Search

Background: Thrombolysis with r-tPA is recommended for patients after acute ischemic stroke (AIS) within 4.5 h of symptom onset. However, only a few patients benefit from this therapeutic regimen. Thus, we aimed to develop an interpretable machine learning (ML)–based model to predict the thrombolysis effect of r-tPA at the super-early stage.Methods: A total of 353 patients with AIS were divided into training and test data sets. We then used six ML algorithms and a recursive feature elimination (RFE) method to explore the relationship among the clinical variables along with the NIH stroke scale score 1 h after thrombolysis treatment. Shapley additive explanations and local interpretable model–agnostic explanation algorithms were applied to interpret the ML models and determine the importance of the selected features.Results: Altogether, 353 patients with an average age of 63.0 (56.0–71.0) years were enrolled in the study. Of these patients, 156 showed a favorable thrombolysis effect and 197 showed an unfavorable effect. A total of 14 variables were enrolled in the modeling, and 6 ML algorithms were used to predict the thrombolysis effect. After RFE screening, seven variables under the gradient boosting decision tree (GBDT) model (area under the curve = 0.81, specificity = 0.61, sensitivity = 0.9, and F1 score = 0.79) demonstrated the best performance. Of the seven variables, activated partial thromboplastin clotting time (time), B-type natriuretic peptide, and fibrin degradation products were the three most important clinical characteristics that might influence r-tPA efficiency.Conclusion: This study demonstrated that the GBDT model with the seven variables could better predict the early thrombolysis effect of r-tPA.

Background: Thrombolysis with r-tPA is recommended for patients after acute ischemic stroke (AIS) within 4.5 h of symptom onset. However, only a few patients benefit from this therapeutic regimen. Thus, we aimed to develop an interpretable machine learning (ML)–based model to predict the thrombolysis effect of r-tPA at the super-early stage. Methods: A total of 353 patients with AIS were divided into training and test data sets. We then used six ML algorithms and a recursive feature elimination (RFE) method to explore the relationship among the clinical variables along with the NIH stroke scale score 1 h after thrombolysis treatment. Shapley additive explanations and local interpretable model–agnostic explanation algorithms were applied to interpret the ML models and determine the importance of the selected features. Results: Altogether, 353 patients with an average age of 63.0 (56.0–71.0) years were enrolled in the study. Of these patients, 156 showed a favorable thrombolysis effect and 197 showed an unfavorable effect. A total of 14 variables were enrolled in the modeling, and 6 ML algorithms were used to predict the thrombolysis effect. After RFE screening, seven variables under the gradient boosting decision tree (GBDT) model (area under the curve = 0.81, specificity = 0.61, sensitivity = 0.9, and F1 score = 0.79) demonstrated the best performance. Of the seven variables, activated partial thromboplastin clotting time (time), B-type natriuretic peptide, and fibrin degradation products were the three most important clinical characteristics that might influence r-tPA efficiency. Conclusion: This study demonstrated that the GBDT model with the seven variables could better predict the early thrombolysis effect of r-tPA. [ABSTRACT FROM AUTHOR]

Objective To investigate the risk factors for hemorrhagic transformation (HT) after intravenous thrombolysis using a recombinant tissue plasminogen activator (r-tPA) in acute cerebral infarction. Methods Patients with acute cerebral infarction receiving r-tPA thrombolysis in Shanghai Eastern Hospital were retrospectively studied. Based on the cranial computed tomography or magnetic resonance imaging examination, after the intravenous thrombolysis, the patients were divided into 2 groups: an HT group and a non-HT group. The information was collected before or after thrombolysis. RESULTS: A total of 162 patients were included in the analysis. The age ranged from 25 to 86 years, with an average age of 65.6 ± 10.6 years. The average time from disease onset to thrombolysis was 188 ± 53.1 minutes. Cranial computed tomography or magnetic resonance imaging showed that 20 patients (12.3%) had HT after thrombolysis. Using univariate analysis, history of atrial fibrillation, positive expression of urinary protein, and high National Institutes of Health Stroke Scale (NIHSS) score before thrombolysis, we found that there was a significant difference between the HT and non-HT group ( P < 0.05) in the level of mean systolic pressure (MSP) 24 hours after thrombolysis. Multivariate logistic regression analysis indicated that age ≥80 years, MSP ≥140 mm Hg, NIHSS score, and fibrinogen concentration before thrombolysis were risk factors for HT after thrombolysis in patients with acute cerebral infarction. Conclusions Age, MSP, NIHSS score, and fibrinogen concentration before thrombolysis are risk factors for HT after thrombolysis in acute cerebral infarction. These 4 factors should be carefully taken into account before thrombolysis. [ABSTRACT FROM AUTHOR]

Given the constraints of resources, thrombolysis for acute ischemic stroke (AIS) is under evaluation in developing countries like India, especially in areas such as western Utter Pradesh, where it is overly crowded and there is poor affordability. Aim: This study was done to evaluate recombinant tissue plasminogen activator r-tpa in acute ischemic stroke in hyper acute phase, in selected patients of western Utter Pradesh, in terms of feasibility and effectivity. Design: Open, non randomized study. Materials and Methods: Thirty two patients were classified using Trial of ORG 10172 in Acute Stroke treatment (TOAST) criteria (large artery atherosclerotic = 8; cardio embolic = 6; small vessel occlusion = 14; other determined etiology = 2; undetermined etiology = 2). The mean time to reach the hospital was 2 h (1.15-3.0), the mean door to CT scan 20 min (10-40) and door to r-tpa injection was 30 min (24-68). The National Institute of Health Stroke Scale (NIHSS) scores ranged from 11-22 (mean 15.5 +2.7). The dose of r-tpa administered was 0.9 mg/kg. Results: Twenty one patients (65.6%) showed significant improvement on the NIHSS score, at 48 h (4 points). (Mean change = 10; range = 4-17). At one month, 25 (78%) recorded improvement on the Barthel index (mean change = 45%). One developed frontal lobe hemorrhage and another developed recurrent stroke; one died of aspiration; and four showed no improvement. Modified Rankin score (m RS) was administered at the end of three months to 28 patients (90%); however, the rest could not be directly observed. The average modified Rankin Score was 1.2 (0-2). Conclusions: Hyperacute thrombolysis was found feasible and effective in selected patients with AIS from western Utter Pradesh and who had poor affordability.

Abstract: Background: Portal vein thrombosis is a frequent complication in liver cirrhosis. Encouraging reports of systemic thrombolysis in non-cirrhotic patients suffering from acute portal vein thrombosis led us to start a pilot study on the efficacy and safety of systemic low dose recombinant tissue plasminogen activator (Actilyse®, Boheringer Ingelheim, Florence, Italy). Patients: Nine cirrhotic patients (6 males and 3 females) with recent portal vein thrombosis were enrolled. Exclusion criteria were portal cavernomatosis, recent (30 days) surgery, active bleeding, hepatocellular carcinoma and cancer in other sites. Methods: All cases were treated for a maximum of 7 days by continuous i.v. infusion of 0.25mg/kg/die of r-tPA plus subcutaneous low molecular weight heparin. Efficacy was evaluated by colour doppler sonography monitoring and confirmed by contrast enhanced computerized tomography. Results: The combined r-tPA/LMWH treatment was well tolerated without clinically significant side effects. Complete resolution of thrombosis occurred in 4 cases, partial regression in 4 and none in 1. Retreatment of a complete recurrence in 1 patient was successful. Variceal pressure dropped from 30.7±4.5mmHg to 21.2±6.6mmHg (p =0.012). Conclusions: Our preliminary data demonstrate that thrombolytic treatment of recent portal vein thrombosis with i.v. r-tPA and LMWH in patients with cirrhosis appears to be safe and effective and can significantly reduce pressure in oesophageal varices. [Copyright &y& Elsevier]

Our objective was to identify the outcome of patients treated with tissue plasminogen activator (r-tPa) in Pakistan and compare these data to available regional and international data. The charts of all patients treated with r-tPa for acute stroke at two centers in Pakistan (Aga Khan University, Karachi and Liaquat National hospital, Karachi) were retrospectively reviewed. We identified 21 patients. The utilization of tPa at Aga Khan Hospital was 18/1,185 patients (1.5%) from 2005 to 2007 while at Liaquat National Hospital was 3/575 patients (0.52%) over 1 year (2007). Mean time interval between stroke onset and start of r-tPa infusion was 169 min. Three patients (14%) developed fatal hemorrhage and two (10%) developed non-fatal hemorrhage. Four patients (19%) died. We identified protocol violations in seven patients (33%). In conclusion, the utilization of thrombolytic therapy is low and complication rate is high. Interventions for training physicians are needed. [ABSTRACT FROM AUTHOR]