Precision Diagnosis to Discriminate Covid-19 and Pneumonia using Mixed-data Model based on Custom Neural Networks

Classifying Covid-19 and Pneumonia is one of the most important and challenging tasks in the field of the medical sector since manual classification with human assistance can lead to incorrect prediction and diagnosis. Additionally, it is a difficult operation when there is a lot of data that need to be analyzed thoroughly. Due to the similarity in symptoms as well as in chest X-ray images of Covid-19 and Pneumonia diseases, it is difficult to distinguish those. The study presents a technological solution to build a mixed-data model using customized neural networks to discriminate between Covid-19 and Pneumonia. The proposed method is applied to the chest X-ray images and symptoms of patients of Covid-19 and Pneumonia. This helps to perform immediate prediction of Covid-19 and Pneumonia providing fast and specialized treatment to the patients appropriately. This prediction also helps the radiologist or doctors in making quick decisions. In this work, imaging data (such as Chest X-ray images) and text data (such as disease symptoms like cough, body pain, short breathing, fever, etc.) are taken for detecting Covid-19, Pneumonia and Normal patients. Data Synthesis is carried out due to the unavailability of mixed data and it has created dataset of 450 entries of Covid-19, Normal and Pneumonia cases. The goal is to design a system that accurately classifies Covid19, Pneumonia, and Normal patients by utilizing convolutional neural networks (CNN) and multi-layer perceptron (MLP) algorithms. An accuracy of 93.33% is obtained for the mixed-data model using a deep neural network, that is designed by combining custom CNN and MLP architectures. © 2022 IEEE.

Clinical profile of SARS-CoV-2 infection-associated pediatric Multisystem Inflammatory Syndrome (MIS-C): A case series from Western Maharashtra

Background and Objectives: Multisystem inflammatory syndrome (MIS-C) is a SARS-COV-2 infection-associated dreaded clinical sequelae in pediatric patients. Its epidemiology is complex and differs from severe acute COVID-19 infection in children. The present case-series report describes the various clinical features, laboratory markers, and interventions among 222 pediatric patients from one of the states in India with the highest prevalence of COVID-19 infection. Methods: An observational study was conducted at one of the tertiary healthcare institutes in the western region of Maharashtra state of India. Twenty-two children were hospitalized with diagnosed MIS-C, aged from 2 months to 18 years, from January to June 2021. Demographic and clinical characteristics and diagnostic and treatment parameters were collected from each subject. Statistical Package for Social Sciences version 21 software was used as a data analysis tool. Results: Clinical assessment revealed high-grade fever, non-purulent conjunctivitis, and abdominal complaints, which were the leading presentations of MIS-C. In inflammatory markers, serum IL-6 levels and D-dimer levels took a longer duration for normalization in the severe MIS-C group. Almost half of the mild-moderate MIS-C patients were managed with only systemic corticosteroids. All remaining patients recovered with the dual therapy of intravenous immunoglobulins (2 g/kg) and systemic corticosteroids with an improved clinical and biological response. Conclusions: The present clinical case-series report concluded that almost all MIS-C cases have a favorable prognosis with dual therapy of corticosteroids and immunoglobulins. With the principle of early diagnosis and prompt treatment, it is possible to manage patients without any critical support. However, long-term follow-up studies of these cases are warranted to validate the clinical approach. © 2022 Medical Journal of Dr. D.Y. Patil Vidyapeeth ;Published by Wolters Kluwer - Medknow.

Face Mask Detection and Recognition System

As today a disease called COVID-19 is causing health crisis and deaths, it became most essential to wear a mask for protecting ourselves from Corona virus. Even in public areas, where is more rush we should wear mask as no virus can spread from person to person if any one of person from public is Corona positive. This paper introduces face mask detection that can be used by the authorities to make mitigation, evaluation, prevention, and action planning against COVID19. So basically in this project we are going to use Python, Keras, OpenCV alongwith MobileNet for this Face Mask Detection System. This includes some steps like data preprocessing, training and testing the model, run and view the accuracy and applying model in the camera. The inputs has provided here are 1000+ images of people with mask and without mask. First the data get processed and then by checking features of each image it will train all the models and the persons with and without mask get separated to two categories: with mask and without mask. If person is wearing mask with 90 or more percent of accuracy, then he will get added to with mask category and person not wearing mask get added to without mask category, so that we can permit with mask person to public areas. © 2022 IEEE.

Bringing experimental therapeutics clinical trials network (ETCTN) to underrepresented population

Background: Access to health care including clinical trials (CT) leading to paradigm-changing cancer treatments are critical for high quality cancer care and equity in society. In this report, we highlight methods in accruing to ETCTN wherein underrepresented rural, low-income, and racial minorities comprise >50% of enrollment. Methods: University of Kansas Cancer Center (KUCC) is one of eight National Cancer Institute (NCI) designated cancer centers awarded CATCH-UP.2020 (CATCH-UP), a congressionally mandated P30 supplement to enhance access for minority/underserved populations to ETCTN precision medicine CT. KUCC catchment area is 23% rural by Rural Urban Continuum Codes (RUCC);almost 90 % of counties are designated primary care HPSA's (Health Professional Shortage Areas). KUCC Early Phase and Masonic Cancer Alliance (rural outreach network) partnered to operationalize CATCH-UP. We engaged disease-focused champion investigators in disease working groups and MCA physicians who selected scientifically sound CT that fit catchment area needs. Patient and Investigator Voices Organizing Together, a patient research advocacy group provided practical feedback. MCA navigator coordinated recruitment. Telehealth was used for rural patients that would have a significant distance to travel just to be screened. Results: CATCH-UP was initiated in September 2020. Twenty-eight CT were activated, many in community sites. Average activation time was 81 days. Delays were mainly from CT amendments. KUCC enrolled the first patient in the CATCH-UP program. In 6 months, we met accrual requirements (24/year, 50% minorities). During first year, we enrolled 47 (>50% minorities), an increase of 680% from our average accrual of 6/year (>50% minorities) in ETCTN through Early Drug Development Opportunity Program (2016-2020). To date, we have enrolled 61, 54% from rural, HPSA, race and other minorities. Although the proportion of minorities did not change but remained high, this funding allowed us to substantially increase the number of patients from a catchment area with high proportion of geographically and socioeconomically underserved minorities given access to early phase CT through ETCTN. Conclusions: Amid COVID-19 pandemic, the NCI CATCH-UP program and methods we used allowed access to novel therapies for rural, medically underserved, and other minority groups.

COVID-19 Outcomes Among Participants in the NHLBI Myelodysplastic Syndromes (MDS) Natural History Study

Introduction: The NHLBI MDS Natural History Study (NCT02775383) is an ongoing prospective cohort study conducted across 144 sites in the U.S. and Israel intended to establish a data and biospecimen repository to advance the understanding of MDS. In response to the COVID-19 pandemic, the study also collected data on COVID-19 infection and management. Here, we report a summary of COVID-19 outcomes from participants in this study and the impact of the pandemic on study operations. Methods: This prospective cohort study initiated in June, 2016 is enrolling patients (pts) undergoing diagnostic work up for suspected or newly diagnosed MDS or MDS/myeloproliferative neoplasms (MPNs) in the setting of cytopenia. Study enrollment was paused from Mar. 27, 2020 to May 18, 2020 due to COVID-19. Previously untreated pts underwent a bone marrow assessment with a centralized histopathology review at enrollment for assignment to a longitudinal cohort (MDS, MDS/MPN overlap, idiopathic cytopenia of undetermined significance (ICUS), acute myeloid leukemia (AML) with <30% blasts, or “At-Risk” (pts with sub-threshold dysplasia, select karyotype, or select genetic mutations) for follow-up every six months;or a cross-sectional cohort (other cytopenia or cancers) with no further follow-up. COVID-19 outcomes, including tests, status, hospitalizations and treatments for COVID-19, were collected for all eligible pts. Protocol deviations related to COVID-19 were also collected. Fisher's exact test was used for comparing the proportions of pts tested or positive between groups. Results: Of 758 eligible pts with available COVID-19 data, 507 (67%) were assigned to the longitudinal cohort and 251 (33%) to the cross-sectional cohort or are pending assignment. Among longitudinal pts, 74 (15%) had ICUS, 240 (47%) MDS, 47 (9%) MDS/MPN overlap, 11 (2%) AML with <30% blasts, and 135 (27%) At-Risk for MDS. The median age over all pts was 72 years (range=21-95) and 66% were male, 92% White, 4% Black, 2% Asian, and 2% other. Among 244 pts (32%) tested for COVID-19 (Table 1), 23 (9%) were positive. Twelve (>50% of the positive pts) were in Wisconsin, California (CA), and Missouri (Figure 1), with 8 identified from Sep. to Dec. 2020, which overlaps with third waves of COVID-19 reported in CA and in the Midwest. Tests from 17 (74%) of the 23 pts were based on a polymerase chain reaction (PCR) assay. The proportion of pts positive were similar between pooled disease (ICUS, MDS, MDS/MPN, AML <30%), At-Risk, and cross-sectional groups (8%, 8%, 16%, respectively;Table 2) but the proportions tested differed significantly (39%, 28%, and 25%, respectively, p=0.004). Among all positive pts, 21 (91%) are recovering or have recovered (16 with sequelae), 1 (4%) died, and 1 outcome is unknown (Table 1). The one participant who died had MDS with excess blasts-1 (MDS-EB1, 5-9% blasts). Eight pts (35% of positive pts) required hospitalization (median duration of 7 days (range=2-17)) or treatment (tx) in response to COVID-19, 7 of whom required both. In the 8 pts who required tx for COVID-19, 4 reported Remdesivir-use, 3 of whom were diagnosed with MDS or MDS/MPN overlap. The study monthly accrual rates were similar when compared pre- vs. post-study pause (23 vs. 22 pts, respectively) but the rate of missed follow-up visits increased from 5% to 11% post-pause. About half (49%) of the 144 COVID-19-related study deviations occurred during the months the study was paused. Conclusions: In this analysis of 758 pts with MDS and related conditions, the largest reported for these diagnoses, the COVID-19 mortality rate (13%) in MDS was lower than has been reported in a smaller (n=61) case study (39%, Feld et al Blood 2020) but is similar to the rates for MDS observed annually each year prior to study pause (range=11-19%) and to the rate reported in a larger (n=2186) observational study of cancer patients (16%, Rivera et al Cancer Discov 2020). Infection rates were similar across disease groups. The pandemic also resulted in substantial study-specific challenges, including incre sed rate of deviations, the study being paused, and difficulty sourcing material for biospecimen processing. Data on vaccine efficacy and rates of pts with long-haul symptoms post-COVID may be of interest in future work. [Formula presented] Disclosures: Padron: BMS: Research Funding;Kura: Research Funding;Taiho: Honoraria;Stemline: Honoraria;Blueprint: Honoraria;Incyte: Research Funding. Komrokji: Novartis: Honoraria;Geron: Honoraria;Acceleron: Honoraria;Agios: Honoraria, Speakers Bureau;Abbvie: Honoraria, Speakers Bureau;JAZZ: Honoraria, Speakers Bureau;BMS: Honoraria, Speakers Bureau. Saber: Govt. COI: Other. Al Baghdadi: Bristol-Myers Squibb: Current holder of individual stocks in a privately-held company, Membership on an entity's Board of Directors or advisory committees;AstraZeneca: Current holder of individual stocks in a privately-held company;Epizyme: Current holder of individual stocks in a privately-held company;Heron Therapeutics: Current holder of individual stocks in a privately-held company;Morphosys: Membership on an entity's Board of Directors or advisory committees;Karyopharm: Membership on an entity's Board of Directors or advisory committees;Cardinal Health: Membership on an entity's Board of Directors or advisory committees. DeZern: Taiho: Consultancy, Membership on an entity's Board of Directors or advisory committees;Novartis: Consultancy, Membership on an entity's Board of Directors or advisory committees;Bristol-Myers Squibb: Consultancy, Membership on an entity's Board of Directors or advisory committees;Takeda: Consultancy, Membership on an entity's Board of Directors or advisory committees. Sekeres: Novartis: Membership on an entity's Board of Directors or advisory committees;Takeda/Millenium: Membership on an entity's Board of Directors or advisory committees;BMS: Membership on an entity's Board of Directors or advisory committees.