scholarly journals Comparative study of back propagation artificial neural networks and logistic regression model in predicting poor prognosis after acute ischemic stroke

Open Medicine ◽  
2019 ◽  
Vol 14 (1) ◽  
pp. 324-330 ◽  
Author(s):  
Yaru Liang ◽  
Qiguang Li ◽  
Peisong Chen ◽  
Lingqing Xu ◽  
Jiehua Li
Keyword(s):  
Neural Networks ◽  
Alkaline Phosphatase ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Poor Prognosis ◽  
Diagnostic Performance ◽  
Back Propagation ◽  
Stroke Patients ◽  
Poor Outcome ◽  
The Poor

AbstractObjectiveTo investigate the predictive value of clinical variables on the poor prognosis at 90-day follow-up from acute stroke onset, and compare the diagnostic performance between back propagation artificial neural networks (BP ANNs) and Logistic regression (LR) models in predicting the prognosis.MethodsWe studied the association between clinical variables and the functional recovery of 435 acute ischemic stroke patients. The patients were divided into 2 groups according to modified Rankin Scale scores evaluated on the 90th day after stroke onset. Both BP ANNs and LR models were established for predicting the poor outcome and their diagnostic performance were compared by receiver operating curve.ResultsAge, free fatty acid, homocysteine and alkaline phosphatase were closely related with the poor outcome in acute ischemic stroke patients and finally enrolled in models. The accuracy, sensitivity and specificity of BP ANNs were 80.15%, 75.64% and 82.07% respectively. For the LR model, the accuracy, sensitivity and specificity was 70.61%, 88.46% and 63.04% respectively. The area under the ROC curve of the BP ANNs and LR model was 0.881and 0.809.ConclusionsBoth BP ANNs and LR model were promising for the prediction of poor outcome by combining age, free fatty acid, homocysteine and alkaline phosphatase. However, BP ANNs model showed better performance than LR model in predicting the prognosis.

scholarly journals Advanced Age and Higher National Institutes of Health Stroke Scale Score as Predictors of Poor Outcome in Ischemic Stroke Patients Treated with Alteplase: A Study from a Tertiary Care Centre in Rural North-west India

2017 ◽  
Vol 08 (02) ◽  
pp. 236-240 ◽  
Author(s):  
Amit Bhardwaj ◽  
Girish Sharma ◽  
Sunil Kumar Raina ◽  
Ashish Sharma ◽  
Monica Angra
Keyword(s):  
Ischemic Stroke ◽  
Acute Stroke ◽  
Acute Ischemic Stroke ◽  
Tertiary Care ◽  
National Institutes Of Health ◽  
Stroke Patients ◽  
Nihss Score ◽  
Good Outcome ◽  
Poor Outcome ◽  
The Poor

ABSTRACT Introduction: Thrombolytic therapy in acute ischemic stroke has been approved for treatment of acute stroke for past two decades. However, identification of predictors of poor outcome after the intravenous (IV) alteplase therapy in acute stroke patients is a matter of research. The present study was conducted with the aim of identifying poor prognostic factors in patients of acute ischemic stroke patients. Methods: The data of 31 acute stroke patients treated with alteplase were gathered to identify the factors that were independent predictors of the poor outcome. Outcome was dichotomized using modified Rankin scale (mRS) score and National Institutes of Health Stroke Scale (NIHSS) score at 3 months after treatment into good outcome mRS - 0–2 and poor outcome mRS - 3–6. Predictors of poor outcome were analyzed. Results: Good outcome (mRS – score 0–2) was seen in 15 (48.4%) patients with median age of (60) and poor outcome (mRS – score 3–6) was seen in 16 (51.6%) patients median age of 75 years, which was statistically significant with the P = 0.002. The presence of risk factors such as hypertension, diabetes, dyslipidemia, smoking, alcohol intake, history of stroke, coronary artery disease, and rheumatic heart disease among the two groups did not seem influence outcome. The severity of stroke as assessed by NIHSS score at the time of presentation was significantly higher among the patients with poor outcome, with P = 0.01. Conclusion: Advance age and higher NIHSS score at the time of onset of stroke and are the independent predictors of the poor outcome after thrombolysis with IV alteplase treatment in acute ischemic stroke patients.

Abstract 10: Predictors of Poor Outcome in Acute Ischemic Stroke Patients after Successful Recanalization

2014 ◽  
Vol 7 (suppl_1) ◽  
Author(s):  
Amy K Starosciak ◽  
Italo Linfante ◽  
Gail Walker ◽  
Osama O Zaidat ◽  
Alicia C Castonguay ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Cerebral Infarction ◽  
Acute Stroke ◽  
Acute Ischemic Stroke ◽  
Predictive Power ◽  
Rescue Therapy ◽  
Univariate Analysis ◽  
Stroke Patients ◽  
Good Outcome ◽  
Poor Outcome

Background: Recanalization of the occluded artery is a powerful predictor of good outcome in acute ischemic stroke secondary to large artery occlusions. Mechanical thrombectomy with stent-trievers results in higher recanalization rates and better outcomes compared to previous devices. However, despite successful recanalization rates (Treatment in Cerebral Infarction, TICI, score ≥ 2b) between 70 and 90%, good clinical outcomes assessed by modified Rankin Scale (mRS) ≤ 2 is present in 40-50% of patients . We aimed to evaluate predictors of poor outcomes (mRS > 2) despite successful recanalization (TICI ≥ 2b) in the acute stroke patients treated with the Solitaire device of the North American Solitaire Stent Retriever Acute Stroke (NASA) registry. Methods: The NASA registry is a multicenter, non-sponsored, physician-conducted, post-marketing registry on the use of SOLITAIRE FR device in 354 acute, large vessel, ischemic stroke patients. Logistic regression was used to evaluate patient characteristics and treatment parameters for association with 90-day mRS score of 0-2 (good outcome) versus 3-6 (poor outcome) within patients who were recanalized successfully (Thrombolysis in Cerebral Infarction or TICI score 2b-3). Univariate tests were followed by development of a multivariable model based on stepwise selection with entry and retention criteria of p < 0.05 from the set of factors with at least marginal significance (p ≤ 0.10) on univariate analysis. The c-statistic was calculated as a measure of predictive power. Results: Out of 354 patients, 256 (72.3%) were successfully recanalized (TICI ≥ 2b). Based on 90-day mRS score for 234 of these patients, there were 116 (49.6%) with mRS > 2. Univariate analysis identified increased risk of mRS > 2 for each of the following: age ≥ 80 years (upper quartile of data), occlusion site other than M1/M2, NIH Stroke Scale (NIHSS) score ≥ 18 (median), history of diabetes mellitus (DM), TICI = 2b, use of rescue therapy, not using a balloon-guided catheter (BGC) or intravenous tissue plasminogen activator (IV t-PA), and time to recanalization > 30 minutes (all p ≤ 0.05). Three or more passes was marginally significant (p=0.097). In multivariable analysis, age ≥ 80 years, site other than M1/M2, initial NIHSS ≥18, DM, absence of IV t-PA, use of rescue therapy and three or more passes were significant independent predictors of poor 90-day outcome in a model with good predictive power (c-index = 0.80). Conclusions: Age, occlusion site, high NIHSS, diabetes, not receiving IV t-PA, use of rescue therapy and three or more passes, were associated with poor 90-day outcome despite successful recanalization.

Defining Minor Symptoms in Acute Ischemic Stroke

2015 ◽  
Vol 39 (3-4) ◽  
pp. 209-215 ◽  
Author(s):  
Davide Strambo ◽  
Alberto A. Zambon ◽  
Luisa Roveri ◽  
Giacomo Giacalone ◽  
Giovanni Di Maggio ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Motor Impairment ◽  
Epidemiological Data ◽  
Minor Stroke ◽  
Predictors Of Outcome ◽  
Stroke Patients ◽  
Nihss Score ◽  
Poor Outcome ◽  
Definition Of

Background: Thrombolysis is often withheld from acute ischemic stroke patients presenting with mild symptoms; however, up to 40% of these patients end up with a poor outcome when left untreated. Since there is lack of consensus on the definition of minor symptoms, we aimed at addressing this issue by looking for features that would better predict functional outcomes at 3 months. Methods: Among all acute ischemic stroke patients admitted to our Stroke Unit (n = 1,229), we selected a cohort of patients who arrived within 24 hours from symptoms onset, with baseline NIHSS ≤6, not treated with thrombolysis (n = 304). Epidemiological data, comorbidities, radiological features and clinical presentation (NIHSS items) were collected to identify predictors of outcome. Our cohort was tested against minor stroke definitions selected from the literature and a newly proposed one. Results: Three months after stroke onset, 97 patients (31.9%) had mRS ≥2. Independent predictors of poor outcome were age (OR 0.97 [95% CI 0.95-9.99]) and baseline NIHSS score (OR 0.79 [95% CI 0.67-0.94]), while cardioembolic aetiology was negatively associated (OR 3.29 [95% CI 1.51-7.14]). Items of NIHSS associated with poor outcome were impairment of right motor arm (OR 0.49 [95% CI 0.27-0.91]) or the involvement of any of the motor items (OR 0.69 [95% CI 0.48-0.99]). The definition of minor stroke as NIHSS ≤3 and the new proposed definition had the highest sensitivity and accuracy and were independent predictors of outcome. Conclusions: Our study confirmed that in spite of a low NIHSS score, one third of patients had poor outcome. As already described, age and NIHSS score remained independent predictors of poor outcome even in mild stroke. Also, motor impairment appeared a major determinant of poor outcome. The new proposed definition of minor stroke featured the NIHSS score and the NIHSS items that better predicted functional outcome. Awareness that even minor stroke can yield to poor outcome should sensitize patients to arrive early to the ED and neurologists to administer rt-PA.

Outcomes after Early Neurological Deterioration and Transitory Deterioration in Acute Ischemic Stroke Patients

2016 ◽  
Vol 42 (5-6) ◽  
pp. 378-386 ◽  
Author(s):  
Bernt Harald Helleberg ◽  
Hanne Ellekjaer ◽  
Bent Indredavik
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Strong Association ◽  
Neurological Deterioration ◽  
Stroke Patients ◽  
Repeated Observations ◽  
The Poor ◽  
Early Neurological Deterioration ◽  
Clinically Significant ◽  
Td Methods

Background and Purpose: Early neurological deterioration (END) occurs in 10-40% of acute ischemic stroke (AIS) patients and has been associated with worse outcome. Recent improvements in treatment may have reduced the prevalence of END. A single early control or repeated observations have been applied to detect END close to occurrence, in order to improve the poor outcome associated with END, as clinical interventions may still be effective. Deterioration detected through repeated observations may be transitory or lead to END. Our aim was to study outcome after END and transitory deterioration (TD). Methods: In acute ischemic stroke patients, key Scandinavian Stroke Scale (SSS) items were scored 12 times from admission to 72 h. END was defined as ≥2 point decrease in any key SSS item from admission to 72 h. Early deterioration episode was defined as similar worsening between two consecutive assessments within 72 h, and TD as early deterioration episode in patients without END. Main outcome measures were odds ratios (OR) for worse functional outcome (including death) measured by modified Rankin scale at 90 days for END and TD compared with stable patients. Results: 368 patients were included. 13.9% had END and 28.3% had TD. Both deterioration groups were associated with worse outcome at 12 weeks compared with stable patients, with ORs of 35.1 (95% CI 8.8-140) for death/dependency and 5.8 (95% CI 1.8-19.4) for death in END patients and ORs of 2.3 (95% CI 1.1-4.8) for death/dependency and 1.9 (95% CI 0.5-6.3) for death in patients with TD. LOS increased by 6.4 days for END (p < 0.001) and 1.1 days for TD (p = 0.014) compared with stable patients. Conclusion: We found a strong association between END and worse outcome, and even TD doubled the OR for death/dependency compared to stable patients. Early deterioration episodes identified through frequent observations are therefore clinically significant and such frequent observations may detect worsening sufficiently close to occurrence for potentially effective treatment to be applied.

scholarly journals Serum Interleukin-37 Increases in Patients after Ischemic Stroke and Is Associated with Stroke Recurrence

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Ying Zhang ◽  
Chengbi Xu ◽  
Haitao Wang ◽  
Shanji Nan
Keyword(s):  
Ischemic Stroke ◽  
Serum Level ◽  
Acute Ischemic Stroke ◽  
Functional Outcome ◽  
Recurrent Stroke ◽  
Clinical Severity ◽  
Stroke Recurrence ◽  
Stroke Patients ◽  
Nihss Score ◽  
Poor Outcome

Background. This study seeks to assess interleukin-37 (IL-37) serum level in acute ischemic stroke and the value of predicting 3-month stroke recurrence and functional outcome in acute ischemic stroke. Methods. From January 1, 2018, to June 30, 2019, all consecutive first-ever acute ischemic stroke patients from our hospital, China, were included. Serum samples, clinical information, and stroke severity (defined by the National Institute of Health stroke scale (NIHSS) score) were collected at baseline. Serum IL-37 level was measured by the enzyme-linked immunosorbent assay (ELISA) method. Functional impairment (defined by the modified Rankin scale (mRS)) and recurrent stroke were assessed 3 months after admission. The relation of IL-37 with either clinical severity at baseline, unfavorable functional outcome, or stroke recurrence at follow-up was evaluated by logistic regression analysis, and the results were presented as odds ratios (OR) with 95% confidence intervals (CI). Results. Three hundred and ten stroke patients were included. The median IL-37 serum level in those patients was 344.1 pg/ml (interquartile range (IQR), 284.4-405.3 vs. control cases: 122.3 pg/ml (IQR, 104.4-1444.0); P < 0.001 ). At 3 months, a total of 36 (11.6%) patients had a stroke recurrence. IL-37 serum levels in those patients were higher than in those patients without stroke recurrence (417.0 pg/ml (IQR, 359.3-436.1) vs. 333.3 pg/ml (279.0-391.0)). In a logistic model adjusted for other factors, IL-37 in the highest quartile (>405.3 pg/ml) was still associated with recurrent stroke ( OR = 3.32 ; 95 % CI = 2.03 – 6.13 ; P < 0.001 ). IL-37 could promote the NIHSS score (area under the curve (AUC) of the IL-37/NIHSS, 0.75; 95% CI, 0.67–0.83; P < 0.001 ), corresponding to a difference of 0.085 (0.005). Serum IL-37 increases in patients with poor outcome, and an IL-37 in the highest quartile is related to poor outcome ( OR = 4.85 ; 95 % CI = 3.11 − 8.22 ; P < 0.001 ). Conclusion. Serum IL-37 increased in patients after ischemic stroke and was associated with stroke recurrence events and poor stroke outcomes. Large randomized controlled trials should be carried out to confirm whether IL-37 lowering treatment improves stroke prognosis.

Sign in / Sign up

Export Citation Format

Share Document