-
1.
Systematic Review of Artificial Intelligence for Abnormality Detection in High-volume Neuroimaging and Subgroup Meta-analysis for Intracranial Hemorrhage Detection
Agarwal, S., Wood, D., Grzeda, M., Suresh, C., Din, M., Cole, J., Modat, M., Booth, T. C.
Clinical neuroradiology. 2023;:1-14
Abstract
PURPOSE Most studies evaluating artificial intelligence (AI) models that detect abnormalities in neuroimaging are either tested on unrepresentative patient cohorts or are insufficiently well-validated, leading to poor generalisability to real-world tasks. The aim was to determine the diagnostic test accuracy and summarise the evidence supporting the use of AI models performing first-line, high-volume neuroimaging tasks. METHODS Medline, Embase, Cochrane library and Web of Science were searched until September 2021 for studies that temporally or externally validated AI capable of detecting abnormalities in first-line computed tomography (CT) or magnetic resonance (MR) neuroimaging. A bivariate random effects model was used for meta-analysis where appropriate. This study was registered on PROSPERO as CRD42021269563. RESULTS Out of 42,870 records screened, and 5734 potentially eligible full texts, only 16 studies were eligible for inclusion. Included studies were not compromised by unrepresentative datasets or inadequate validation methodology. Direct comparison with radiologists was available in 4/16 studies and 15/16 had a high risk of bias. Meta-analysis was only suitable for intracranial hemorrhage detection in CT imaging (10/16 studies), where AI systems had a pooled sensitivity and specificity 0.90 (95% confidence interval [CI] 0.85-0.94) and 0.90 (95% CI 0.83-0.95), respectively. Other AI studies using CT and MRI detected target conditions other than hemorrhage (2/16), or multiple target conditions (4/16). Only 3/16 studies implemented AI in clinical pathways, either for pre-read triage or as post-read discrepancy identifiers. CONCLUSION The paucity of eligible studies reflects that most abnormality detection AI studies were not adequately validated in representative clinical cohorts. The few studies describing how abnormality detection AI could impact patients and clinicians did not explore the full ramifications of clinical implementation.
-
2.
A systematic review on viscoelastic testing in subarachnoid haemorrhage patients
Tjerkstra, M. A., Wolfs, A. E., Verbaan, D., Vandertop, W. P., Horn, J., Müller, M. C. A., Juffermans, N. P.
World Neurosurgery. 2023
Abstract
OBJECTIVES Bleeding and thromboembolic complications frequently occur following subarachnoid haemorrhage (SAH) and substantially contribute to poor outcome. Viscoelastic testing could be used for detection of coagulopathies following SAH. This review summarizes literature on the utility of viscoelastic testing to detect coagulopathy in SAH patients and explores whether viscoelastic parameters are associated with SAH-related complications and clinical outcome. MATERIALS AND METHODS PUBMED, EMBASE and Google Scholar were systematically searched on August 18(th), 2022. Two authors independently selected studies which performed viscoelastic testing in SAH patients and assessed the quality of studies using the Newcastle Ottawa Scale or a previously published framework for quality assessment. Data was meta-analysed if methodologically possible. RESULTS The search yielded 19 studies (1160 SAH patients). Pooling of data including all relevant studies was not possible for any of the outcome measurements due to methodological differences. Thirteen of 19 studies evaluated the association of coagulation profiles and SAH, of which 11 studies showed a hypercoagulable profile. Rebleeding was associated with platelet dysfunction, deep venous thrombosis was associated with faster clot initiation and both delayed cerebral ischemia and poor outcome were associated with increased clot strength. CONCLUSIONS This explorative review shows that SAH patients frequently have a hypercoagulable profile. TEG- and ROTEM-parameters are associated with rebleeding, delayed cerebral ischemia, deep venous thrombosis and poor clinical outcome after SAH, however more research on the subject is needed. Future studies should focus on determining the optimal time frame and cut-off values for TEG or ROTEM to predict these complications.
-
3.
Can Artificial Intelligence Be Applied to Diagnose Intracerebral Hemorrhage under the Background of the Fourth Industrial Revolution? A Novel Systemic Review and Meta-Analysis
Zhao K, Zhao Q, Zhou P, Liu B, Zhang Q, Yang M
International journal of clinical practice. 2022;2022:9430097
Abstract
AIM: We intended to provide the clinical evidence that artificial intelligence (AI) could be used to assist doctors in the diagnosis of intracerebral hemorrhage (ICH). METHODS Studies published in 2021 were identified after the literature search of PubMed, Embase, and Cochrane. Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) was used to perform the quality assessment of studies. Data extraction of diagnosis effect included accuracy (ACC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV), area under curve (AUC), and Dice scores (Dices). The pooled effect with its 95% confidence interval (95%CI) was calculated by the random effects model. I-Square (I (2)) was used to test heterogeneity. To check the stability of the overall results, sensitivity analysis was conducted by recalculating the pooled effect of the remaining studies after omitting the study with the highest quality or the random effects model was switched to the fixed effects model. Funnel plot was used to evaluate publication bias. To reduce heterogeneity, recalculating the pooled effect of the remaining studies after omitting the study with the lowest quality or perform subgroup analysis. RESULTS Twenty-five diagnostic tests of ICH via AI and doctors with overall high quality were included. Pooled ACC, SEN, SPE, PPV, NPV, AUC, and Dices were 0.88 (0.83∼0.93), 0.85 (0.81∼0.89), 0.90 (0.88∼0.92), 0.80 (0.75∼0.85), 0.93 (0.91∼0.95), 0.84 (0.80∼0.89), and 0.90 (0.85∼0.95), respectively. There was no publication bias. All of results were stable as revealed by sensitivity analysis and were accordant as outcomes via subgroups analysis. CONCLUSION Under the background of the fourth industrial revolution, AI might be an effective and efficient tool to assist doctors in the clinical diagnosis of ICH.
-
4.
Causes and Risk Factors of Pediatric Spontaneous Intracranial Hemorrhage-A Systematic Review
Ciochon UM, Bindslev JBB, Hoei-Hansen CE, Truelsen TC, Larsen VA, Nielsen MB, Hansen AE
Diagnostics (Basel, Switzerland). 2022;12(6)
Abstract
Previous studies suggest that the most common cause of spontaneous intracerebral hemorrhage in children and adolescents is arteriovenous malformations (AVMs). However, an update containing recently published data on pediatric spontaneous intracranial hemorrhages is lacking. The aim of this study is to systematically analyze the published data on the etiologies and risk factors of pediatric spontaneous intracranial hemorrhage. This systematic review was performed in compliance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. A search in PubMed, Embase, Scopus, Web of Science and Cochrane Library was conducted aiming for articles published in year 2000 and later, containing data on etiology and risk factors of spontaneous intracranial hemorrhages in unselected cohorts of patients aged between 1 month and 18 years. As a result, forty studies were eligible for data extraction and final analysis. These included 7931 children and adolescents with 4009 reported etiologies and risk factors. A marked variety of reported etiologies and risk factors among studies was observed. Vascular etiologies were the most frequently reported cause of pediatric spontaneous intracranial hemorrhages (n = 1727, 43.08% of all identified etiologies or risk factors), with AVMs being the most common vascular cause (n = 1226, 70.99% of all vascular causes). Hematological and systemic causes, brain tumors, intracranial infections and cardiac causes were less commonly encountered risk factors and etiologies.
-
5.
Thromboelastography-Guided Therapy Enhances Patient Blood Management in Cirrhotic Patients: A Meta-analysis Based on Randomized Controlled Trials
Hartmann J, Dias JD, Pivalizza EG, Garcia-Tsao G
Seminars in thrombosis and hemostasis. 2022
-
-
-
Free full text
-
Full text
-
Editor's Choice
Abstract
Patients with cirrhosis often have abnormal hemostasis, with increased risk of hemorrhage and thrombosis. Thromboelastography provides a rapid assessment of the coagulation status and can guide product transfusions in adult patients with cirrhosis. This study aimed to determine whether the use of thromboelastography in adult patients with cirrhosis decreases blood product use and impacts adverse events or mortality compared with standard practice. A registered (PROSPERO CRD42020192458) systematic review and meta-analysis was conducted for randomized controlled trials (RCTs) comparing thromboelastography-guided hemostatic management versus standard practice (control). Co-primary outcomes were the number of transfused platelet units and fresh frozen plasma (FFP) units. Secondary outcomes were mortality, adverse events, utilization of individual blood products, blood loss or excessive bleeding events, hospital/intensive care unit stay, and liver transplant/intervention outcomes. The search identified 260 articles, with five RCTs included in the meta-analysis. Platelet use was five times lower with thromboelastography versus the control, with a relative risk of 0.17 (95% confidence interval [CI]: [0.03-0.90]; p = 0.04), but FFP use did not differ significantly. Thromboelastography was associated with less blood product (p < 0.001), FFP + platelets (p < 0.001), and cryoprecipitate (p < 0.001) use. No differences were reported in bleeding rates or longer term mortality between groups, with the thromboelastography group having lower mortality at 7 days versus the control (relative risk [95% CI] = 0.52 [0.30-0.91]; p = 0.02). Thromboelastography-guided therapy in patients with cirrhosis enhances patient blood management by reducing use of blood products without increasing complications.
PICO Summary
Population
Patients with cirrhosis (5 studies, n= 302).
Intervention
Thromboelastography-guided haemostatic management.
Comparison
Standard coagulation testing (standard practice).
Outcome
Platelet use was five times lower with thromboelastography vs. standard practice, with a relative risk of 0.17 (95% confidence interval [CI]: [0.03-0.90]), but fresh frozen plasma (FFP) use did not differ significantly. Thromboelastography was associated with less blood product, FFP + platelets, and cryoprecipitate use. No differences were reported in bleeding rates or longer-term mortality between groups, with the thromboelastography group having lower mortality at 7 days vs. standard practice (relative risk [95% CI] = 0.52 [0.30-0.91]).
-
6.
Systematic review and meta-analysis: incidence of variceal hemorrhage in patients with cirrhosis undergoing transesophageal echocardiography
Odewole M, Sen A, Okoruwa E, Lieber SR, Cotter TG, Nguyen AD, Mufti A, Singal AG, Rich NE
Alimentary pharmacology & therapeutics. 2022
Abstract
BACKGROUND The presence of esophageal varices is considered a relative contraindication to transesophageal echocardiography (TEE) by cardiology professional societies, so gastroenterologists are often consulted to perform upper endoscopy prior to TEE in patients with cirrhosis. AIM: To perform a systematic review to quantify the risk of bleeding complications in patients with cirrhosis following TEE. METHODS Two reviewers searched Ovid MEDLINE, MEDLINE In-Process and EMBASE databases from January 1992 to May 2021 for studies reporting bleeding complications from TEE in patients with cirrhosis. We calculated the pooled incidence rate of bleeding events using the metaprop command with a random effect model. RESULTS We identified 21 studies comprising 4050 unique patients with cirrhosis; 9 studies (n = 3015) assessed the risk of intraoperative TEE during liver transplant (LT) and 12 studies (n = 1035) assessed bleeding risk in patients undergoing TEE for other indications. The pooled incidence of bleeding post-TEE was 0.37% (95% CI 0.04-0.94%) across all studies. Bleeding complications were low among patients undergoing TEE during LT as well as those undergoing TEE for other diagnostic reasons (0.97% vs. 0.004%) and among studies with mean MELD >18 compared to those with mean MELD <18 (0.43% vs. 0.08%). Few studies had a comparator arm, and data on patient-level factors impacting bleeding complications (including degree of liver dysfunction and coagulopathy) were limited across studies. CONCLUSIONS The risk of bleeding complications following TEE is low in patients with cirrhosis, suggesting TEE is safe and risk stratification with upper endoscopy may not be necessary.
-
7.
Viscoelastic Testing Prior to Non-surgical Procedures Reduces Blood Product Use Without Increasing Bleeding Risk in Cirrhosis
Shenoy, A., Louissaint, J., Shannon, C., Tapper, E. B., Lok, A. S.
Digestive Diseases and Sciences. 2022;67(11):5290-5299
Abstract
BACKGROUND/AIMS: Thromboelastography (TEG) and Rotational Thromboelastometry (ROTEM) analyze hemostatic function in patients with coagulopathy. We sought to quantify the impact of TEG and ROTEM-guided transfusion algorithms on blood product utilization in patients with cirrhosis undergoing non-surgical procedures. METHODS We performed a systematic review and meta-analysis on the utility of viscoelastic testing prior to non-surgical procedures to determine their impact on pre-procedural blood product use and post-procedural bleeding events. Studies comparing TEG or ROTEM-guided transfusions with standard-of-care (SOC) prior to non-surgical procedures in adult patients with cirrhosis were included. Primary outcomes were fresh frozen plasma (FFP) and platelet transfusion and secondary outcomes of post-procedure bleeding, transfusion-related complications, and mortality; and were reported as standardized mean differences (SMD) and risk ratios (RR). RESULTS Six studies (five randomized controlled trials and one cohort study) involving 367 patients met inclusion criteria. Compared with SOC, TEG/ROTEM-guided transfusions led to an overall decreased number of patients who received FFP transfusions (SMD = -0.93, 95% CI [-1.54, -0.33], p < 0.001) and platelets transfusions (SMD = -1.50, CI [-1.85, -1.15], p < 0.001). Total amount of FFP (SMD-0.86, p < 0.001) and platelet (SMD = -0.99, p < 0.001) transfused in the TEG/ROTEM group were also lower. Decreased pre-procedure transfusion in the TEG/ROTEM group did not result in increased post-procedure bleeding (RR = 0.61, p = 0.09) or in mortality (RR = 0.91, p = 0.93). CONCLUSION In patients with cirrhosis, TEG or ROTEM significantly reduces blood product utilization prior to non-surgical procedures, with no increase in post-procedure bleeding or mortality. TEG and ROTEM utilization can promote high-value care and improve transfusion stewardship in this population.
-
8.
Relationship between annualized case volume and in-hospital motality in subarachnoid hemorrhage: A systematic review and meta-analysis
Huang JY, Lin HY, Wei QQ, Pan XH, Liang NC, Gao W, Shi SL
Medicine. 2021;100(48):e27852
-
-
Free full text
-
Abstract
Studies on the relationship between hospital annualized case volume and in-hospital mortality in patients with subarachnoid hemorrhage (SAH) have shown conflicting results. Therefore, we performed a meta-analysis to further examine this relationship.The authors searched the PubMed and Embase databases from inception through July 2020 to identify studies that assessed the relationship between hospital annualized SAH case volume and in-hospital SAH mortality. Studies that reported in-hospital mortality in SAH patients and an adjusted odds ratio (OR) comparing mortality between low-volume and high-volume hospitals or provided core data to calculate an adjusted OR were eligible for inclusion. No language or human subject restrictions were imposed.Five retrospective cohort studies with 46,186 patients were included for analysis. The pooled estimate revealed an inverse relationship between annualized case volume and in-hospital mortality (OR, 0.53; 95% confidence interval, 0.42-0.68, P < .0001). This relationship was consistent in almost all subgroup analyses and was robust in sensitivity analyses.This meta-analysis confirms an inverse relationship between hospital annualized SAH case volume and in-hospital SAH mortality. Higher annualized case volume was associated with lower in-hospital mortality.
-
9.
Computer-Aided Diagnosis of Gastrointestinal Ulcer and Hemorrhage Using Wireless Capsule Endoscopy: Systematic Review and Diagnostic Test Accuracy Meta-analysis
Bang CS, Lee JJ, Baik GH
Journal of medical Internet research. 2021;23(12):e33267
Abstract
BACKGROUND Interpretation of capsule endoscopy images or movies is operator-dependent and time-consuming. As a result, computer-aided diagnosis (CAD) has been applied to enhance the efficacy and accuracy of the review process. Two previous meta-analyses reported the diagnostic performance of CAD models for gastrointestinal ulcers or hemorrhage in capsule endoscopy. However, insufficient systematic reviews have been conducted, which cannot determine the real diagnostic validity of CAD models. OBJECTIVE To evaluate the diagnostic test accuracy of CAD models for gastrointestinal ulcers or hemorrhage using wireless capsule endoscopic images. METHODS We conducted core databases searching for studies based on CAD models for the diagnosis of ulcers or hemorrhage using capsule endoscopy and presenting data on diagnostic performance. Systematic review and diagnostic test accuracy meta-analysis were performed. RESULTS Overall, 39 studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of ulcers (or erosions) were .97 (95% confidence interval, .95-.98), .93 (.89-.95), .92 (.89-.94), and 138 (79-243), respectively. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of hemorrhage (or angioectasia) were .99 (.98-.99), .96 (.94-0.97), .97 (.95-.99), and 888 (343-2303), respectively. Subgroup analyses showed robust results. Meta-regression showed that published year, number of training images, and target disease (ulcers vs erosions, hemorrhage vs angioectasia) was found to be the source of heterogeneity. No publication bias was detected. CONCLUSIONS CAD models showed high performance for the optical diagnosis of gastrointestinal ulcer and hemorrhage in wireless capsule endoscopy.
-
10.
How outcomes are measured after spontaneous intracerebral hemorrhage: A systematic scoping review
Massicotte S, Lun R, Yogendrakumar V, Dewar B, Chung HS, Konder R, Yim H, Davis A, Fergusson D, Shamy M, et al
PloS one. 2021;16(6):e0253964
Abstract
BACKGROUND AND PURPOSE Recovery after intracerebral haemorrhage (ICH) is often slower than ischemic stroke. Despite this, ICH research often quantifies recovery using the same outcome measures obtained at the same timepoints as ischemic stroke. The primary objective of this scoping review is to map the existing literature to determine when and how outcomes are being measured in prospective studies of recovery after ICH. METHODS We searched MEDLINE, Embase, Cochrane Central Register of Controlled Trials and Web of Science from inception to November 2019, for prospective studies that included patients with ICH. Two investigators independently screened the studies and extracted data around timing and type of outcome assessment. RESULTS Among the 9761 manuscripts reviewed, 395 met inclusion criteria, of which 276 were observational studies and 129 were interventional studies that enrolled 66274 patients. Mortality was assessed in 93% of studies. Functional outcomes were assessed in 85% of studies. The most frequently used functional assessment tool was the modified Rankin Scale (mRS) (60%), followed by the National Institute of Health Stroke Severity Scale (22%) and Barthel Index (21%). The most frequent timepoint at which mortality was assessed was 90 days (41%), followed by 180 days (18%) and 365 days (12%), with 2% beyond 1 year. The most frequent timepoint used for assessing mRS was 90 days (62%), followed by 180 days (21%) and 365 days (17%). CONCLUSION While most prospective ICH studies report mortality and functional outcomes only at 90 days, a significant proportion do so at 1 year and beyond. Our results support the feasibility of collecting long-term outcome data to optimally assess recovery in ICH.