Social Economic Impacts for Covid-19 Pandemics Using Machine Learning Based Optimization Algorithm

As the number of COVID-19 patients grows exponentially, not all cases are likely dealt with by doctors and medical professionals. Researchers will add to the fight against COVID-19 by developing smarter strategies to achieve accelerated control of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), virus that causes disease. Proposed method suggests best ways to optimize protection and avoid COVID-19 spread. Big benefit of the hybrid algorithm is that COVID-19 is diagnosed and treated more rapidly. Pandemic diseases possibilities are handling with help of Computational Intelligence, using cases and applications from current COVID-19 pandemic. This work discusses data that can be analyzed based on optimization algorithm which provides betterCOVID-19 detection and diagnosis. This algorithm uses a machine learning model to decide how the hazard function changes concerning characteristics of potential methods to find parameters in optimization of machine learning model, which has in many cases been shown to be accurate for actual clinical datasets. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Utilization of Transfer Learning Model in Detecting COVID-19 Cases From Chest X-Ray Images

Diagnosis of COVID-19 pneumonia using patients' chest x-ray images is new but yet important task in the field of medicine. Researchers from different parts of the globe have developed many deep learning models to classify COVID-19. The performance of feature extraction and classifier plays a vital role in the recognizing the different patterns in the image. The pivotal process is the extraction of optimum features from the chest x-ray images. The main goal of this study is to design an efficient hybrid algorithm that integrates the robustness of MobileNet (using transfer learning approach) to extract features and support vector machine (SVM) to classify COVID-19. Experiments were conducted to test the proposed algorithm, and it was found to have a high classification accuracy of 95%.

Phase II trial of GVDexa (gemcitabine, vinorelbine and dexamethasone) regimen in relapsed/refractory Hodgkin's lymphoma

Background: Gemcitabine, vinorelbine and liposomal doxorubicin (GVD) is an effective regimen in relapsed/refractory Hodgkin's lymphoma (RRHL). Conventional second-line chemotherapy is still required as the cost of immunotherapy and antibody-drug conjugates are prohibitive to Indian patients. We report the results of a phase II, open-label, single-arm, single centre interventional study in RRHL where dexamethasone replaced liposomal doxorubicin. Methods: Adult patients (≥18 years) with RRHL at first or second relapse were included. GVDex was delivered as outpatient once in 3 weeks (Gemcitabine 1000 mg/m2 IV over 30 min on D1,8;Vinblastine 25 mg/m2 IV fast infusion on D1,8;Dexamethasone 40 mg PO D1-4) for two cycles followed by interim PET CT assessment by Cheson's criteria and Deauville scoring. The primary endpoint was the objective response rate (ORR = complete response + partial response). The sample size was calculated using Fleming's 2-stage model (α error: 0.05 and power: 0.8). Twenty patients were required in the first stage. If there were ≥16 responses, the null hypothesis would be rejected and the study stopped. Results: Between May 2016, and December 2020, 26 patients with RRHL were screened, and 20 were enrolled: primary resistant HL-8 patients (40%) and relapsed HL-12 patients (60%). The median age was 35 years (range:20-52). Six patients (30%) presented with limited stage and 14 patients (70%) with advanced stage HL at relapse. GVdex was delivered as a first salvage regimen in 18 patients (90%) and second in 2 patients. After 2 cycles of GVDex, 16 (80%) had responded [partial response: 12 (60%);complete response: 4 (20%)]. Median number of cycles of GVDex: 3 (range: 1-4). Five patients (25%) required dose reductions due to chemotherapy-related toxicities. The median duration of objective response was 13.4 months. Eleven patients (55%) underwent highdose chemotherapy supported by autologous stem cell rescue. After a median follow-up of 25 months (95% CI: 5.9-44.5), the median progression-free survival (PFS) was 24.7 months, and the median overall survival (OS) has not been reached. The estimated 2-year PFS was 44%, and the 2-year OS was 79%. The most common treatment-related adverse events were anemia (100%), neutropenia (70%, 14/20) and fatigue (70%, 14/20). Grade 3 or 4 treatment-related AEs occurred in 14 patients (70%). Grade ≥3 neutropenia occurred in 9 patients (45%) and febrile neutropenia in 3 patients (15%). Serious adverse events were reported in 3 patients (15%). One patient developed Ficat and Arlet classification stage III avascular necrosis of the femoral head. One patient died due to suspected COVID-19 pneumonia (non-neutropenic fever) before cycle 2 of chemotherapy. Conclusions: GVDex it is an effective salvage regimen with acceptable toxicity in patients with RRHL.