Value of machine learning to predict functional outcome of endovascular treatment for acute ischaemic stroke of the posterior circulation

2021 ◽  
pp. 197140092110490
Author(s):  
Ludger Feyen ◽  
Peter Schott ◽  
Hendrik Ochmann ◽  
Marcus Katoh ◽  
Patrick Haage ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Ischaemic Stroke ◽  
Endovascular Treatment ◽  
Linear Model ◽  
Acute Ischaemic Stroke ◽  
Favourable Outcome ◽  
Posterior Circulation ◽  
Nearest Neighbour ◽  
Modified Rankin Scale

Purpose Clinical outcomes vary considerably among individuals with vessel occlusion of the posterior circulation. In the present study we evaluated machine learning algorithms in their ability to discriminate between favourable and unfavourable outcomes in patients with endovascular treatment of acute ischaemic stroke of the posterior circulation. Methods This retrospective study evaluated three algorithms (generalised linear model, K-nearest neighbour and random forest) to predict functional outcomes at dismissal of 30 patients with acute occlusion of the basilar artery who were treated with thrombectomy. Input variables encompassed baseline as well as peri and postprocedural data. Favourable outcome was defined as a modified Rankin scale score of 0–2 and unfavourable outcome was defined as a modified Rankin scale score of 3–6. The performance of the algorithms was assessed with the area under the receiver operating curve and with confusion matrixes. Results Successful reperfusion was achieved in 83%, with 30% of the patients having a favourable outcome. The area under the curve was 0.93 for the random forest model, 0.86 for the K-nearest neighbour model and 0.78 for the generalised linear model. The accuracy was 0.69 for the generalised linear model and 0.84 for the random forest and the K nearest neighbour models. Conclusion Favourable and unfavourable outcomes at dismissal of patients with acute ischaemic stroke of the posterior circulation can be predicted immediately after the follow-up non-enhanced computed tomography using machine learning.

scholarly journals Endovascular treatment of acute ischaemic stroke in octogenarians and nonagenarians compared with younger patients

2019 ◽  
Vol 32 (4) ◽  
pp. 303-308 ◽  
Author(s):  
Yasuhiro Kawabata ◽  
Norio Nakajima ◽  
Hidenori Miyake ◽  
Shunichi Fukuda ◽  
Tetsuya Tsukahara
Keyword(s):  
Ischaemic Stroke ◽  
Functional Outcome ◽  
Scale Score ◽  
Endovascular Therapy ◽  
Acute Ischaemic Stroke ◽  
Intravenous Thrombolysis ◽  
Favourable Outcome ◽  
Modified Rankin Scale ◽  
Very Elderly ◽  
Younger Patients

Purpose: Endovascular therapy for emergent large vessel occlusion has been established as the standard approach for acute ischaemic stroke. However, the effectiveness and safety of endovascular therapy in the very elderly population has not been proved. Objective: To determine the safety and effectiveness of endovascular therapy in octogenarians and nonagenarians. Methods: We retrospectively reviewed all patients who underwent endovascular therapy at two stroke centres between April 2012 and July 2018. Functional outcome was assessed using the modified Rankin scale at 90 days after stroke or at discharge. A favourable outcome was defined as a modified Rankin scale score of 0–2 or not worsening of the modified Rankin scale score before stroke. Outcome was compared between younger patients (aged 46–79 years, n = 40) and octogenarians and nonagenarians (aged 80–97 years, n = 19). Results: Octogenarian and nonagenarian patients had pre-stroke functional deficit (modified Rankin scale score >1) more frequently than younger patients (57.9% vs. 20.0%, respectively, P = 0.0059). No difference was observed between very elderly and younger patients in the rate of successful reperfusion (89.5% vs. 67.5%, respectively, P = 0.11), favourable functional outcome (47.4% vs. 45.0%, respectively, P = 1.00) and mortality (21.1% vs. 27.5%, respectively, P = 1.00). On multiple regression analysis, successful reperfusion, concomitant use of intravenous thrombolysis, and out-of-hospital onset were independent predictors of favourable outcome ( P = 0.0003, 0.015 and 0.028, respectively). Conclusions: Successful reperfusion, concomitant use of intravenous thrombolysis, and out-of-hospital onset were clinical predictors of favourable outcome. However, we did not observe an age-dependent effect of clinical outcome after endovascular therapy.

scholarly journals Choice of ANaesthesia for EndoVAScular treatment of acute ischaemic stroke at posterior circulation (CANVAS II): protocol for an exploratory randomised controlled study

BMJ Open ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. e036358
Author(s):  
Fa Liang ◽  
Yan Zhao ◽  
Xiang Yan ◽  
Youxuan Wu ◽  
Xiuheng Li ◽  
...  
Keyword(s):  
Ischaemic Stroke ◽  
Endovascular Treatment ◽  
Acute Ischaemic Stroke ◽  
Neurological Outcome ◽  
Neurological Function ◽  
Posterior Circulation ◽  
Controlled Study ◽  
Randomised Controlled ◽  
Medical University ◽  
Type Of Anaesthesia

IntroductionObservational and interventional studies indicate that the type of anaesthesia may be associated with the postprocedural neurological function in patients with anterior circulation acute ischaemic stroke undergoing endovascular treatment. Patients with acute posterior circulation ischaemic stroke may experience different physiological changes and result in severe neurological outcome. However, the effect of the type of anaesthesia on postprocedure neurological function remained unclear in this population.Methods and analysisThis is an exploratory randomised controlled trial that will be carried out at Beijing Tiantan Hospital, Capital Medical University. Patients with acute posterior circulation ischaemic stroke and deemed suitable for emergency endovascular recanalisation will be recruited in this trial. Eighty-four patients will be randomised to receive either general anaesthesia or conscious sedation with 1:1 allocation ratio. The primary endpoint is the 90-day modified Rankin Scale.Ethics and disseminationThe study has been reviewed by and approved by Ethics Committee of Beijing Tiantan Hospital of Capital Medical University (KY2017-074-02). If the results are positive, the study will indicate whether the type of anaesthesia affects neurological outcome after endovascular treatment of posterior stroke. The findings of the study will be published in peer-reviewed journals and presented at national or international conferences.Trial registration numberNCT03317535.

Outcomes of endovascular treatment for acute ischaemic stroke in Mater Dei Hospital, Malta

2021 ◽  
pp. 197140092110344
Author(s):  
Kyle Cilia ◽  
Reuben Grech ◽  
Maria Mallia
Keyword(s):  
Cerebral Infarction ◽  
Ischaemic Stroke ◽  
Endovascular Treatment ◽  
Scale Score ◽  
Acute Ischaemic Stroke ◽  
Mechanical Thrombectomy ◽  
Functional Independence ◽  
National Institutes Of Health ◽  
Modified Rankin Scale ◽  
The Mean

Introduction The aim of this study was to assess the outcomes of endovascular treatment for acute ischaemic stroke in Mater Dei Hospital, Malta and compare them with international data. Methods A prospective review of all patients who underwent mechanical thrombectomy from 2015 to the end of 2019 was performed. Eligible patients had large vessel occlusion confirmed on computed tomography angiography. Demographical data, the National Institutes of Health stroke scale at presentation, endovascular procedure details and process times were analysed. The thrombolysis in cerebral infarction score was used to assess the degree of reperfusion. A thrombolysis in cerebral infarction score of 2b–3 was considered as successful recanalisation. Functional outcome (modified Rankin scale score) and mortality at 90 days were measured. Functional independence was defined as a modified Rankin scale score of 2 or less. Results A total of 132 patients underwent endovascular treatment, one patient was excluded due to incomplete data. The mean age was 71 (range 25–94) years, and the mean National Institutes of Health stroke scale at presentation was 14. Of the 131 patients treated, 69 received intravenous thrombolysis. Successful recanalisation (thrombolysis in cerebral infarction score 2b–3) was achieved in 80% of patients (105/131); 53% of patients (69/131) achieved functional independence at 90 days, with a mortality of 21% at 90 days. Symptomatic intracranial haemorrhage was recorded in 16 patients (12%) There was a statistical difference in the functional independence and mortality rate in favour of the successful recanalisation group. Conclusion Our data are consistent with a favourable clinical outcome after successful recanalisation. Service in Malta is achieving favourable outcomes for patients treated with mechanical thrombectomy for acute ischaemic stroke.

scholarly journals Efficacy and safety of butylphthalide for patients who had acute ischaemic stroke receiving intravenous thrombolysis or endovascular treatment (BAST trial): study protocol for a randomised placebo-controlled trial

BMJ Open ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. e045559
Author(s):  
Xuelei Zhang ◽  
Anxin Wang ◽  
Jing Yu Zhang ◽  
Baixue Jia ◽  
Xiaochuan Huo ◽  
...  
Keyword(s):  
Ischaemic Stroke ◽  
Endovascular Treatment ◽  
Functional Outcome ◽  
Acute Ischaemic Stroke ◽  
Controlled Trial ◽  
Intravenous Thrombolysis ◽  
Serious Adverse Events ◽  
Double Blind ◽  
Ischaemic Injury ◽  
Study Results

IntroductionAs a neuroprotective medication, butylphthalide (NBP) may help protect against cerebral ischaemic injury. However, evidence on whether NBP influences the outcomes of patients who had acute ischaemic stroke who are receiving revascularisation treatment is limited. This study aims to evaluate whether additional NBP therapy can improve the functional outcome of patients who receive intravenous recombinant tissue plasminogen activator and/or endovascular treatment (EVT).Methods and analysisThe study will be a randomised, double-blind, placebo-controlled, multiple-centre, parallel group trial. The sample size is estimated at 1200 patients. Eligible patients will be randomised at a 1:1 ratio to receive either NBP or placebo daily for 90 days, which will include 14 days of injections and 76 days of capsules. The first use of NBP/placebo will be started within 6 hours of onset of ischaemic stroke. The primary outcome is the functional outcome as assessed by the 90-day modified Rankin Scale, adjusted for baseline scores on the National Institutes of Health Stroke Scale. The primary safety outcome is the percentage of serious adverse events during the 90 days of treatment. This trial will determine whether NBP medication benefits patients who had acute ischaemic stroke who receive intravenous thrombolysis or EVT.Ethics and disseminationThe protocol was written according to the general ethical guidelines of the Declaration of Helsinki and approved by the Institutional Review Board/Ethics Committee of Beijing Tiantan Hospital, Capital Medical University with approval number KY 2018-003-02. Ethics committees of all participating sites have approved the study . Results of the study will be published in peer-reviewed scientific journals and shared in scientific presentations.Trial registration numberNCT03539445.

Classification and photometric redshift estimation of quasars in photometric surveys

2020 ◽  
Vol 15 (S359) ◽  
pp. 40-41
Author(s):  
L. M. Izuti Nakazono ◽  
C. Mendes de Oliveira ◽  
N. S. T. Hirata ◽  
S. Jeram ◽  
A. Gonzalez ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Nearest Neighbour ◽  
Random Forest Algorithm ◽  
Photometric Redshift ◽  
Using Data

AbstractWe present a machine learning methodology to separate quasars from galaxies and stars using data from S-PLUS in the Stripe-82 region. In terms of quasar classification, we achieved 95.49% for precision and 95.26% for recall using a Random Forest algorithm. For photometric redshift estimation, we obtained a precision of 6% using k-Nearest Neighbour.

scholarly journals Mechanical thrombectomy in acute ischaemic stroke patients with pre-interventional intracranial haemorrhage following intravenous thrombolysis

2021 ◽  
pp. 197140092110091
Author(s):  
Hanna Styczen ◽  
Matthias Gawlitza ◽  
Nuran Abdullayev ◽  
Alex Brehm ◽  
Carmen Serna-Candel ◽  
...  
Keyword(s):  
Clinical Outcome ◽  
Ischaemic Stroke ◽  
Acute Ischaemic Stroke ◽  
Intracranial Haemorrhage ◽  
Mechanical Thrombectomy ◽  
Intravenous Thrombolysis ◽  
Modified Rankin Scale ◽  
Large Vessel Occlusion ◽  
Stroke Patients ◽  
Vessel Occlusion

Background Data on outcome of endovascular treatment in patients with acute ischaemic stroke due to large vessel occlusion suffering from intravenous thrombolysis-associated intracranial haemorrhage prior to mechanical thrombectomy remain scarce. Addressing this subject, we report our multicentre experience. Methods A retrospective analysis of consecutive acute ischaemic stroke patients treated with mechanical thrombectomy due to large vessel occlusion despite the pre-interventional occurrence of intravenous thrombolysis-associated intracranial haemorrhage was performed at five tertiary care centres between January 2010–September 2020. Baseline demographics, aetiology of stroke and intracranial haemorrhage, angiographic outcome assessed by the Thrombolysis in Cerebral Infarction score and clinical outcome evaluated by the modified Rankin Scale at 90 days were recorded. Results In total, six patients were included in the study. Five individuals demonstrated cerebral intraparenchymal haemorrhage on pre-interventional imaging; in one patient additional subdural haematoma was observed and one patient suffered from isolated subarachnoid haemorrhage. All patients except one were treated by the ‘drip-and-ship’ paradigm. Successful reperfusion was achieved in 4/6 (67%) individuals. In 5/6 (83%) patients, the pre-interventional intracranial haemorrhage had aggravated in post-interventional computed tomography with space-occupying effect. Overall, five patients had died during the hospital stay. The clinical outcome of the survivor was modified Rankin Scale=4 at 90 days follow-up. Conclusion Mechanical thrombectomy in patients with intravenous thrombolysis-associated intracranial haemorrhage is technically feasible. The clinical outcome of this subgroup of stroke patients, however, appears to be devastating with high mortality and only carefully selected patients might benefit from endovascular treatment.

scholarly journals Heart Disease Prediction using Machine Learning Techniques

2021 ◽  
pp. 42-47
Author(s):  
Ramesh Ponnala ◽  
K. Sai Sowjanya
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Random Forest ◽  
Linear Model ◽  
Machine Learning Techniques ◽  
Disease Prediction ◽  
Huge Amount ◽  
Healthcare Enterprise ◽  
Learning Techniques ◽  
Accuracy Level

Prediction of Cardiovascular ailment is an important task inside the vicinity of clinical facts evaluation. Machine learning knowledge of has been proven to be effective in helping in making selections and predicting from the huge amount of facts produced by using the healthcare enterprise. on this paper, we advocate a unique technique that pursuits via finding good sized functions by means of applying ML strategies ensuing in improving the accuracy inside the prediction of heart ailment. The severity of the heart disease is classified primarily based on diverse methods like KNN, choice timber and so on. The prediction version is added with special combos of capabilities and several known classification techniques. We produce a stronger performance level with an accuracy level of a 100% through the prediction version for heart ailment with the Hybrid Random forest area with a linear model (HRFLM).

scholarly journals Endovascular treatment of intracranial ‘blister’ and dissecting aneurysms

2019 ◽  
Vol 32 (5) ◽  
pp. 353-365 ◽  
Author(s):  
Marius G Kaschner ◽  
Bastian Kraus ◽  
Athanasios Petridis ◽  
Bernd Turowski
Keyword(s):  
Endovascular Treatment ◽  
Favourable Outcome ◽  
Modified Rankin Scale ◽  
Parent Vessel ◽  
Vessel Occlusion ◽  
Parent Vessel Occlusion ◽  
Aneurysm Occlusion ◽  
Vessel Reconstruction ◽  
Dissecting Aneurysms

IntroductionBlister and dissecting aneurysms may have a different pathological background but they are commonly defined by instability of the vessel wall and bear a high risk of fatal rupture and rerupture. Lack of aneurysm sack makes treatment challenging.PurposeThe purpose of this study was to assess the safety and feasibility of endovascular treatment of intracranial blister and dissecting aneurysms.MethodsWe retrospectively analysed all patients with ruptured and unruptured blister and dissecting aneurysms treated endovascularly between 2004–2018. Procedural details, complications, morbidity/mortality, clinical favourable outcome (modified Rankin Scale ≤2) and aneurysm occlusion rates were assessed.ResultsThirty-four patients with endovascular treatment of 35 aneurysms (26 dissecting aneurysms and 9 blister aneurysms) were included. Five aneurysms were treated by parent vessel occlusion, and 30 aneurysms were treated by vessel reconstruction using stent monotherapy ( n = 9), stent-assisted coiling ( n = 7), flow diverting stents ( n = 13) and coiling + Onyx embolization ( n = 1). No aneurysm rebleeding and no procedure-related major complications or deaths occurred. There were five deaths in consequence of initial subarachnoid haemorrhage. Complete occlusion (79.2%) was detected in 19/24 aneurysms available for angiographic follow-up, and aneurysm recurrence in 2/24 (8.3%). The modified Rankin Scale ≤2 rate at mean follow-up of 15.1 months was 64.7%.ConclusionTreatment of blister and dissecting aneurysms developed from coil embolization to flow diversion with multiple stents to the usage of flow diverting stents. Results using modern flow diverting stents encourage us to effectively treat this aneurysm entity endovascularly by vessel reconstruction. Therefore, we recommend preference of vessel reconstructive techniques to parent vessel occlusion.

Sign in / Sign up

Export Citation Format

Share Document