ObjectiveTo systematically review the early clinical prediction value of machine learning (ML) for cardiac arrest (CA).MethodsPubMed, EMbase, WanFang Data and CNKI databases were electronically searched to retrieve all ML studies on predicting CA from January 2015 to February 2021. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies. The value of each model was evaluated based on the area under receiver operating characteristic curve (AUC) and accuracy.ResultsA total of 38 studies were included. In terms of data sources, 13 studies were based on public database, and other studies retrospectively collected clinical data, in which 21 directly predicted CA, 3 predicted CA-related arrhythmias, and 9 predicted sudden cardiac death. A total of 51 models had been adopted, among which the most popular ML methods included artificial neural network (n=11), followed by random forest (n=9) and support vector machine (n=5). The most frequently used input feature was electrocardiogram parameters (n=20), followed by age (n=12) and heart rate variability (n=10). Six studies compared the ML models with other traditional statistical models and the results showed that the AUC value of ML was generally higher than that in traditional statistical models.ConclusionsThe available evidence suggests that ML can accurately predict the occurrence of CA, and the performance is significantly superior to traditional statistical model in certain cases.
Objective To investigate multi-slice spiral CT (MSCT) and MRI features of stasis cirrhosis and the diagnostic value of MSCT and MRI. Methods MSCT and MRI findings of 35 patients with stasis cirrhosis were studied. The size of liver and spleen, the diameter of hepatic vein (HV), enhancement pattern of liver parenchyma, contrast medium reflux in inferior vena cava (IVC) and (or) HV, ascites, number of varices and correlated abnormalities were reviewed. Results The volume index of liver and spleen of 35 patients was 4434.95 cm3 and 621.92 cm3 respectively. The mean diameter of HV of 27 patients (77.1%) was 3.61 cm and HV of other 8 patients (22.9%) were too small to show. Number of patients showed waves of borderline, inhomogeneous pattern of parenchymal contrast enhancement, contrast medium reflux in IVC and (or) HV, varices and ascites was 5 (14.3%), 29 (82.9%), 20 (57.1%), 16 (45.7%), and 6 (17.1%), respectively. Correlated abnormalities included cardiac enlargement 〔4 cases (11.4%)〕, pericardium thickening 〔11 cases (31.4%)〕, and pericardial effusion 〔2 cases (5.7%)〕. Conclusions Stasis cirrhosis mainly demonstrate liver enlargement, inhomogeneous pattern of parenchymal contrast enhancement, contrast medium reflux in IVC and (or) HV, and slight portal hypertension. MSCT and MRI play invaluable roles in diagnosis, differential diagnosis and etiological diagnosis of stasis cirrhosis.
Aortic stenosis accounts for a large proportion of valvular heart disease in China. This article described an unusual case of severe aortic stenosis with severe cardiopulmonary decompensation treated by emergency transcatheter aortic valve replacement. Preoperative assessment was performed by transesophageal echocardiography. The extracorporeal membrane oxygenation team was informed to be ready. During the operation, no obvious perivalve leakage was observed after valve released. The transvalvular pressure gradient decreased to 7 mm Hg (1 mm Hg=0.133 kPa).The patient’s symptoms were completely relieved after the operation, and no adverse events occurred during the hospitalization. After discharge, color Doppler echocardiography showed that stenosis was eliminated, cardiac function was improved, no significant perivalvular leakage was observed, and pulmonary hypertension reduced to moderate. The success of this operation confirmed the efficacy of emergency transcatheter aortic valve replacement, and showed that after a rigorous evaluation, emergency transcatheter aortic valve replacement may be a reasonable choice for patients with severe aortic valve stenosis.
Objective To investigate the effects of noninvasive positive pressure ventilation (NPPV) on patients with acute left heart failure. Methods Twenty patients with acute left heart failure diagnosed between September 2013 and July 2014 were randomized into treatment group (n=10) and control group (n=10). Both groups used conventional sedations, diuretics and drugs that strengthened the heart and dilated the vessels, while early use of NPPV was applied in the experimental group. Arterial blood gas analysis [pH value, pressure of arterial carbon dioxide (PaCO2), and pressure of arterial oxygen (PaO2)], heart rate (HR), respiration, duration of Intensive Care Unit (ICU) stay and invasive mechanical ventilation, duration of overall mechanical ventilation, and success case numbers before and two hours after treatment were observed and analyzed. Results For the control group, two hours after treatment, PaO2 was (67.0±8.5) mm Hg (1 mm Hg=0.133 kPa), HR was (124±10) times/min, Respiration was (34±4) times/min, the duration of ICU stay was (6.0±1.1) days, invasive ventilation was for (32.0±3.1) hours, and the total time of mechanical ventilation was (32.0±3.1) hours. Those indexes for the treatment group two hours after treatment were: PaO2, (82.3±8.9) mm Hg; HR, (98±11) times/min; respiration, (24±4) times/min; the duration of ICU stay, (4.0±0.8) days; invasive ventilation time, (16.0±1.3) hours; the total time of mechanical ventilation, (26.0±1.8) hours. All the differences for each index between the two groups were statistically significant (P < 0.05). Conclusion Early application of NPPV can rapidly relieve clinical symptoms and reduce the medical cost for patients with acute left heart failure.
Objective To explore the clinical effects of emergency transcatheter aortic replacement (TAVR) on the treatment of patients with acute refractory heart failure or cardiogenic shock secondary to severe aortic stenosis during hospitalization. Methods The study selected 44 patients from 8 heart valve centers from January 2018 to January 2021. All patients received emergency TAVR treatment. The patients’ baseline clinical data, cardiac ultrasound indicators, and postoperative hospital stay were collected. Paired t-test and McNemar test were used to compare and analyze the preoperative and postoperative cardiac ultrasound indexes, moderate to severe aortic stenosis, and cardiac function. Results The average age of the patients was (72.0±7.9) years. Valve displacement occurred in one patient during the operation, and the surgical success rate was 97.7%. Four cases died during hospitalization, and the mortality rate was 9.1%. The median length of hospital stay was 11.5 d. The postoperative aortic valve area was significantly higher than that before surgery [(0.5±0.2) vs. (3.8±1.6) mm2, P<0.05], the mean transvalvular pressure of the aortic valve was significantly lower than that before operation [(64.0±24.9) vs. (11.3±4.6) mm Hg (1 mm Hg=0.133 kPa), P<0.05], the peak aortic flow velocity was significantly lower than that before operation [(4.5±0.7) vs. (1.9±0.7) m/s, P<0.05], the left ventricular end diastolic inner diameter was lower than that before operation [(59.0±7.2) vs. (56.1±7.3) mm, P<0.05], the left ventricular ejection fraction increased significantly compared with that before operation [(30.1±10.4)% vs. (40.9±11.0)%, P<0.05], and the cardiac function improved significantly compared with that before operation (P<0.05). During the operation, 2 cases (4.5%) underwent valve-in-valve implantation, 11 cases (25.0%) underwent percutaneous coronary intervention during the same period. During the postoperative hospital stay, 1 case (2.3%) developed stroke, 3 cases (6.8%) experienced severe bleeding, 5 cases (11.4%) had severe vascular complications, 2 cases (4.5%) experienced acute myocardial infarction, 30 cases (68.2%) had small or trace paravalvular regurgitation, 3 cases (6.8%) received permanent pacemaker implantation, and 5 cases (11.4%) developed acute kidney injury. Conclustion Emergency TAVR is an effective and feasible treatment plan for patients with acute refractory heart failure or cardiogenic shock secondary to severe aortic stenosis.
Objective To investigate the clinical efficacy and safety of intravenous thrombolysis bridging endovascular thrombectomy (EVT) in patients with acute cardioembolic stroke. Methods We retrospectively included patients with cardioembolic stroke who were admitted within 24 h after onset of stroke symptoms and had received EVT in the Department of Neurology, West China Hospital of Sichuan University between January 2017 and December 2021. Based on whether they had received intravenous thrombolysis, the patients were divided into bridging therapy group and direct EVT group. The primary outcome was unfavorable outcome by 3 months, defined as a modified Rankin Scale (mRS) score of 3 to 6. The secondary outcomes included intracranial hemorrhage during hospitalization and 3-month death. Multivariable logistic regression was performed to assess the treatment effect on the primary outcome after adjusting for confounding factors. Results A total of 285 patients were enrolled. Among them, 174 (61.1%) were female, the median age was 74 years (interquartile range 64-80 years), and the median time from stroke onset to admission was 4.0 h (interquartile range 3.0-5.0 h). Compared to patients in the direct EVT group (n=202), patients in the bridging therapy group (n=83) had a lower rate of unfavorable functional outcome (55.4% vs 68.3%, P=0.039) by 3 months, while the incidences of intracranial hemorrhage (47.0% vs. 39.6%, P=0.251) and 3-month death (20.5% vs. 30.7%, P=0.080) were comparable between the two groups. After adjusting for confounding factors, the bridging therapy improved 3-month functional outcomes over direct EVT [odds ratio=0.482, 95% confidence interval (0.249, 0.934), P=0.031]. Conclusion In patients with acute cardioembolic stroke, intravenous thrombolysis bridging endovascular treatment can significantly improve 3-month functional outcomes without increasing the risk of intracranial hemorrhage.