ABSTRACT

BACKGROUND: The safety and efficacy of direct-acting oral anticoagulants (DOACs) for therapeutic anticoagulation in the setting of primary or metastatic brain cancer is not known.

OBJECTIVE: To conduct a meta-analysis and systematic review of studies that compare the risk of intracranial hemorrhage (ICH) in patients with brain cancer treated with DOACs vs. LMWH.

METHODS: A literature search was conducted using PubMed, EMBASE, and Cochrane databases. Summary statistics were obtained by calculating the risk ratio (RR), and heterogeneity across studies was estimated using the I2 statistic. A total of 10 retrospective studies (n=1,638) met criteria for inclusion. The primary endpoint was the pooled RR for ICH in patients with brain tumors receiving anticoagulation with DOACs compared with those receiving LMWH. Secondary analyses included the risk of fatal ICH in each subgroup.

RESULTS: The pooled RR for ICH in patients receiving DOACs vs. those receiving LMWH was 0.65 (95% confidence interval [CI], 0.36-1.17; P = 0.15; I2 = 50%). In studies evaluating primary brain cancer, there was a reduction in risk of ICH with DOACs (RR, 0.35; 95% CI, 0.18-0.69; P = 0.003; I2 = 0%). In patients with metastatic brain cancer, there was no difference in the risk of ICH with type of anticoagulation (RR, 1.05; 95% CI, 0.71-1.56; P = 0.80; I2 = 0%). The overall risk of fatal ICH was not different between anticoagulants.

DISCUSSION: The risk of ICH in patients with brain cancer receiving therapeutic anticoagulation varies by anticoagulation agent and diagnosis of primary or metastatic disease.

PMID:37866517 | DOI:10.1016/j.jtha.2023.10.011

07:05

PubMed articles on: Cancer & VTE/PE

Computer image analysis with artificial intelligence: a practical introduction to convolutional neural networks for medical professionals

Postgrad Med J. 2023 Oct 4:qgad095. doi: 10.1093/postmj/qgad095. Online ahead of print.

ABSTRACT

Artificial intelligence tools, particularly convolutional neural networks (CNNs), are transforming healthcare by enhancing predictive, diagnostic, and decision-making capabilities. This review provides an accessible and practical explanation of CNNs for clinicians and highlights their relevance in medical image analysis. CNNs have shown themselves to be exceptionally useful in computer vision, a field that enables machines to 'see' and interpret visual data. Understanding how these models work can help clinicians leverage their full potential, especially as artificial intelligence continues to evolve and integrate into healthcare. CNNs have already demonstrated their efficacy in diverse medical fields, including radiology, histopathology, and medical photography. In radiology, CNNs have been used to automate the assessment of conditions such as pneumonia, pulmonary embolism, and rectal cancer. In histopathology, CNNs have been used to assess and classify colorectal polyps, gastric epithelial tumours, as well as assist in the assessment of multiple malignancies. In medical photography, CNNs have been used to assess retinal diseases and skin conditions, and to detect gastric and colorectal polyps during endoscopic procedures. In surgical laparoscopy, they may provide intraoperative assistance to surgeons, helping interpret surgical anatomy and demonstrate safe dissection zones. The integration of CNNs into medical image analysis promises to enhance diagnostic accuracy, streamline workflow efficiency, and expand access to expert-level image analysis, contributing to the ultimate goal of delivering further improvements in patient and healthcare outcomes.

PMID:37794609 | DOI:10.1093/postmj/qgad095

07:05

PubMed articles on: Cancer & VTE/PE

Artificial intelligence in the prediction of venous thromboembolism: A systematic review and pooled analysis

Eur J Haematol. 2023 Oct 4. doi: 10.1111/ejh.14110. Online ahead of print.

ABSTRACT

BACKGROUND: Accurate diagnostic and prognostic predictions of venous thromboembolism (VTE) are crucial for VTE management. Artificial intelligence (AI) enables autonomous identification of the most predictive patterns from large complex data. Although evidence regarding its performance in VTE prediction is emerging, a comprehensive analysis of performance is lacking.

AIMS: To systematically review the performance of AI in the diagnosis and prediction of VTE and compare it to clinical risk assessment models (RAMs) or logistic regression models.

METHODS: A systematic literature search was performed using PubMed, MEDLINE, EMBASE, and Web of Science from inception to April 20, 2021. Search terms included "artificial intelligence" and "venous thromboembolism." Eligible criteria were original studies evaluating AI in the prediction of VTE in adults and reporting one of the following outcomes: sensitivity, specificity, positive predictive value, negative predictive value, or area under receiver operating curve (AUC). Risks of bias were assessed using the PROBAST tool. Unpaired t-test was performed to compare the mean AUC from AI versus conventional methods (RAMs or logistic regression models).

RESULTS: A total of 20 studies were included. Number of participants ranged from 31 to 111 888. The AI-based models included artificial neural network (six studies), support vector machines (four studies), Bayesian methods (one study), super learner ensemble (one study), genetic programming (one study), unspecified machine learning models (two studies), and multiple machine learning models (five studies). Twelve studies (60%) had both training and testing cohorts. Among 14 studies (70%) where AUCs were reported, the mean AUC for AI versus conventional methods were 0.79 (95% CI: 0.74-0.85) versus 0.61 (95% CI: 0.54-0.68), respectively (p < .001). However, the good to excellent discriminative performance of AI methods is unlikely to be replicated when used in clinical practice, because most studies had high risk of bias due to missing data handling and outcome determination.

CONCLUSION: The use of AI appears to improve the accuracy of diagnostic and prognostic prediction of VTE over conventional risk models; however, there was a high risk of bias observed across studies. Future studies should focus on transparent reporting, external validation, and clinical application of these models.

PMID:37794526 | DOI:10.1111/ejh.14110

07:05

PubMed articles on: Cancer & VTE/PE

Implementation of routine venous thromboembolism prophylaxis during neoadjuvant chemotherapy for patients with ovarian cancer

Gynecol Oncol. 2023 Oct 11;178:89-95. doi: 10.1016/j.ygyno.2023.10.001. Online ahead of print.

ABSTRACT

OBJECTIVE: To compare the venous thromboembolism (VTE) rate in patients with ovarian cancer undergoing neoadjuvant chemotherapy before and after implementing routine thromboprophylaxis.

METHODS: This is a quasi-experimental pre-post study evaluating the VTE rate in patients with ovarian cancer who received neoadjuvant chemotherapy following a quality improvement initiative of routine thromboprophylaxis within a single healthcare system that started in January 2017. Patients were excluded if VTE was diagnosed before initiating chemotherapy. Patient factors and perioperative variables of interest were investigated for their association with VTE through univariate and multivariate models.

RESULTS: Of the 136 patients in the pre-implementation group, 3.7% (n = 5) received thromboprophylaxis. Of the 154 patients in the post-implementation group, 65.6% (n = 101) received thromboprophylaxis. Provider compliance varied from 51% in 2019 to 79.3% in 2021. The overall rate of VTE, from the start of chemotherapy to the end of treatment, was 21.3% (n = 29) pre- and 8.4% (n = 13) in the post-implementation group (p < 0.01). There was no difference in major bleeding events between groups (0% vs. 0.68%, p = 0.63). On univariate analysis, thromboprophylaxis (OR 0.19; 95% CI 0.07-0.52) and post-implementation period (OR 0.34; 95% CI 0.17-0.69) were associated with a decreased risk of any VTE during primary treatment. On multivariate analysis, only thromboprophylaxis remained significantly associated with reduced VTE rates (aOR 0.19; 95% CI 0.07-0.53).

CONCLUSION: Routine thromboprophylaxis during neoadjuvant chemotherapy is associated with reduced risk of VTE throughout primary treatment and is not associated with increased bleeding events.

PMID:37832182 | DOI:10.1016/j.ygyno.2023.10.001

07:05

PubMed articles on: Cancer & VTE/PE

Arterial and Venous Thromboembolic Complications in 832 Patients with BCR-ABL-Negative Myeloproliferative Neoplasms

Hamostaseologie. 2023 Oct 9. doi: 10.1055/a-2159-8767. Online ahead of print.

ABSTRACT

Arterial (ATE) and venous (VTE) thromboembolic complications are common causes of morbidity and mortality in BCR-ABL-negative myeloproliferative neoplasms (MPNs). However, there are few studies that include all MPN subtypes and focus on both MPN-associated ATE and VTE. In our single-center retrospective study of 832 MPN patients, a total of 180 first thromboembolic events occurred during a median follow-up of 6.6 years (range: 0-37.6 years), of which 105 were VTE and 75 were ATE. The probability of a vascular event at the end of the follow-up period was 36.2%, and the incidence rate for all first ATE/VTE was 2.43% patient/year. The most frequent VTE localizations were deep vein thrombosis with or without pulmonary embolism (incidence rate: 0.59% patient/year), while strokes were the most frequent ATE with an incidence rate of 0.32% patient/year. When comparing the group of patients with ATE/VTE (n = 180) and the group without such an event (n = 652) using multivariate Cox regression analyses, patients with polycythemia vera (hazard ratio [HR]: 1.660; [95% confidence interval [CI] 1.206, 2.286]) had a significantly higher risk of a thromboembolic event than the other MPN subtypes. In contrast, patients with a CALR mutation had a significantly lower risk of thromboembolism compared with JAK2-mutated MPN patients (HR: 0.346; [95% CI: 0.172, 0.699]). In summary, a high incidence of MPN-associated VTE and ATE was observed in our retrospective study. While PV patients or generally JAK2-mutated MPN patients had a significantly increased risk of such vascular events, this risk was reduced in CALR-mutated MPN patients.

PMID:37813367 | DOI:10.1055/a-2159-8767

07:05

PubMed articles on: Cancer & VTE/PE

Pulmonary Embolism Unplugged: Catheter-Directed Therapies for Intermediate-Risk Pulmonary Embolism

JACC Cardiovasc Interv. 2023 Sep 27:S1936-8798(23)01212-8. doi: 10.1016/j.jcin.2023.08.029. Online ahead of print.

NO ABSTRACT

PMID:37855803 | DOI:10.1016/j.jcin.2023.08.029

07:05

PubMed articles on: Cancer & VTE/PE

Unveiling Lung Adenocarcinoma: Non-bacterial Thrombotic Endocarditis as the Debut Sign

Cureus. 2023 Sep 14;15(9):e45271. doi: 10.7759/cureus.45271. eCollection 2023 Sep.

ABSTRACT

Non-bacterial thrombotic endocarditis (NBTE) involves the deposition of fibrin and platelets on heart valves, frequently leading to systemic embolism. The association between NBTE and cancer demands thorough investigation in cases lacking an evident cause. This case report elucidates the clinical course of a nonsmoking woman in her sixties with NBTE linked to pulmonary adenocarcinoma. The patient, who had a history of multiple sclerosis (MS) and was receiving dimethyl fumarate treatment, presented to the emergency department with stroke-like symptoms. Diagnostic challenges arose due to preexisting motor sensory impairment from MS. Initial evaluations revealed hypocapnia and elevated inflammatory markers. Blood cultures were obtained twice, and imaging confirmed pneumonia, left pleural effusion, and chronic pulmonary embolism while excluding acute vascular events or intracranial hemorrhage. The first transthoracic echocardiogram (TTE) indicated no cardiac abnormalities. Treatment encompassed parenteral antibiotics, systemic anticoagulation, and admission to medical floors. Although the initial treatment yielded a positive clinical response, subsequent complications emerged. On the tenth day, the patient required additional interventions, including broad-spectrum antibiotics and supplemental oxygen. A follow-up chest X-ray revealed persistent pneumonia and pleural effusion, and blood cultures upon admission returned negative. A subsequent head MRI confirmed an embolic stroke and displayed evidence of MS progression. Around the twentieth day, empirical treatment for infective endocarditis was initiated, and an 8 mm vegetation on the aortic valve was identified via transesophageal echocardiography (TOE). Acute pulmonary edema prompted a transfer to the intermediate care unit. Further investigations, including left thoracocentesis and CT, unveiled exudate and metastatic lesions in the liver, ilium, and kidney. Unfortunately, on the twenty-fifth day, the patient experienced acute myocardial infarction, right leg ischemia, disseminated intravascular coagulation, and shock. Pleural fluid analysis revealed malignant cells suggestive of lung adenocarcinoma. This case underscores the pivotal role of timely NBTE recognition and the search for malignancy when workup for infective endocarditis and autoimmune panels is negative. Moreover, it emphasizes the significance of vigilant monitoring, particularly in immunocompromised individuals or those with preexisting neurological deficits, especially when new neurological symptoms manifest. These insights significantly contribute to the comprehension of NBTE management and its implications for analogous patient cohorts.

PMID:37846253 | PMC:PMC10576842 | DOI:10.7759/cureus.45271

07:05

PubMed articles on: Cancer & VTE/PE

The prevalence of relevant drug-drug interactions and associated clinical outcomes in patients with cancer-associated thrombosis on concurrent anticoagulation and anticancer or supportive care therapies

Thromb Res. 2023 Oct 11;231:128-134. doi: 10.1016/j.thromres.2023.10.004. Online ahead of print.