Association of Tranexamic Acid Administration With Mortality and Thromboembolic Events in Patients With Traumatic Injury: A Systematic Review and Meta-analysis
Karl V, Thorn S, Mathes T, Hess S, Maegele M
JAMA network open. 2022;5(3):e220625
IMPORTANCE Tranexamic acid is widely available and used off-label in patients with bleeding traumatic injury, although the literature does not consistently agree on its efficacy and safety. OBJECTIVE To examine the association of tranexamic acid administration with mortality and thromboembolic events compared with no treatment or with placebo in patients with traumatic injury in the literature. DATA SOURCES On March 23, 2021, PubMed, Embase, and the Cochrane Library were searched for eligible studies published between 1986 and 2021. STUDY SELECTION Randomized clinical trials and observational studies investigating tranexamic acid administration compared with no treatment or placebo among patients with traumatic injury and traumatic brain injury who were 15 years or older were included. Included studies were published in English or German. The electronic search yielded 1546 records, of which 71 were considered for full-text screening. The selection process was performed independently by 2 reviewers. DATA EXTRACTION AND SYNTHESIS The study followed the Cochrane Handbook for Systematic Reviews of Interventions and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Data were extracted by 2 independent reviewers and pooled using the inverse-variance random-effects model. MAIN OUTCOMES AND MEASURES Outcomes were formulated before data collection and included mortality at 24 hours and 28 and 30 days (1 month) as well as the incidence of thromboembolic events and the amount of blood products administered. Owing to missing data, overall mortality was added and the amount of blood products administered was discarded. RESULTS Thirty-one studies with a total of 43 473 patients were included in the systematic review. The meta-analysis demonstrated that administration of tranexamic acid was associated with a significant decrease in 1-month mortality compared with the control cohort (risk ratio, 0.83 [95% CI, 0.71-0.97]; I2 = 35%). The results of meta-analyses for 24-hour and overall mortality and thromboembolic events were heterogeneous and could not be pooled. Further investigations on clinical heterogeneity showed that populations with trauma and trial conditions differed markedly. CONCLUSIONS AND RELEVANCE These findings suggest that tranexamic acid may be beneficial in various patient populations with trauma. However, reasonable concerns about potential thromboembolic events with tranexamic acid remain.
Convolutional neural network performance compared to radiologists in detecting intracranial hemorrhage from brain computed tomography: A systematic review and meta-analysis
Daugaard Jørgensen M, Antulov R, Hess S, Lysdahlgaard S
European journal of radiology. 2021;146:110073
PURPOSE To compare the diagnostic accuracy of convolutional neural networks (CNN) with radiologists as the reference standard in the diagnosis of intracranial hemorrhages (ICH) with non contrast computed tomography of the cerebrum (NCTC). METHODS PubMed, Embase, Scopus, and Web of Science were searched for the period from 1 January 2012 to 20 July 2020; eligible studies included patients with and without ICH as the target condition undergoing NCTC, studies had deep learning algorithms based on CNNs and radiologists reports as the minimum reference standard. Pooled sensitivities, specificities and a summary receiver operating characteristics curve (SROC) were employed for meta-analysis. RESULTS 5,119 records were identified through database searching. Title-screening left 47 studies for full-text assessment and 6 studies for meta-analysis. Comparing the CNN performance to reference standards in the retrospective studies found a pooled sensitivity of 96.00% (95% CI: 93.00% to 97.00%), pooled specificity of 97.00% (95% CI: 90.00% to 99.00%) and SROC of 98.00% (95% CI: 97.00% to 99.00%), and combining retrospective and studies with external datasets found a pooled sensitivity of 95.00% (95% CI: 91.00% to 97.00%), pooled specificity of 96.00% (95% CI: 91.00% to 98.00%) and a pooled SROC of 98.00% (95% CI: 97.00% to 99.00%). CONCLUSION This review found the diagnostic performance of CNNs to be equivalent to that of radiologists for retrospective studies. Out-of-sample external validation studies pooled with retrospective studies found CNN performance to be slightly worse. There is a critical need for studies with a robust reference standard and external data-set validation.