0
selected
-
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.
Quantification of blood loss for the diagnosis of postpartum hemorrhage: a systematic review and meta-analysis
Ruiz, M. T., Azevedo, N. F., Resende, C. V., Rodrigues, W. F., Meneguci, J., Contim, D., Wernet, M., Oliveira, C. J. F.
Revista brasileira de enfermagem. 2023;76(6):e20230070
Abstract
OBJECTIVE to compare the effectiveness of different diagnostic methods to estimate postpartum blood volume loss. METHODS a systematic review of effectiveness according to PRISMA and JBI Protocol. Searches in PubMed/MEDLINE, LILACS, Scopus, Embase, Web of Science and CINAHL, with descriptor "Postpartum Hemorrhage" associated with keyword "Quantification of Blood Loss". Tabulated extracted data, presented in metasynthesis and meta-analysis was applied to quantitative data. To assess risk of bias, JBI Appraisal Tools were applied. RESULTS fourteen studies were included, published between 2006 and 2021. Quantification of loss by any method was superior to visual estimation and is highly recommended, however the studies' high heterogeneity did not allow estimating this association. CONCLUSION the studies' high heterogeneity, with a probable margin of error given the uncontrolled factors, indicates the need for further studies, however quantification proved to be effective in relation to visual estimate. PROSPERO registration CRD 42021234486.
-
3.
The Recognition of Excessive blood loss At ChildbirTh (REACT) Study: A two-phase exploratory, sequential mixed methods inquiry using focus groups, interviews, and a pilot, randomised crossover study
Hancock A, Weeks AD, Furber C, Campbell M, Lavender T
BJOG : an international journal of obstetrics and gynaecology. 2021
-
-
-
-
Editor's Choice
Abstract
OBJECTIVES To explore how childbirth-related blood loss is evaluated and excessive bleeding recognised; and develop and test a theory of postpartum haemorrhage (PPH) diagnosis. DESIGN Two-phase, exploratory, sequential mixed methods design using focus groups, interviews and a pilot, randomised crossover study. SETTING Two hospitals in North West England. SAMPLE Women (following vaginal birth with and without PPH), birth partners, midwives and obstetricians. METHODS Phase 1 (qualitative): 8 focus groups and 20 one-to-one, semi-structured interviews were conducted with 15 women, 5 birth partners, 11 obstetricians, 1 obstetric anaesthetist and 19 midwives (n=51). Phase 2 (quantitative): 11 obstetricians and 10 midwives (n=21) completed two simulations of fast and slow blood loss using a high-fidelity childbirth simulator. RESULTS Responses to blood loss were described as automatic, intuitive reactions to the speed, nature and visibility of blood flow. Health professionals reported that quantifying volume was most useful after a PPH diagnosis, to validate intuitive decisions and guide on-going management. During simulations, PPH treatment was initiated at volumes at or below 200ml (fast mean blood loss 79.6ml, SD 41.1; slow mean blood loss 62.6ml, SD 27.7). All participants treated fast, visible blood loss, but only half treated slow blood loss, despite there being no difference in volumes (difference 18.2ml, 95% CI -5.6 to 42.2ml, p=0.124). CONCLUSIONS Experience and intuition, rather than blood loss volume, inform recognition of excessive blood loss after birth. Women and birth partners want more information and open communication about blood loss. Further research exploring clinical decision-making and how to support it is required.
PICO Summary
Population
Women following vaginal birth, birth partners, midwives and obstetricians in two centres in the UK (n= 51).
Intervention
Simulation of ‘slow blood loss followed by fast blood loss’ (n= 10).
Comparison
Simulation of ‘fast blood loss followed by slow blood loss’ (n= 11).
Outcome
This mixed methods study had a qualitative phase involving focus groups and interviews, and a quantitative phase consisting in a randomised crossover study. Responses to blood loss were described as automatic, intuitive reactions to the speed, nature and visibility of blood flow. Health professionals reported that quantifying volume was most useful after a postpartum haemorrhage (PPH) diagnosis, to validate intuitive decisions and guide on-going management. During simulations, PPH treatment was initiated at volumes at or below 200ml (fast mean blood loss 79.6ml, SD 41.1; slow mean blood loss 62.6ml, SD 27.7). All participants treated fast, visible blood loss, but only half treated slow blood loss, despite there being no difference in volumes (difference 18.2ml).
-
4.
Techniques for blood loss estimation in major non-cardiac surgery: a systematic review and meta-analysis
Tran A, Heuser J, Ramsay T, McIsaac DM, Martel G
Canadian journal of anaesthesia = Journal canadien d'anesthesie. 2020
-
-
-
Full text
-
Editor's Choice
Abstract
PURPOSE Estimated blood loss (EBL) is an important tool in clinical decision-making and surgical outcomes research. It guides perioperative transfusion practice and serves as a key predictor of short-term perioperative risks and long-term oncologic outcomes. Despite its widespread clinical and research use, there is no gold standard for blood loss estimation. We sought to systematically review and compare techniques for intraoperative blood loss estimation in major non-cardiac surgery with the objective of informing clinical estimation and research standards. SOURCE A structured search strategy was applied to Ovid Medline, Embase, and Cochrane Library databases from inception to March 2020, to identify studies comparing methods of intraoperative blood loss in adult patients undergoing major non-cardiac surgery. We summarized agreement between groups of pairwise comparisons as visual estimation vs formula estimation, visual estimation vs other, and formula estimation vs other. For each of these comparisons, we described tendencies for higher or lower EBL values, consistency of findings, pooled mean differences, standard deviations, and confidence intervals. PRINCIPLE FINDINGS We included 26 studies involving 3,297 patients in this review. We found that visual estimation is the most frequently studied technique. In addition, visual techniques tended to provide lower EBL values than formula-based estimation or other techniques, though this effect was not statistically significant in pooled analyses likely due to sample size limitations. When accounting for the contextual mean blood loss, similar case-to-case variation exists for all estimation techniques. CONCLUSIONS We found that significant case-by-case variation exists for all methods of blood loss evaluation and that there is significant disagreement between techniques. Given the importance placed on EBL, particularly for perioperative prognostication models, clinicians should consider the universal adoption of a practical and reproducible method for blood loss evaluation. TRIAL REGISTRATION PROSPERO (CRD42015029439); registered: 18 November 2015.PROSPERO (CRD42015029439); registered: 18 November 2015.
PICO Summary
Population
Adult patients undergoing major non-cardiac surgery (26 studies, n= 3,297).
Intervention
Visual estimation of blood loss.
Comparison
Formula estimation of blood loss, and other tecnniques for estimating blood loss.
Outcome
Visual estimation was the most frequently studied technique. Visual techniques tended to provide lower estimated blood loss values than formula-based estimation or other techniques, though this effect was not statistically significant in pooled analyses. When accounting for the contextual mean blood loss, similar case-to-case variation existed for all estimation techniques.
-
5.
The accuracy of aneurysm size in predicting rebleeding after subarachnoid hemorrhage: a meta-analysis
Yu Z, Zheng J, Guo R, Li M, Li H, Ma L, You C
Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology. 2020
Abstract
BACKGROUND Aneurysmal subarachnoid hemorrhage (SAH) is a severe cerebrovascular disease. Rebleeding is an independent predictor of unfavorable outcome after aneurysmal SAH. However, the accuracy of aneurysm size for predicting rebleeding after aneurysmal SAH is still unclear. Hence, we conducted this meta-analysis to evaluate the predictive accuracy of large aneurysm for rebleeding after SAH. METHODS We performed a literature search in PubMed and Embase. Original studies about aneurysm size and rebleeding after SAH were included. Two reviewers completed data extraction and quality assessment. Pooled sensitivity, specificity, and their 95% confidence intervals (CIs) of large aneurysm for predicting rebleeding were calculated and shown in a forest plot. The overall accuracy of large aneurysm for predicting rebleeding after SAH was shown using a summary receiver operating characteristic (SROC) curve. Publication bias were assessed using Deeks' funnel plot. RESULTS A total of ten studies with 3889 patients met eligibility criteria and were included in this meta-analysis. The pooled sensitivity and specificity of large aneurysm for predicting rebleeding were 0.39 (95% CI 0.25-0.56) and 0.75 (95% CI 0.67-0.82), respectively. The area under SROC curve was 0.67 (95% CI 0.62-0.71). Deeks' funnel plot did not show obvious publication bias among included studies in this meta-analysis. CONCLUSION The specificity of large aneurysm for predicting rebleeding after SAH is relatively high. However, its overall accuracy for predicting aneurysm rebleeding is not very satisfying. A comprehensive model should be developed to improve the accuracy of rebleeding prediction after SAH.
-
6.
The more you lose the more you miss: accuracy of postpartum blood loss visual estimation. A systematic review of the literature
Natrella, M., Di Naro, E., Loverro, M., Benshalom-Tirosh, N., Trojano, G., Tirosh, D., Besser, L., Loverro, M. T., Mastrolia, S. A.
The Journal of Maternal-Fetal & Neonatal Medicine : the official journal of the European Association of Perinatal Medicine, the Federation of Asia and Oceania Perinatal Societies, the International Society of Perinatal Obstetricians. 2018;31(1):106-115
Abstract
Midwives and nurses have a key role in monitoring postpartum period. They represent the first line professional figure in quantifying blood loss, initiating early diagnosis of obstetric hemorrhage, and mobilizing a team response, if needed. These actions are crucial in determining maternal outcome in postpartum hemorrhage (PPH). In our review we aimed to: (1) Provide a picture of PPH including its pathophysiology, epidemiology, and associated complications; (2) Discuss diagnosis of this dangerous postpartum event; and, (3) Especially evaluate the efficiency of the employment of visual blood loss estimation as a rapid way to suspect PPH and activate the patient assessment.
-
7.
A systematic review of definitions and reporting of bleeding outcome measures in haemophilia
Chai-Adisaksopha, C., Hillis, C., Thabane, L., Iorio, A.
Haemophilia : The Official Journal of the World Federation of Hemophilia. 2015;21(6):731-5
Abstract
INTRODUCTION Bleeding frequency is an important outcome commonly used in haemophilia studies. There is a variation in practice in how bleeding is measured and defined. AIM: The primary objective of this study was to determine how investigators define and report bleeding outcome measures. METHODS MEDLINE, EMBASE and the CENTRAL were searched from January 1990 to January 2014. We retrieved all published studies that included patients with haemophilia A or B and reported some measures of bleeding. Two reviewers independently performed title and abstract screening, full-text review and data abstraction of the identified studies. RESULTS A total of 118 studies fulfilled the inclusion criteria. Study designs were randomized controlled trials (RCT; 14%), cohort (68%), cross-sectional (5%) and others design (11%). The median duration of follow-up (Q1, Q3) was 20 (7.9, 50) months. We found 10 different bleeding outcomes reported [absolute number of bleeding 60 (50.8%) studies, annualized bleeding rate 60 (50.8%) studies, bleed per month 10 (8.5%) studies and others 11 (9.3%) studies]. Of these, 32 (27%) studies reported only mean or median without dispersion and 33 (28%) studies did not report any measures of central tendency (dispersion). CONCLUSIONS There is substantial variation in definitions and measures of bleeding outcomes in the haemophilia literature. This creates difficulty and limitations in comparing the outcomes between studies and in performing meta-analysis. The haemophilia research community needs to develop a consensus on a clear definition of bleeding and how to address the limitations associated with variations in measures of bleeding between centres and studies.