Machine learning approach for detecting Covid-19 from speech signal using Mel frequency magnitude coefficient.

The Covid-19 pandemic is one of the most significant global health concerns that have emerged in this decade. Intelligent healthcare technology and techniques based on speech signal and artificial intelligence make it feasible to provide a faster and more efficient timely detection of Covid-19. The main objective of our study is to design speech signal-based noninvasive, low-cost, remote diagnosis of Covid-19. In this study, we have developed system to detect Covid-19 from speech signal using Mel frequency magnitude coefficients (MFMC) and machine learning techniques. In order to capture higher-order spectral features, the spectrum is divided into a larger number of subbands with narrower bandwidths as MFMC, which leads to better frequency resolution and less overall noise. As a consequence of an improvement in frequency resolution as well as a decrease in the quantity of noise that is included with the extraction of MFMC, the higher-order MFMCs are able to identify Covid-19 from speech signals with an increased level of accuracy. The procedures for machine learning are often less complicated than those for deep learning, and they may commonly be carried out on regular computers. However, deep learning systems need extensive computing power and data storage. Twelve, twenty-four, thirty, and forty spectral coefficients are obtained using MFMC in our study, and from these coefficients, performance is accessed using machine learning classifiers, such as random forests and K-nearest neighbor (KNN); however, KNN has performed better than the other model with having AUC score of 0.80.

Transient Neurological Dysfunction and Intracranial Hypertension After Tourniquet Deflation in a Patient With a Head Injury: A Case Report.

A tourniquet is used during surgery to produce a bloodless surgical field and decrease intraoperative blood loss. Although useful, tourniquets are associated with various physiological alterations both during inflation and deflation phases which may be poorly tolerated in compromised patients. We report a case of transient neurological dysfunction and intracranial hypertension after tourniquet deflation in a 15-year-old patient with a head injury. Intracranial hypertension under general anesthesia was diagnosed based on bradyarrhythmia and elevated ultrasonographic optic nerve sheath diameter as compared to preoperative values.

Heparin-Induced Thrombocytopenia in COVID-19: A Systematic Review.

Background: It has been more than a year since the whole world is struggling with COVID-19 pandemic and may experience resurgences in the near future. Along with severe pneumonia, this disease is notorious for extensive thromboembolic manifestations. That is why experts advocated aggressive anticoagulation as a part of the therapy since the beginning. However, from May 2020 onwards, cases of heparin-induced thrombocytopenia (HIT) are being reported. HIT in itself is an autoimmune entity leading to life-threatening thrombosis in the setting of thrombocytopenia. Continuation of heparin can have disastrous consequences in case of unrecognized HIT. Hence, timely recognition of HIT is of utmost value to modify the anticoagulation strategy and salvaging lives. We performed a systemic review trying to find all reported cases of HIT in COVID-19. Methods: It involved extensive search of the databases including PubMed, Google Scholar, Scopus, and Embase in an attempt to find all reported literature in the last 1 year (November 1, 2019-December 25, 2020) using keywords in various combinations. Literature search resulted in a total of 27 articles and 12 articles were finally selected based on the study design and their relevance pertaining to the intervention done and the outcome of interest. Results: A total of 35 patients were included (mean age 56.7 ± 12.8 years, male-to-female ratio = 2:1). The most frequent comorbidity was hypertension. Fifty-seven percent of cases were with low-molecular weight heparin and the rest with unfractionated heparin. Confirmatory functional assay was done in 85.7% of cases (67% by serotonin-release assay [SRA] and 33% by heparin-induced platelet aggregation [HIPA]). All cases tested with HIPA were positive, while with SRA, only 30% were positive. The most common alternate anticoagulation used was argatroban infusion. The new arterial thrombotic event was seen in only 5.7% of cases as repeat myocardial infarction, stroke, and splenic infarction, while clinically significant bleeding was seen in 17.1% of cases. Fifty percent of bleeding episodes were seen where conventional doses of argatroban were used, while no mortality was seen with low-dose argatroban infusion. However, only 45.7% of patients were discharged, 31.4% of patients died, while the outcome was pending for 23% of patients. Conclusion: Severe endotheliitis and immune dysregulation giving rise to HIT antibodies and antiphospholipid antibodies have been demonstrated in COVID-19 and modifying our therapy becomes indispensable when it is pathogenic with potentially fatal consequences. In the light of interim results of REMAP-CAP study in severe COVID-19 cases where heparin does not improve the outcome, the present anticoagulation strategy needs re-evaluation. Unrecognized HIT can be catastrophic and close clinical monitoring is required for patients on heparin therapy.