-
Seminars in Thrombosis and Hemostasis Apr 2024Khorana score (KS) is an established risk assessment model for predicting cancer-associated thrombosis. However, it ignores several risk factors and has poor...
Khorana score (KS) is an established risk assessment model for predicting cancer-associated thrombosis. However, it ignores several risk factors and has poor predictability in some cancer types. Machine learning (ML) is a novel technique used for the diagnosis and prognosis of several diseases, including cancer-associated thrombosis, when trained on specific diagnostic modalities. Consolidating the literature on the use of ML for the prediction of cancer-associated thrombosis is necessary to understand its diagnostic and prognostic abilities relative to KS. This systematic review aims to evaluate the current use and performance of ML algorithms to predict thrombosis in cancer patients. This study was conducted per Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Databases Medline, EMBASE, Cochrane, and ClinicalTrials.gov, were searched from inception to September 15, 2023, for studies evaluating the use of ML models for the prediction of thrombosis in cancer patients. Search terms "machine learning," "artificial intelligence," "thrombosis," and "cancer" were used. Studies that examined adult cancer patients using any ML model were included. Two independent reviewers conducted study selection and data extraction. Three hundred citations were screened, of which 29 studies underwent a full-text review, and ultimately, 8 studies with 22,893 patients were included. Sample sizes ranged from 348 to 16,407 patients. Thrombosis was characterized as venous thromboembolism ( = 6) or peripherally inserted central catheter thrombosis ( = 2). The types of cancer included breast, gastric, colorectal, bladder, lung, esophageal, pancreatic, biliary, prostate, ovarian, genitourinary, head-neck, and sarcoma. All studies reported outcomes on the ML's predictive capacity. The extreme gradient boosting appears to be the best-performing model, and several models outperform KS in their respective datasets.
PubMed: 38604227
DOI: 10.1055/s-0044-1785482 -
The Western Journal of Emergency... Mar 2024Point-of-care ultrasound (POCUS) performed by emergency physicians (EP) has emerged as an effective alternative to radiology department ultrasounds for the diagnosis of... (Meta-Analysis)
Meta-Analysis
INTRODUCTION
Point-of-care ultrasound (POCUS) performed by emergency physicians (EP) has emerged as an effective alternative to radiology department ultrasounds for the diagnosis of lower extremity deep vein thrombosis (DVT). Systematic reviews suggested good sensitivity and specificity overall for EP-performed POCUS for DVT diagnosis, yet high levels of heterogeneity were reported.
METHODS
In this systematic review and meta-analysis, we aimed to provide the most up-to-date estimates of the accuracy of EP-performed POCUS for diagnosis of DVT and to explore potential correlations with test performance. We performed systematic searches in MEDLINE and Embase for original, primary data articles from January 2012-June 2021 comparing the efficacy of POCUS performed by EPs to the local standard. Quality Assessment of Diagnostic Accuracy Studies-2 for individual articles are reported. We obtained summary measures of sensitivity, specificity, and their corresponding 95% confidence intervals (CI) using bivariate mixed-effects regression models. We performed meta-regression, subgroup, and sensitivity analyses as planned in the protocol CRD42021268799 submitted to PROSPERO.
RESULTS
Fifteen publications fit the inclusion criteria, totaling 2,511 examinations. Pooled sensitivity and specificity were 90% (95% CI 82%-95%) and 95% (CI 91%-97%), respectively. Subgroup analyses by EP experience found significantly better accuracy for exams performed by EP specialists (93%, CI 88%-97%) vs trainees (77%, CI 60%-94%). Specificity for EP specialists (97%, CI 94%-99%) was higher than for trainees (87%, CI 76%-99%, = 0.01). Three-point compression ultrasound (CUS) was more sensitive than two-point CUS but was only statistically significant when limited to EP specialists (92% vs 88%, = 0.07, and 95% vs 88%, = 0.02, respectively).
CONCLUSION
Point-of-care ultrasound performed by emergency physicians is sensitive and specific for the diagnosis of suspected DVT when performed by trained attending EPs. Three-point compression ultrasound examination may be more sensitive than two-point CUS.
Topics: Humans; Point-of-Care Systems; Emergency Service, Hospital; Ultrasonography; Sensitivity and Specificity; Venous Thrombosis; Physicians
PubMed: 38596931
DOI: 10.5811/westjem.18125 -
International Journal of Stroke :... Apr 2024Venous thromboembolic events, including deep vein thrombosis (DVT) and pulmonary embolism (PE), are frequent complications in patients with intracerebral hemorrhage... (Review)
Review
BACKGROUND
Venous thromboembolic events, including deep vein thrombosis (DVT) and pulmonary embolism (PE), are frequent complications in patients with intracerebral hemorrhage (ICH). Various prophylactic strategies have been employed to mitigate this risk, such as heparin, intermittent pneumatic compression (IPC), and graduated compression stockings (GCS). The optimal thromboembolic prophylaxis approach remains uncertain due to the lack of randomized controlled trials (RCTs) comparing all interventions.
AIMS
We conducted a network meta-analysis and meta-analysis to systematically review and synthesize evidence from RCTs and non-randomized studies on the efficacy and safety of thromboembolic prophylaxis strategies in hospitalized ICH patients.
SUMMARY OF FINDINGS
Our study followed a registered protocol (PROSPERO CRD42023489217) and Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines incorporating the extension for network meta-analyses. Search for eligible studies was performed up to December 2023. We considered the occurrence of DVT, PE, hematoma expansion (HE), and all-cause mortality as outcome measures. A total of 16 studies, including 7 RCTs and 9 non-randomized studies, were included in the analysis. Network meta-analysis revealed that IPC demonstrated the highest efficacy in reducing DVT incidence (odds ratios (OR) 0.30, 95% confidence interval (CI) 0.08-1.16), particularly considering only RCTs (OR 0.33, 95% CI 0.16-0.67). GCS showed the highest safety profile for HE (OR 0.67, 95% CI 0.14-3.13), but without efficacy. Chemoprophylaxis did not reduce the risk of PE events (OR 1.10, 95% CI 0.17-7.19) with a higher occurrence of HE (OR 1.33, 95% CI 0.60-2.96), but the differences were not significant.
CONCLUSION
Our study supports the use of IPC as the primary thromboembolic prophylaxis measure in ICH patients. Further research, including head-to-head RCTs, is needed to strengthen the evidence base and optimize clinical decision-making for thromboembolic prophylaxis in this vulnerable patient population.
PubMed: 38591740
DOI: 10.1177/17474930241248542 -
Injury Jun 2024Optimal thromboprophylaxis in orthopaedic procedures is crucial in an attempt to lower the risk of venous thromboembolism, including deep vein thrombosis and pulmonary... (Review)
Review
OBJECTIVE
Optimal thromboprophylaxis in orthopaedic procedures is crucial in an attempt to lower the risk of venous thromboembolism, including deep vein thrombosis and pulmonary embolism. We aim to: 1) identify clinical practice guidelines (CPGs) and recommendations (CPRs) on thromboprophylaxis in adult patients undergoing orthopaedic procedures, and 2) assess the methodological quality and reporting clarity of these guidelines.
METHODS
The study was conducted following the 2020 PRISMA guidelines for a systematic review and has been registered on the international prospective register of systematic reviews (PROSPERO) under the registration number (CRD42023406988). An electronic search was conducted using Medline, Embase, Cochrane, Web of Science, Google Scholar and medRxiv. The search terms used were ""adults", "orthopedic surgery", "orthopedic surgeries", "orthopedic surgical procedure", "orthopedic surgical procedures" "english language", "venous thromboembolism", in all possible combinations (January 2013 to March 2023). The eligible studies were evaluated by four blind raters, employing the Appraisal of Guidelines for Research & Evaluation II (AGREE-II) analysis tool.
RESULTS
The literature research resulted in 931 studies. Finally, a total of 16 sets of guidelines were included in the current analysis. There were 8 national and 8 international CPGs. Eight CPGs made specific recommendations for orthopaedic surgery and referred mostly to joints; one guideline focused on pelvi-acetabular trauma, while the rest were more inclusive and non-specific. Four guidelines, one from the American Society of Hematology (ASH), two from the United Kingdom (UK) and one from India were found to have the highest methodological quality and reporting clarity according to the AGREE-II tool. Inter-rater agreement was very good with a mean Cohens Kappa 0.962 (95 % CI, 0.895-0.986) in the current analysis. So, the reliability of the measurements can be interpreted as good to excellent.
CONCLUSION
Optimal thromboprophylaxis in orthopaedic procedures is crucial. The available guidelines were found to be mostly of high methodological quality and inter-rater agreement was very good, according to our study.
Topics: Humans; Practice Guidelines as Topic; Venous Thromboembolism; Orthopedic Procedures; Anticoagulants; Pulmonary Embolism; Postoperative Complications; Venous Thrombosis
PubMed: 38582056
DOI: 10.1016/j.injury.2024.111517 -
Annals of Medicine and Surgery (2012) Apr 2024Cerebral venous thromboembolism (CVT) poses a significant risk of venous infarction and haemorrhage, which can lead to neurological deficits and, in severe cases, even... (Review)
Review
BACKGROUND
Cerebral venous thromboembolism (CVT) poses a significant risk of venous infarction and haemorrhage, which can lead to neurological deficits and, in severe cases, even death. The optimal treatment regimen for patients with CVT remains unclear.
METHODS
MEDLINE, Embase, Google Scholar, Web of Science (WoS), and Cochrane Central databases were searched for randomized controlled trials (RCTs) and observational studies assessing the efficacy and safety of rivaroxaban in patients with CVT. All-site venous thromboembolism (VTE), risk of clinically relevant non-major bleeding, incidence of partial recanalization, complete recanalization and major haemorrhage were among outcomes of interest. Mantel-Haenszel weighted random-effects model was used to calculate relative risks (RRs) with 95% CIs.
RESULTS
The analysis included 1 RCT and 3 observational studies containing 211 patients. Compared to vitamin K antagonists (VKAs), rivaroxaban did not significantly decrease the all-site VTE [RR 0.31 (95% CI 0.01, 8.43); =0.49, I=0%]. Compared with VKAs, patients on rivaroxaban did not show a significantly reduced risk of recurrent cerebral venous thrombosis. In terms of incidence of partial recanalization, there was no discernible difference between rivaroxaban and VKAs [RR 0.90 (95% CI 0.66, 1.22); =0.49, I=0%]. There was no discernible difference in incidence of complete recanalization [RR 0.98 (95% CI 0.32, 3.03); =0.97, I=28%] and incidence of major haemorrhage [RR 0.19 (95% CI 0.01, 4.54); =0.30].
CONCLUSION
Rivaroxaban was found to have similar efficacy to VKAs. Due to its lower risk of severe bleeding and no need for INR monitoring, rivaroxaban may be a preferable treatment option for CVT.
PubMed: 38576935
DOI: 10.1097/MS9.0000000000001689 -
Vascular Medicine (London, England) Jun 2024Inferior vena cava (IVC) anomalies are uncommon congenital causes of deep vein thrombosis (DVT). KILT syndrome (kidney and IVC abnormalities with leg thrombosis) has... (Review)
Review
Inferior vena cava (IVC) anomalies are uncommon congenital causes of deep vein thrombosis (DVT). KILT syndrome (kidney and IVC abnormalities with leg thrombosis) has only been described as case reports in the literature. Therefore, the characteristics, evaluation, and management of patients with KILT syndrome have not yet been standardized. This study aimed to systematically review and analyze the clinical and radiographic data and treatment of previously reported cases of KILT syndrome. In this systematic review, we performed a literature search of the PubMed, Scopus, and Web of Science databases in December 2023, with no restrictions on the publication date. After duplicate extractions, 4195 articles were screened. Case reports and case series reporting on KILT syndrome were included. In addition to previously published cases, we included a new case of a previously healthy 25-year-old man with KILT syndrome in the analysis. A total of 34 cases were therefore included in this study. The majority (76.5%) were male patients with a median age of 24 years. In most patients, unprovoked bilateral iliofemoral thrombosis was diagnosed, and 64.7% had left kidney abnormalities. Our study suggests that anomalies of the IVC should be suspected in all young patients, especially male patients, with proximal, recurrent, or idiopathic DVT. If an IVC anomaly is confirmed, the kidneys should be examined to monitor and preserve healthy kidneys in cases of KILT syndrome. The data collected from all patients emphasize the requirement of long-term anticoagulation and risk factor control. Surgical measures may be effective for treating symptomatic refractory cases.
Topics: Humans; Vena Cava, Inferior; Venous Thrombosis; Kidney; Male; Adult; Female; Young Adult; Risk Factors; Adolescent; Child; Treatment Outcome; Vascular Malformations; Anticoagulants; Child, Preschool; Middle Aged
PubMed: 38573108
DOI: 10.1177/1358863X241240427 -
Clinical and Applied... 2024Cerebral venous sinus thrombosis (CVST) is a rare neurovascular condition that has been observed in individuals with coronavirus disease 2019 (COVID-19). This systematic...
Cerebral venous sinus thrombosis (CVST) is a rare neurovascular condition that has been observed in individuals with coronavirus disease 2019 (COVID-19). This systematic review aimed to explore the sex differences and characteristics of concurrent COVID-19 and CVST cases. A total of 212 CVST patients were included in the study. Women with CVST had a slightly higher mean age compared to men (47.359 years vs 46.08 years). Women were more likely to report symptoms such as fever (56.1%) and decreased sense of smell or taste (71.4%), while men more frequently experienced nausea or vomiting (55.6%), headache (62.9%), and seizures (72%). Notably, current smokers, who were predominantly men, had a higher occurrence of CVST. On the other hand, women had a higher likelihood of CVST risk factors such as oral contraceptive pill (OCP) use and autoimmune diseases. Treatment approaches also showed sex-based differences. Unfractionated heparin was administered more often to women with CVST (63.2%). The in-hospital mortality rate for CVST patients was 21.3%, with men having a significantly higher mortality rate than women (65.2% vs 34.8%, = .027). Survival analysis revealed that factors such as smoking history, diabetes mellitus, hypertension, OCP use, COVID-19 symptoms, CVST symptoms, and the need for intubation significantly influenced survival outcomes. Understanding these sex differences in COVID-19-related CVST is crucial for accurate diagnosis and effective management, ultimately leading to improved patient outcomes. Our findings highlight the importance of considering sex as a factor in the evaluation and treatment of individuals with COVID-19 and concurrent CVST.
Topics: Humans; Male; Female; Middle Aged; Heparin; Sex Characteristics; Sinus Thrombosis, Intracranial; COVID-19; Risk Factors
PubMed: 38551022
DOI: 10.1177/10760296241240748 -
The Journal of Trauma and Acute Care... Apr 2024Trauma patients are at increased risk of venous thromboembolism (VTE), including deep venous thrombosis (DVT) and/or pulmonary embolism (PE). We conducted a systematic...
INTRODUCTION
Trauma patients are at increased risk of venous thromboembolism (VTE), including deep venous thrombosis (DVT) and/or pulmonary embolism (PE). We conducted a systematic review and meta-analysis summarizing the association between prognostic factors and the occurrence of VTE following traumatic injury.
METHODS
We searched the EMBASE and MEDLINE databases from inception to August 2023. We identified studies reporting confounding adjusted associations between patient, injury or post-injury care factors and risk of VTE. We performed meta-analyses of odds ratios (ORs) using the random effects method and assessed individual study risk of bias using the QUIPS tool.
RESULTS
We included 31 studies involving 1,981,946 patients. Studies were predominantly observational cohorts from North America. Factors with moderate or higher certainty of association with increased risk of VTE include older age, obesity, male sex, higher injury severity score, pelvic injury, lower extremity injury, spinal injury, delayed VTE prophylaxis, need for surgery and tranexamic acid use. After accounting for other important contributing prognostic variables, a delay in the delivery of appropriate pharmacologic prophylaxis for as little as 24 to 48 hours independently confers a clinically meaningful two-fold increase in incidence of VTE.
CONCLUSION
These findings highlight the contribution of patient predisposition, the importance of injury pattern, and the impact of potentially modifiable post-injury care on risk of VTE after traumatic injury. These factors should be incorporated into a risk stratification framework to individualize VTE risk assessment and support clinical and academic efforts reduce thromboembolic events among trauma patients.Study TypeSystematic Review & Meta-Analysis.
LEVEL OF EVIDENCE
Level II.
PubMed: 38548736
DOI: 10.1097/TA.0000000000004326 -
World Neurosurgery Jun 2024Venous sinus thromboses (VSTs) are rare complications of neurosurgical procedures in the proximity of the dural sinuses. Surgery of the posterior cranial fossa (PCF) and... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Venous sinus thromboses (VSTs) are rare complications of neurosurgical procedures in the proximity of the dural sinuses. Surgery of the posterior cranial fossa (PCF) and particularly of the cerebellopontine angle (CPA) shows increased risk of VST. VST management is challenging because anticoagulant therapy must be balanced with the risk of postoperative bleeding. We performed a systematic review and meta-analysis to summarize the most important neuroradiologic and clinical aspects of VST after PCF/CPA surgery.
METHODS
We performed a comprehensive literature search to identify articles reporting data on VST after PCF/CPA surgery. We selected only comparative studies providing adequate neuroimaging assessing VST and a control group.
RESULTS
We included 13 articles reporting 1855 patients. VST occurred in 251/1855 cases (estimated incidence, 17.3%; 95% confidence interval [CI], 12.4%-22.2%). Only presigmoid approach (odds ratio [OR], 2.505; 95% CI, 1.161-5.404; P = 0.019) and intraoperative sinus injury (OR, 8.95; 95% CI, 3.43-23.34; P < 0.001) showed a significant association with VST. VST-related symptoms were reported in 12/251 patients with VST (pooled incidence, 3.1%; 95% CI, 1%-5.2%). In particular, we found a significantly increased OR of cerebrospinal fluid leak (OR, 3.197; 95% CI, 1.899-5.382; P < 0.001) and cerebrospinal fluid dynamic alterations in general (OR, 3.625; 95% CI, 2.370-5.543; P < 0.001). Indications for VST treatment were heterogeneous: 58/251 patients underwent antithrombotics, with 6 treatment-related bleedings. Recanalization overall occurred in 56.4% (95% CI, 40.6%-72.2%), with no significant difference between treated and untreated patients. However, untreated patients had a favorable outcome.
CONCLUSIONS
VST is a relatively frequent complication after PCF/CPA surgery and a presigmoid approach and intraoperative sinus injury represent the most significant risk factors. However, the clinical course is generally benign, with no advantage of antithrombotic therapy.
Topics: Humans; Sinus Thrombosis, Intracranial; Cranial Fossa, Posterior; Risk Factors; Neurosurgical Procedures; Postoperative Complications; Treatment Outcome
PubMed: 38531470
DOI: 10.1016/j.wneu.2024.03.087 -
Blood Advances Jun 2024Venous thromboembolism (VTE) is a leading cause of preventable in-hospital mortality. Monitoring VTE cases is limited by the challenges of manual medical record review... (Meta-Analysis)
Meta-Analysis
Venous thromboembolism (VTE) is a leading cause of preventable in-hospital mortality. Monitoring VTE cases is limited by the challenges of manual medical record review and diagnosis code interpretation. Natural language processing (NLP) can automate the process. Rule-based NLP methods are effective but time consuming. Machine learning (ML)-NLP methods present a promising solution. We conducted a systematic review and meta-analysis of studies published before May 2023 that use ML-NLP to identify VTE diagnoses in the electronic health records. Four reviewers screened all manuscripts, excluding studies that only used a rule-based method. A meta-analysis evaluated the pooled performance of each study's best performing model that evaluated for pulmonary embolism and/or deep vein thrombosis. Pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with confidence interval (CI) were calculated by DerSimonian and Laird method using a random-effects model. Study quality was assessed using an adapted TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) tool. Thirteen studies were included in the systematic review and 8 had data available for meta-analysis. Pooled sensitivity was 0.931 (95% CI, 0.881-0.962), specificity 0.984 (95% CI, 0.967-0.992), PPV 0.910 (95% CI, 0.865-0.941) and NPV 0.985 (95% CI, 0.977-0.990). All studies met at least 13 of the 21 NLP-modified TRIPOD items, demonstrating fair quality. The highest performing models used vectorization rather than bag-of-words and deep-learning techniques such as convolutional neural networks. There was significant heterogeneity in the studies, and only 4 validated their model on an external data set. Further standardization of ML studies can help progress this novel technology toward real-world implementation.
Topics: Humans; Natural Language Processing; Machine Learning; Venous Thromboembolism; Electronic Health Records
PubMed: 38522096
DOI: 10.1182/bloodadvances.2023012200