Deep learning-based hybrid clinical decision support system algorithm for COVID-19 diagnosis via PCR graphics and Thorax CT images, preliminary data

Introduction: The limited sensitivity of microbiological testing, challenges in radiological differential diagnosis, and expectations of quick and accurate diagnosis required developing clinical decision support systems (CDSS). We propose a new deep learning-based hybrid CDSS that combines the advantageous aspects of thorax computed tomography(CT) and reverse transcriptase-polymerase chain reaction(PCR) to overcome the weakness of each one. Method(s): We retrospectively constructed a database that contains CT images of healthy subjects and patients with COVID-19 pneumonia(CP), bacterial/viral pneumonia(BVP), interstitial lung diseases(ILD), and PCR data of patients who were tested positive and negative for SARS-CoV-2. A new 3D-convolutional neural network (3D-CNN) and long short-term memory network(LSTM) based CDSS is developed to perform accurate and robust detection of COVID19 using CT images and PCR data. Result(s): Performance results of the proposed models (Fig1) provide highly reliable diagnosis of COVID-19 with 93.2% and 99.7% AUC for CT and PCR data, respectively. Conclusion(s): Proposed CDSS with state-of-the-art deep learning methods provides similar performance compared to both radiologists in CT evaluation and microbiologists in PCR evaluation and can be safely used. We plan to develop a hybrid CDSS algorithm further, combining laboratory data with CT and PCR models.

Repurposing Sitagliptin for COVID-19 in Adults: Clinical Benefits and An Approach for the Mechanism

Introduction: Dipeptidyl peptidase-4 (DPP4) has been shown to be a functional receptor for MERS-CoV. An interaction between the viral spike protein and DPP4 is thought to facilitate viral entry. We aimed to find out whether sitagliptin, a member of DPP4 inhibitors, would have beneficial effects in COVID-19 patients. Materials and Methods: In this single center retrospective study, we evaluated 58 patients of whom 16 were on sitagliptin treatment. Molecular docking studies were performed to identify possible interactions between ACE2 and sitagliptin. Results: Sitagliptin use shortened the time to clinical recovery about 3.5 and fastened viral clearance more than 5 days. Resolution of all symptoms was achieved on a mean±standard error (SE) of 2.50 ± 0.40 days in sitagliptin (+) group and 5.69 ± 0.61 days in sitagliptin (-) group (Log-rank test, p< 0.001). PCR tests for SARS-CoV-2 resulted negative in mean ± SE of 7.50 ± 0.98 days in sitagliptin (+) and 13.17 ± 1.07 days in sitagliptin (-) group (Log-rank test, p= 0.003). Compared to day 0, CRP, ferritin and D-dimer levels on days three, five, and seven were significantly lower whereas lymphocyte count was higher in sitagliptin (+) group. Conclusion: Our results suggest that sitagliptin seems to have a potential to be considered for the treatment of COVID-19.

Subacute thyroiditis during the COVID-19 pandemic: a prospective study.

PURPOSE: Subacute thyroiditis(SAT) is a destructive thyroiditis associated with viral infections. Several SAT cases associated with SARS-CoV-2 infection/vaccination were recently reported. We aimed to evaluate prospectively all cases applied to our tertiary center and their relationship with SARS-CoV-2 during 16 months of the pandemic. Cases during similar pre-pandemic period were recorded for numeric comparison. METHODS: Prospective study took place between March 2020 and July 2021. SAT was diagnosed by classical criteria. Swabs for SARS-CoV-2 and a wide respiratory viral panel (RV-PCR) were taken. Previous COVID-19 was assessed by SARS-CoV-2 IgM&IgG levels. Study group was divided into three as: CoV-SAT, patients who had or still have COVID-19, Vac-SAT, patients diagnosed within three months after SARS-CoV-2 vaccination and NonCoV-SAT, those not associated with COVID-19 or vaccination. RESULTS: Out of 64 patients, 18.8% (n = 12) was classified as CoV-SAT, 9.3% (n = 6) as Vac-SAT and 71.9% as (n = 46) NonCoV-SAT. SARS-CoV-2 RT-PCR tests on the diagnosis of SAT were negative in all, but two patients tested positive five days later, in second testing, performed upon clinical necessity. CoV-SAT and NonCoV-SAT groups were similar in terms of clinical, laboratory, and treatment characteristics. However, symptoms were milder and treatment was easier in Vac-SAT group (p = 0.006). CONCLUSIONS: Total number of SAT cases during the pandemic period was comparable to pre-pandemic period. However, a considerable rate of SARS-CoV-2 exposure in SAT patients was established. COVID-19 presented with SAT, as the first manifestation in three cases. Vaccine-related cases developed in a shorter time period, clinical presentation was milder, and only a few required corticosteroids.

COVID-19 and Bacterial Co-Infection: Fusobacterium Bacteremia

Coronavirus Disease 2019 (COVID-19) is a viral infection first seen in Wuhan, China, in December 2019 and then affected the whole world by causing a pandemic. The disease may be asymptomatic, and symptoms such as fever, cough, shortness of breath, weakness, headache, and sore throat can be seen. Various bacterial infections may accompany the process in some COVID-19 patients. In this case, accompanying Fusobacterium nucleatum bacteremia in a patient diagnosed with COVID-19 was examined.