OBJECTIVE: To establish a machine learning model to predict the risk of early neurological deterioration (END) based on the clinical and laboratory data of patients with acute ischemic stroke (AIS) before intravenous thrombolysis. METHODS: The clinical data of AIS patients who received intravenous thrombolytic with recombinant tissue plasminogen activator (rt-PA) at the Stroke Center of the First Hospital of Qinhuangdao City from January 2019 to July 2022 were retrospectively analyzed. Patients were divided into END group and non-END group according to whether END appeared after intravenous thrombolytic. Clinical data of patients at admission were collected, including demographic characteristics, clinical evaluation, comorbidification, drug use history, laboratory tests, etc. Univariate and multivariate Logistic regression analysis were performed to screen out the independent predictors of the END of AIS patients after intravenous thrombolytic. The study subjects were randomly divided into a training set and a test set in a 7 : 3 ratio. Four machine learning prediction models, including Logistic regression (LR), K-nearest neighbor (KNN), support vector machine (SVM) and random forest (RF), were established based on independent predictors. The receiver operator characteristic curve (ROC curve) was used to evaluate the predictive ability of each model in END. RESULTS: A total of 704 patients were enrolled, of whom 99 were identified as END and 605 as non-END. Univariate and multivariate Logistic regression analysis was used to screen out the National Institutes of Health stroke scale [NIHSS, odds ratio (OR) = 1.049, 95% confidence interval (95%CI) was 1.015-1.082, P = 0.004], systolic blood pressure (OR = 1.013, 95%CI was 1.004-1.022, P = 0.004), lymphocyte percentage (LYM%, OR = 0.903, 95%CI was 0.853-0.953, P < 0.001), platelet to lymphocyte ratio (PLR, OR = 1.007, 95%CI was 1.002-1.014, P = 0.013) were the independent predictors of END in AIS patients after intravenous thrombolysis. The area under the curve (AUC) of LR, KNN, SVM, and RF machine learning models in the test dataset were 0.789 (95%CI was 0.675-0.902), 0.797 (95%CI was 0.685-0.910), 0.851 (95%CI was 0.751-0.952) and 0.809 (95%CI was 0.699-0.919), respectively. The RF model had the highest sensitivity (95.7%). The accuracy (0.736), specificity (72.0%) and AUC of SVM model were the highest, and its overall prediction ability was better than the other three models. CONCLUSIONS Machine learning models have a potential role in early predicting the risk of END after intravenous thrombolysis in AIS patients, and can provide help in clinical decision-making for intravenous thrombolysis.
Humans ; Tissue Plasminogen Activator/therapeutic use* ; Ischemic Stroke/drug therapy* ; Brain Ischemia ; Retrospective Studies ; Thrombolytic Therapy ; Stroke ; Fibrinolytic Agents/therapeutic use*

Objective To compare the clinical effects of three treatment methods including systemic thrombolysis(ST),catheter-directed thrombolysis(CDT),and AngioJet percutaneous mechanical thrombectomy(PMT)in acute lower extremity deep venous thrombosis(LEDVT). Methods The data of 82 patients diagnosed with LEDVT in the Department of Vascular and Gland Surgery of the First Affiliated Hospital of Hebei North University from January 2017 to December 2020 were collected.The patients were assigned into a ST group(n=50),a CDT group(n=16),and a PMT group(n=16)according to different treatment methods.The efficacy and safety were compared among the three groups. Results Compared with that before treatment,the circumferential diameter difference of both lower limbs on days 1,2,and 3 of treatment in the ST,CDT,and PMT groups reduced(all P<0.001).The PMT group showed smaller circumferential diameter difference of lower limbs on days 1,2,and 3 of treatment than the ST group(all P<0.001)and smaller circumferential diameter difference of the lower patellar margin on day 1 of treatment than the CDT group(P<0.001).The PMT group showed higher diminution rate for swelling of the affected limb at the upper and lower edges of the patella than the ST group(P<0.001)and higher diminution rate for swelling at the upper edge of the patella than the CDT group(P=0.026).The incidence of complications after treatment showed no significant differences among the three groups(all P>0.05).The median of hospital stay in the PMT group was shorter than that in the ST and CDT groups(P=0.002,P=0.001).The PMT group had higher thrombus clearance rate than the ST group(P=0.002)and no significant difference in the thrombus clearance rate from the CDT group(P=0.361).The vascular recanalization rates in the PMT(all P<0.001)and CDT(P<0.001,P=0.002,P=0.009)groups 3,6,and 12 months after treatment were higher than those in ST group,and there were no significant differences between PMT and CDT groups(P=0.341,P=0.210,P=0.341). Conclusions ST,CDT,and PMT demonstrated significant efficacy in the treatment of LEDVT,and PMT was superior to ST and CDT in terms of circumferential diameter difference of the lower limbs,diminution rate for swelling of the affected limb,thrombus clearance rate,length of hospital stay,and long-term vascular recanalization.There was no obvious difference in safety among the three therapies.
Humans ; Thrombolytic Therapy/methods* ; Fibrinolytic Agents/therapeutic use* ; Treatment Outcome ; Thrombectomy/methods* ; Venous Thrombosis/drug therapy* ; Lower Extremity/blood supply* ; Catheters ; Retrospective Studies

Objective: For patients with atrial fibrillation (AF) complicated with acute coronary syndrome (ACS), both anticoagulant and antiplatelet therapy should be applied, but the use of anticoagulation therapy is still poor in these patients in China. The purpose of this study was to explore the status and adherence of antithrombotic therapy in AF patients with ACS and the impact on 1 year clinical outcomes. Methods: Patients with AF hospitalized for ACS were retrospectively included from 6 tertiary hospitals in China between July 2015 and December 2020. According to the use of anticoagulant drugs at discharge, patients were divided into two groups: anticoagulant treatment group and non-anticoagulant treatment group. Logistic regression model was used to analyze the main factors influencing the use of anticoagulant drugs in patients with atrial fibrillation complicated with ACS. Major adverse cardiac events (MACEs) were defined as all-cause death, non-fatal myocardial infarction or coronary revascularization, and ischemic stroke and Bleeding Academic Research Consortium (BARC) 3 bleeding events were also collected at 1 year after discharge. After propensity score matching, Cox proportional hazards models and Kaplan-Meier analysis were used to evaluate the effect of anticoagulant treatment and non-anticoagulant treatment on 1-year prognosis. The patients were divided into different groups according to whether anticoagulation was performed at discharge and follow-up, and the sensitivity of the results was analyzed. Results: A total of 664 patients were enrolled, and 273 (41.1%) were treated with anticoagulant therapy, of whom 84 (30.8%) received triple antithrombotic therapy, 91 (33.3%) received double antithrombotic therapy (single antiplatelet combined with anticoagulant), and 98 (35.9%) received single anticoagulant therapy. Three hundred and ninety-one (58.9%) patients were treated with antiplatelet therapy, including 253 (64.7%) with dual antiplatelet therapy and 138 (35.3%) with single antiplatelet therapy. After 1∶1 propensity score matching between the anticoagulant group and the non-anticoagulant group, a total of 218 pairs were matched. Multivariate logistic regression analysis showed that history of diabetes, HAS-BLED score≥3, and percutaneous coronary intervention were predictors of the absence of anticoagulant therapy, while history of ischemic stroke and persistent atrial fibrillation were predictors of anticoagulant therapy. At 1-year follow-up, 218 patients (79.9%) in the anticoagulant group continued to receive anticoagulant therapy, and 333 patients (85.2%) in the antiplatelet group continued to receive antiplatelet therapy. At 1-year follow-up, 36 MACEs events (13.2%) occurred in the anticoagulant group, and 81 MACEs events (20.7%) in the non-anticoagulant group. HR values and confidence intervals were calculated by Cox proportional risk model. Patients in the non-anticoagulant group faced a higher risk of MACEs (HR=1.802, 95%CI 1.112-2.921, P=0.017), and the risk of bleeding events was similar between the two group (HR=0.825,95%CI 0.397-1.715, P=0.607). Conclusions: History of diabetes, HAS-BLED score≥3, and percutaneous coronary intervention are independent factors for the absence of anticoagulant therapy in patients with AF complicated with ACS. The incidence of MACEs, death and myocardial infarction is lower in the anticoagulant group, and the incidence of bleeding events is similar between the two groups. The risk of bleeding and ischemia/thrombosis should be dynamically assessed during follow-up and antithrombotic regiments should be adjusted accordingly.
Humans ; Atrial Fibrillation/drug therapy* ; Platelet Aggregation Inhibitors/adverse effects* ; Acute Coronary Syndrome/drug therapy* ; Fibrinolytic Agents/therapeutic use* ; Retrospective Studies ; Treatment Outcome ; Anticoagulants ; Myocardial Infarction/complications* ; Hemorrhage ; Percutaneous Coronary Intervention ; Ischemic Stroke/drug therapy* ; Stroke

Objective: To evaluate different methods' efficacy of controlling acute bleeding and managing long-term menstruation in patients with heavy menstrual bleeding (HMB) associated with antithrombotic therapy. Methods: The clinical data of 22 cases with HMB associated with antithrombotic therapy admitted to Peking University People's Hospital from January 2010 to August 2022 were analyzed, aged 39 years old (26-46 years). Changes in menstrual volume, hemoglobin (Hb), and quality of life were collected after control of acute bleeding and long-term menstrual management. Menstrual volume was assessed by pictorial blood assessment chart (PBAC), and quality of life was assessed by menorrhagia multi-attribute scale (MMAS). Results: (1) Treatment of acute bleeding: of the 22 cases with HMB associated with antithrombotic therapy, 16 cases were treated in our hospital and 6 in other hospital for emergency bleeding; of the 16 cases treated in our hospital, 3 underwent emergency intrauterine Foley catheter balloon compression due to severe bleeding (Hb decreased by 20 to 40 g/L within 12 hours). Of the 22 cases with antithrombotic therapy-related HMB, 15 (including 2 cases with severe bleeding) underwent emergency aspiration or endometrial resection, and intraoperative placement of levonorgestrel-releasing intrauterine system (LNG-IUS) followed by a significant reduction in bleeding volume; 3 cases had controlled acute bleeding after rivaroxaban dose reduction and continued observation; 2 cases were given gonadotropin-releasing hormone agonists to control acute bleeding in other hospital, of which 1 case was temporarily treated with periodic blood transfusion, and the other one patient underwent total hysterectomy; and 2 cases had temporary amenorrhea with oral mifepristone after intrauterine balloon compression or oral norethindrone. (2) Long-term menstrual management: of the 22 cases with antithrombotic therapy-related HMB, 15 had LNG-IUS placement and 12 had LNG-IUS placement for 6 months, and menstrual volume was significantly reduced [PBAC scores were 365.0 (272.5-460.0) vs 25.0 (12.5-37.5), respectively; Z=4.593, P<0.001], Hb was significantly increased [91.5 g/L (71.8-108.2 g/L) vs 128.5 g/L (121.2-142.5 g/L); Z=4.695, P<0.001], and quality of life was significantly improved [MMAS scores were 415.0 (327.5-472.5) vs 580.0 (570.0-580.0), respectively; Z=-3.062, P=0.002] before placement compared with 6 months after placement. Three rivaroxaban dose reduction patients' PBAC scores decreased by 20 to 35 but remained >100, and perceived quality of life did not change significantly. Two cases with temporary amenorrhea treated with oral mifepristone felt significantly improved quality of life, and the MMAS scores increased by 220 and 180, respectively. Conclusion: Intrauterine Foley catheter balloon compression, aspiration or endometrial ablation could be used to control acute bleeding in patients with antithrombotic therapy-related HMB, and LNG-IUS for long-term management could reduce menstrual volume, increase hemoglobin, and improve the quality of life of patients.
Female ; Humans ; Adult ; Menorrhagia/etiology* ; Fibrinolytic Agents/adverse effects* ; Levonorgestrel/adverse effects* ; Amenorrhea/drug therapy* ; Mifepristone/therapeutic use* ; Quality of Life ; Rivaroxaban/therapeutic use* ; Hemoglobins ; Intrauterine Devices, Medicated/adverse effects* ; Contraceptive Agents, Female

Humans ; Cardiovascular Diseases/drug therapy* ; Fibrinolytic Agents/therapeutic use* ; Hemorrhage ; Anticoagulants ; Platelet Aggregation Inhibitors

Humans ; Cardiovascular Diseases/drug therapy* ; Fibrinolytic Agents/therapeutic use* ; Hemorrhage ; Anticoagulants ; Platelet Aggregation Inhibitors

Acute Coronary Syndrome/drug therapy* ; Anticoagulants/therapeutic use* ; Coronary Disease/drug therapy* ; Drug Therapy, Combination ; Fibrinolytic Agents/therapeutic use* ; Humans ; Percutaneous Coronary Intervention ; Platelet Aggregation Inhibitors/therapeutic use*

Aortic Valve ; Aortic Valve Stenosis/surgery* ; China ; Consensus ; Fibrinolytic Agents/therapeutic use* ; Heart Valve Prosthesis ; Heart Valve Prosthesis Implantation ; Humans ; Risk Factors ; Transcatheter Aortic Valve Replacement ; Treatment Outcome

Cranial Sinuses ; Dilatation ; Fibrinolytic Agents/therapeutic use* ; Humans ; Sinus Thrombosis, Intracranial/therapy* ; Thrombolytic Therapy ; Treatment Outcome

Amputation ; Chronic Limb-Threatening Ischemia ; Fibrinolytic Agents/therapeutic use* ; Humans ; Limb Salvage ; Peripheral Arterial Disease ; Risk Factors ; Singapore ; Treatment Outcome