ABSTRACT
The major challenge in today's world is that medical research is facing the existence of a vast number of viruses and their mutations, which from time to time cause outbreaks. Also, the continuous and spontaneous mutations occurring in the viruses and the emergence of resistant virus strains have become serious medical hazards. So, in view of the growing number of diseases, like the recent COVID-19 pandemic that has caused the deaths of millions of people, there is a need to improve rapid and sensitive diagnostic strategies to initiate timely treatment for such conditions. In the cases like COVID-19, where a real cure due to erratic and ambiguous signs is not available, early intervention can be life-saving. In the biomedical and pharmaceutical industries, nanotechnology has evolved exponentially and can overcome multiple obstacles in the treatment and diagnosis of diseases. Nanotechnology has developed exponentially in the biomedical and pharmaceutical fields and can overcome numerous challenges in the treatment and diagnosis of diseases. At the nano stage, the molecular properties of materials such as gold, silver, carbon, silica, and polymers get altered and can be used for the creation of reliable and accurate diagnostic techniques. This review provides insight into numerous diagnostic approaches focused on nanoparticles that could have been established for quick and early detection of such diseases.
ABSTRACT
Objective: To compare clinical and paraclinical similarities between trauma patients with positive RT-PCR tests (PCR+ve) and the RT-PCR negative ones (PCR -ve). Methods: This a case-control study, where cases had a PCR+ve and controls had a negative result. Two groups were compared regarding (para) clinical values. Multivariable binary logistic regression analysis investigated the variables predicting COVID-19 and the mortality rate. Results: Both groups were similar regarding the clinical findings and comorbidities (p>0.05). PCR+ve group had lower lymphocyte count (1.41 [1.45] vs. 1.66 [1.61], p=0.030), CPK level (411 [928.75] vs. 778 [1946.5]. p=0.006) and CRP level (17 [42.5] vs. 24 [50.75], p=0.004). However, none of these findings were significant in the multivariable analysis. Finally, PCR+ve group had increased odds of death (OR=2.88; 95% CI=1.22-7.41). Conclusion: Unlike our primary hypothesis, the study failed to mark any significant (para) clinical features guiding us to detect COVID-19 earlier in trauma patients. Moreover, the PCR+ve group is at increased mortality risk. A larger, multicentric prospective study should be designed to address this issue.
ABSTRACT
The inability to test at scale has become humanity's Achilles' heel in the ongoing war against the COVID-19 pandemic. Therefore, various intelligent diagnostic approaches have been proposed in the literature to fight against this pandemic situation. However, in this paper, an Artificial Intelligence (AI) powered automatic screening solution has been proposed for rapid and accurate diagnosis of COVID-19. The proposed system analyzes the audio signals of human being using modified DenseNet121 to detect COVID-19 cases accurately. The proposed methodology has been applied on a publicly available benchmark dataset known as Coswara [1]. Experimental results demonstrate the efficacy of the proposed system in terms of blind test accuracy. © 2021 IEEE.
ABSTRACT
Chronic lymphocytic leukemia (CLL) is a disease of the elderly, with a median age at diagnosis of approximately 70 years. The natural course of the disease varies greatly, and patients with non-progressive and asymptomatic leukemia do not require treatment. The results of CLL treatment have improved significantly in recent years, mainly due to the introduction of new, more effective drugs, including BCR inhibitors and BCL2 inhibitors. The new drugs are used continuously, while venetoclax in combination with anti-CD20 antibodies is used for 24 (rituximab) or 12 (obinutuzumab) months, depending on the type of antibody and line of therapy. The choice of treatment protocol should largely depend on the assessment of 17p deletion/TP53 mutation and immunoglobulin variable heavy chain (IGVH) mutation status, which correlate with a worse response to immunochemotherapy. The role of immunochemotherapy, which until recently was the mainstay of CLL treatment, has now significantly decreased. In the first-line, it is recommended only in patients without 17p deletion/TP53 mutation, with mutated IGVH. Other patients should receive novel targeted therapies. However, at the time of the preparation of these recommendations, these therapies are not available in the firs-line of treatment in Poland. Novel targeted therapies play a major role in the treatment of refractory/relapsed CLL, and immunochemotherapy is recommended primarily in patients with a long-term response to first-line therapy. In this article, we present an update of the guidelines for the diagnosis and treatment of CLL, including the treatment of autoimmune complications, as well as the prophylaxis and treatment of infections, developed by the Polish Society of Haematologists and Transfusiologists and PALG-CLL Working Group.
ABSTRACT
The ongoing COVID-19 pandemic has overloaded current healthcare systems, including radiology systems and departments. Machine learning-based medical imaging diagnostic approaches play an important role in tracking the spread of this virus, identifying high-risk patients, and controlling infections in real-time. Researchers aggregate radiographic samples from different data sources to establish a multi-source learning scheme to mitigate the insufficiency of COVID-19 samples from individual hospitals, especially in the early stage of the disease. However, data heterogeneity across different clinical centers with various imaging conditions is considered a significant limitation in model performance. This paper proposes a contrastive learning scheme for the automatic diagnosis of COVID-19 to effectively mitigate data heterogeneity in multi-source data and learn a robust and generalizable model. Inspired by advances in domain adaptation, we employ contrastive training objectives to promote intra-class cohesion across different data sources and inter-class separation of infected and non-infected cases. Extensive experiments on two public COVID-19 CT datasets demonstrate the effectiveness of the proposed method for tackling data heterogeneity problems with boosted diagnosis performance. Moreover, benefiting from the contrastive learning framework, our method can be generalized to solve data heterogeneity problems under a broader multi-source learning setting. © 2021 IEEE
ABSTRACT
The outbreak of severe pneumonia at the end of 2019 was proved to be caused by the SARS-CoV-2 virus spreading out the world. And COVID-19 spread rapidly through a terrible transmission way by human-to-human, which led to many suspected cases waiting to be diagnosed and huge daily samples needed to be tested by an effective and rapid detection method. With an increasing number of COVID-19 infections, medical pressure is severe. Therefore, more efficient and accurate diagnosis methods were keen urgently established. In this review, we summarized several methods that can rapidly and sensitively identify COVID-19; some of them are widely used as the diagnostic techniques for SARS-CoV-2 in various countries, some diagnostic technologies refer to SARS (Severe Acute Respiratory Syndrome) or/and MERS (Middle East Respiratory Syndrome) detection, which may provide potential diagnosis ideas.