Aspiration mechanical thrombectomy in acute and subacute iliofemoral deep vein thrombosis in the COVID era: challenges and outcome

BACKGROUND: Catheter directed thrombolysis (CDT) proved to be effective treatment in deep venous thrombosis (DVT), However, there is some concerns about the associated bleeding risk. We assessed the safety and efficacy including technical and clinical success in resolution of iliofemoral DVT after one session treatment with penumbra aspiration mechanical thrombectomy catheter as an alternative CDT. METHOD(S): This is a retrospective study that was conducted on patients presented to Aseer Central Hospital and Saudi German Hospital in Saudi Arabia from January 2019 to December 2020 with symptomatic acute iliofemoral DVT. Patients were treated with Indigo continuous aspiration mechanical thrombectomy 8 system (Penumbra Inc, Alameda, CA, USA). Secondary end point was treatment complications, DVT recurrence and postphlebetic syndrome occurrence within 1 year follow-up. RESULT(S): Our study included twenty-three patients with sixteen females (59.6%) and seven males (30.4%) with a median age of 38 years (18-60years). Indication for treatment was primary DVT in seventeen patients (73.9%), recurrent DVT in six patients (26.1%). Provoked DVT was present in fifteen patients (65.2%) with nine of them was tested positive for COVID-19 while non provoked DVT in eight patients (4.8%). Seven patients (30.4%) had underlying May-Thurner Syndrome after thrombus removal and needed stenting for left common iliac vein (CIV) and two patients (8.7%) with recurrent DVT has significant residual Left common iliac vein stenosis that needed stenting. Two patient (8.7%) have thrombosis extending to inferior vena cava. Initial technical success using Penumbra was 82.6%. All patients in whom aspiration thrombectomy was not successful underwent further treatment with CDT which was successful in further three cases with failure in one case making overall technical success was 95.7%. Recurrent iliac occlusion after successful recanalization was seen in two patients (8.7%) at 6 months follow up. One patient (4.3%) developed pulmonary embolism that required full anticoagulation with no further treatment. No patient develops postphlebetic syndrome at 1 year follow-up. CONCLUSION(S): Penumbra aspiration thrombectomy catheter was safe, effective and promising technique in treatment of acute iliofemoral DVT and allowed definitive treatment in one session with no need for the use of thrombolysis in the majority of cases with no risk for bleeding complications, shorter hospital stay, no need for ICU admission and lower cost. COVID infection does not seem to alter the outcome. Copyright © 2022 EDIZIONI MINERVA MEDICA.

an intelligent computing for diagnosing covid-19 using available blood tests

Since the end of 2019, the Coronavirus (known as COVID-19) has spread rapidly and caused considerable losses in terms of human life and the economy. There are many difficulties with diagnosing COVID-19, including leaks in the material and equipment used in laboratories, issues with the media used to transport the virus, and the worldwide shortage in supplies. These difficulties primarily affect countries with low standards of living. Hence, scientists have been motivated to use new, low-cost, highly efficient technology for such diagnoses. In this study, artificial intelligence (AI) algorithms, precisely the logistic regression (LR), support vector machine (SVM), and extreme gradi-ent boosting machine (XGBoost) algorithms, were used as classifiers and achieved com-prehensive performances. As a result, a new model for COVID-19 diagnoses based on standard blood tests, which are cheap and available, was designed. We found that many of these classical blood tests are significantly correlated with a COVID-19 diagnosis by im-plementing the proposed model. The results show that the best classification accuracy ob-tained was 0.87, associated with an F1-Score of 0.91. This overall accuracy is considered good despite the limited number of blood test samples. Hence, machine learning algorithms can be used in conjunction with blood tests in countries with insufficient resources to com-bat this pandemic. © ICIC International 2022.

Covid-19 Identification using deep neural networks

COVID-19 is a novel virus which is originated from Wuhan, a city in China. By March 2021, World Health Organization has confirmed the virus has increased in the number of infections to over 117 million cases globally. In this scenario of increasing Corona infected patients, most hospitals are lagging in the availability of the Corona test kits. Owing to the lack of precise automated toolkits, auxiliary diagnostic tools are in high demand. Therefore, it becomes necessary to enforce AI-based automatic detection techniques. It can also address the issue of unavailability of physicians in remote areas. This study proposes the use of deep neural networks and transfer learning for the detection of COVID-19 infectees through radio-graphs of chest X-rays. We have used hand-crafted Convolutional Neural Network (CNN) besides using the existing famous pre-trained networks employing transfer learning. Remarkable accuracy achieved was 96.89% for our hand-crafted CNN, 92.67% for ResNet34, and 98.26% on DenseNet-121, respectively. However, our hand-crafted CNN required 8 million less parameters than ResNet34 and comparable to DenseNet-121. © 2021 IEEE.