Displaying all 3 publications

Abstract:
Sort:
  1. Robust biometric system using session invariant multimodal EEG and keystroke dynamics by the ensemble of self-ONNs
    Rahman A, Chowdhury MEH, Khandakar A, Tahir AM, Ibtehaz N, Hossain MS, et al.
    Comput Biol Med, 2022 Mar;142:105238.
    PMID: 35077938 DOI: 10.1016/j.compbiomed.2022.105238
    Harnessing the inherent anti-spoofing quality from electroencephalogram (EEG) signals has become a potential field of research in recent years. Although several studies have been conducted, still there are some vital challenges present in the deployment of EEG-based biometrics, which is stable and capable of handling the real-world scenario. One of the key challenges is the large signal variability of EEG when recorded on different days or sessions which impedes the performance of biometric systems significantly. To address this issue, a session invariant multimodal Self-organized Operational Neural Network (Self-ONN) based ensemble model combining EEG and keystroke dynamics is proposed in this paper. Our model is tested successfully on a large number of sessions (10 recording days) with many challenging noisy and variable environments for the identification and authentication tasks. In most of the previous studies, training and testing were performed either over a single recording session (same day) only or without ensuring appropriate splitting of the data on multiple recording days. Unlike those studies, in our work, we have rigorously split the data so that train and test sets do not share the data of the same recording day. The proposed multimodal Self-ONN based ensemble model has achieved identification accuracy of 98% in rigorous validation cases and outperformed the equivalent ensemble of deep CNN models. A novel Self-ONN Siamese network has also been proposed to measure the similarity of templates during the authentication task instead of the commonly used simple distance measure techniques. The multimodal Siamese network reduces the Equal Error Rate (EER) to 1.56% in rigorous authentication. The obtained results indicate that the proposed multimodal Self-ONN model can automatically extract session invariant unique non-linear features to identify and authenticate users with high accuracy.
  2. Fulltext Symptomatology, prognosis and clinical findings of STEMI as a ramification of COVID-19: A systematic review and proportion meta-analysis
    Jaiswal V, Almas T, Peng Ang S, David Song, Shama N, Storozhenko T, et al.
    Ann Med Surg (Lond), 2022 Apr;76:103429.
    PMID: 35284069 DOI: 10.1016/j.amsu.2022.103429
    BACKGROUND: There is an increasing COVID-19 population with concurrent STEMI. SARS-CoV-2 poses a significant risk of hypercoagulable and/or prothrombotic events due to the disturbance in hemostasis by affecting all three components of the Virchow's triad. These abnormalities in hemostasis are an increased risk factor for cardiovascular events, including acute thrombotic occlusion of coronary arteries leading to myocardial infarction.

    OBJECTIVE: The objective of this study is to collate the prognosis, symptomatology and clinical findings of COVID-19 adverse events causing STEMI.

    METHODS: Databases were queried with various keyword combinations to find applicable articles. Cardiovascular risk factors, symptomatology, mortality and rates of PCI were analyzed using random-effect model.

    RESULTS: 15 studies with a total of 379 patients were included in the final analysis. Mean age of patients was 62.82 ± 36.01, with a male predominance (72%, n = 274). Hypertension, dyslipidemia and diabetes mellitus were the most common cardiovascular risk factors among these patients, with a pooled proportion of 72%, 59% and 40% respectively. Dyspnea (61%, n = 131) was the most frequent presenting symptom, followed by chest pain (60%, n = 101) and fever (56%, n = 104). 62% of the patients had obstructive CAD during coronary angiography. The primary reperfusion method used in the majority of cases was percutaneous coronary intervention (64%, n = 124). Mortality, which is the primary outcome in our study, was relatively high, with a rate of 34% across studies.

    CONCLUSION: Our findings show that most cases have been found in males, while the most common risk factors were Hypertension and Diabetes Mellitus. In most COVID-19 cases with ST-segment myocardial infarction, most hospitalized patients underwent primary percutaneous coronary intervention instead of fibrinolysis. The in-hospital mortality was significantly higher, making this report significant. As the sample size and reported study are considerably less, it warrants a further large-scale investigation to generalize it.

  3. Fulltext Epidemiology, clinical ramifications, and cellular pathogenesis of COVID-19 mRNA-vaccination-induced adverse cardiovascular outcomes: A state-of-the-heart review
    Almas T, Rehman S, Mansour E, Khedro T, Alansari A, Malik J, et al.
    Biomed Pharmacother, 2022 May;149:112843.
    PMID: 35325848 DOI: 10.1016/j.biopha.2022.112843
    The coronavirus disease 2019 (COVID-19) has overwhelming healthcare systems globally. To date, a myriad of therapeutic regimens has been employed in an attempt to curb the ramifications of a severe COVID-19 infection. Amidst the ongoing pandemic, the advent and efficacious uptake of COVID-19 vaccination has significantly reduced disease-related hospitalizations and mortality. Nevertheless, many side-effects are being reported after COVID-19 vaccinations and myocarditis is the most commonly reported sequelae post vaccination. Majority of these diseases are associated with COVID-19 mRNA vaccines. Various studies have established a temporal relationship between these complications, yet the causality and the underlying pathogenesis remain hypothetical. In this review, we aim to critically appraise the available literature regarding the cardiovascular side effects of the various mRNA vaccines and the associated pathophysiology.
Related Terms
    Try searching for something
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links