). Favorable outcome (90-day mRS, 0-2) was reached in 51.2% (n = 21/41), and successful reperfusion, in 90.9% (n = 40/44). The literature search identified 6 studies involving a total of 171 subjects. In the meta-analysis, including our series data, symptomatic intracerebral hemorrhage occurred in 8.6% of patients (95% CI, 5.0%-14.3%) and favorable outcome was reached in 47.6% of patients (95% CI, 27.4%-68.7%). The 90-day mortality rate was 22.6% (95% CI, 13.6%-35.2%). Day 1 artery patency was observed in 89.7% (95% CI, 81.4%-94.6%).ConclusionsCangrelor offers promising safety and efficacy profiles, especially considering the complex endovascular reperfusion procedures in which it is usually applied. Further large prospective data are required to confirm these findings.
Project description:BackgroundPerioperative ischemic stroke is a rare but devastating complication. Mechanical thrombectomy is a promising therapeutic method, but very little data is available on its efficacy and safety. This study aims to answer this question by comparing the clinical outcomes of perioperative and community-onset stroke patients after endovascular therapy.MethodsA retrospective cohort study was conducted on a total of 35 perioperative and 584 community-onset acute ischemic stroke patients who underwent endovascular thrombectomy at our hospital over the past 3.5 years. The recanalization rate, clinical recovery and cerebral hemorrhage within 90 days after therapy were compared between these two patient groups.ResultsEndovascular thrombectomy provided perioperative and community-onset ischemic stroke patients with comparable rates of successful reperfusion (mTICI ≥2b grade) (97.1% vs. 97.3%; p = 0. 967) and favorable functional recovery (mRS ≤ 2) (51.4% vs. 43.3%, p = 0.348), with no increase in severe intracranial hemorrhage (0% vs. 2.6 and 1.0%, for hematoma ≥30% of infarcted tissue and intraventricular hemorrhage, respectively) within 90 days. In addition, perioperative stroke patients had higher prevalence of atrial fibrillation (42.9% vs. 26.7%; p = 0.038) and intracranial cerebral artery stenosis without clear embolism (17.1% vs. 3.8%; p < 0.001) than community-onset stroke patients.ConclusionEndovascular thrombectomy is an effective and safe therapeutic approach for patients with perioperative ischemic stroke, although the results need to be validated by further studies with larger populations. Atrial fibrillation and large artery stenosis may contribute to the pathogenesis of perioperative ischemic stroke.