Predicting Venous Thrombosis in Osteoarthritis Using a Machine Learning Algorithm: A Population-Based Cohort Study

Osteoarthritis (OA) is the most common joint disease associated with pain and disability. OA patients are at a high risk for venous thrombosis (VTE). Here, we developed an interpretable machine learning (ML)-based model to predict VTE risk in patients with OA. To establish a prediction model, we used six ML algorithms, of which 35 variables were employed. Recursive feature elimination (RFE) was used to screen the most related clinical variables associated with VTE. SHapley additive exPlanations (SHAP) were applied to interpret the ML mode and determine the importance of the selected features. Overall, 3169 patients with OA (average age: 66.52 ± 7.28 years) were recruited from Xi’an Honghui Hospital. Of these, 352 and 2817 patients were diagnosed with and without VTE, respectively. The XGBoost algorithm showed the best performance. According to the RFE algorithms, 15 variables were retained for further modeling with the XGBoost algorithm. The top three predictors were Kellgren–Lawrence grade, age, and hypertension. Our study showed that the XGBoost model with 15 variables has a high potential to predict VTE risk in patients with OA.

COVID-19 is associated with higher risk of venous thrombosis, but not arterial thrombosis, compared with influenza: Insights from a large US cohort

Introduction Infection with SARS-CoV-2 is typically compared with influenza to contextualize its health risks. SARS-CoV-2 has been linked with coagulation disturbances including arterial thrombosis, leading to considerable interest in antithrombotic therapy for Coronavirus Disease 2019 (COVID-19). However, the independent thromboembolic risk of SARS-CoV-2 infection compared with influenza remains incompletely understood. We evaluated the adjusted risks of thromboembolic events after a diagnosis of COVID-19 compared with influenza in a large retrospective cohort. Methods We used a US-based electronic health record (EHR) dataset linked with insurance claims to identify adults diagnosed with COVID-19 between April 1, 2020 and October 31, 2020. We identified influenza patients diagnosed between October 1, 2018 and April 31, 2019. Primary outcomes [venous composite of pulmonary embolism (PE) and acute deep vein thrombosis (DVT); arterial composite of ischemic stroke and myocardial infarction (MI)] and secondary outcomes were assessed 90 days post-diagnosis. Propensity scores (PS) were calculated using demographic, clinical, and medication variables. PS-adjusted hazard ratios (HRs) were calculated using Cox proportional hazards regression. Results There were 417,975 COVID-19 patients (median age 57y, 61% women), and 345,934 influenza patients (median age 47y, 66% women). Compared with influenza, patients with COVID-19 had higher venous thromboembolic risk (HR 1.53, 95% CI 1.38–1.70), but not arterial thromboembolic risk (HR 1.02, 95% CI 0.95–1.10). Secondary analyses demonstrated similar risk for ischemic stroke (HR 1.11, 95% CI 0.98–1.25) and MI (HR 0.93, 95% CI 0.85–1.03) and higher risk for DVT (HR 1.36, 95% CI 1.19–1.56) and PE (HR 1.82, 95% CI 1.57–2.10) in patients with COVID-19. Conclusion In a large retrospective US cohort, COVID-19 was independently associated with higher 90-day risk for venous thrombosis, but not arterial thrombosis, as compared with influenza. These findings may inform crucial knowledge gaps regarding the specific thromboembolic risks of COVID-19.

What We Know (and Do not Know) Regarding the Pathogenesis of Pulmonary Thrombosis in COVID-19

The clinical course of coronavirus disease 2019 (COVID-19) is often complicated by the onset of venous thrombosis and thromboembolism (VTE), encompassing also pulmonary thrombosis. Recent statistics attests that the cumulative frequency of VTE can be as high as 30% in COVID-19 hospitalized patients, increasing to nearly 40 to 70% (depending on systematic screening) in those with severe illness, mechanical ventilation, or intensive care unit admission. The risk of venous thrombosis seems mostly limited to the active phase of disease, and is directly associated with some genetic (i.e., inherited prothrombotic predisposition) and demographical factors (male sex, overweight/obesity), disease severity (risk increasing progressively from hospitalization to development of severe illness, being the highest in patients needing mechanical ventilation and/or intensive care), presence and extent of pulmonary disease, coexistence of multiple risk factors (immobilization, mechanical ventilation, co- or superinfections), along with increased values of inflammatory and thrombotic biomarkers. At least three different phenotypes of pulmonary thrombosis may develop in COVID-19 patients, one caused by typical embolization from peripheral venous thrombosis (e.g., deep vein thrombosis), a second type triggered by local inflammation of nearby pulmonary tissue, and a third one mostly attributable to the prothrombotic state consequent to the pronounced systemic inflammatory response (i.e., the so-called cytokine storm) that is frequently observed in COVID-19. Although the pathogenesis of these three conditions has different features, their discrimination is essential for diagnostic and therapeutic purposes. The prognosis of COVID-19 patients who develop pulmonary thrombosis is also considerably worse than those who do not, thus probably needing frequent monitoring and more aggressive therapeutic management.

Endovascular treatment for cerebral venous thrombosis: current status, challenges, and opportunities

Cerebral venous thrombosis (CVT) mostly affects young people. So far, endovascular treatment (EVT) has not been shown to be beneficial in CVT, partially because venous EVT tools are not yet fully optimized, and therefore EVT is only used as a rescue treatment in rare cases. Identifying a subgroup of CVT patients that could benefit from EVT is challenging, given the milder course of disease compared with acute ischemic stroke, the paucity of data on prognostic factors (both in the clinical and imaging domain), and the lack of consensus on what constitutes 'technical success' in CVT EVT. In this review, we discuss the major obstacles that are encountered when trying to identify CVT patients that may benefit from EVT, and propose a roadmap that could help to overcome these challenges in the near future.

Case Reports of Pregnancy-Related Cerebral Venous Thrombosis in the Neurology Department of the Emergency Clinical Hospital in Constanta

Cerebral venous thrombosis accounts for 0.5–1% of all cerebrovascular events and is one type of stroke that affects the veins and cerebral sinuses. Females are more affected than males, as they may have risk factors, such as pregnancy, first period after pregnancy, treatment with oral contraceptives treatment with hormonal replacement, or hereditary thrombophilia. This neurological pathology may endanger a patient’s life. However, it must be suspected in its acute phase, when it presents with variable clinical characteristics, so that special treatment can be initiated to achieve a favorable outcome with partial or complete functional recovery. The case study describes the data and the treatment of two patients with confirmed cerebral venous thrombosis with various localizations and associated risk factors, who were admitted to the neurology department of the Sf. Apostol Andrei Emergency Hospital in Constanta. The first patient was 40 years old and affected by sigmoid sinus and right lateral sinus thrombosis, inferior sagittal sinus, and right sinus thrombosis, associated with right temporal subacute cortical and subcortical hemorrhage, which appeared following a voluntary abortion. The second case was a patient aged 25 who was affected by left parietal cortical vein thrombosis, associated with ipsilateral superior parietal subcortical venous infarction, which appeared following labor. The data are strictly observational and offer a perspective on clinical manifestations and clinical and paraclinical investigations, including the treatment of young patients who had been diagnosed with cerebral venous thrombosis and admitted to the neurology department.