Understanding the Effects of Human Factors on the Spread of COVID-19 Using a Neural Network

During the spread of an infectious disease such as COVID-19, the identification of human factors that affect the spread is a really important area of research. These factors directly impact the spread of such a disease and are important in identifying the various regions that are at a higher risk than others. This allows for an optimal distribution of resources according to predicted demand. Traditional infectious modeling techniques are good at representing the spread and can incorporate multiple factors that resemble real-life scenarios. The primary issue here is the identification of relevant variables. In this study, a residual analysis is presented to downsize the dataset available and shortlist the variables classified as absolutely necessary for disease modeling. The performance of different datasets is evaluated using an Artificial Neural Network and regression analysis. The results show that the drop in performance using the reduced dataset is reasonable as it is very difficult to obtain a perfect dataset covering only necessary variables. This approach can be automated in the future as it offers a small dataset containing a few variables against a large dataset with possibly hundreds of variables. © 2020 IEEE.

Identifying Factors in COVID-19 AI Case Predictions

Many machine learning methods are being developed to predict the spread of COVID-19. This paper focuses on the expansion of inputs that may be considered in these models. A correlation matrix is used to identify those variables with the highest correlation to COVID-19 cases. These variables are then used and compared in three methods that predict future cases: a Support Vector Machine Regression (SVR), Multidimensional Regression with Interactions, and the Stepwise Regression method. All three methods predict a rise in cases similar to the actual rise in cases, and importantly, are all able to predict to a certain degree the unexpected dip in cases on the 10th and 11th day of prediction. © 2020 IEEE.

CAPTURE: Cancer and COVID-19antiviral immune monitoring study

Introduction: Certain retrospective and registry-based studies have indicated a higher risk of COVID-19 adverseoutcomes in cancer, but a detailed understanding of the immune response in cancer patients and the impact ofcancer therapy is needed. CAPTURE is a pan-cancer, prospective longitudinal study established in response to theunique challenges of SARS-CoV-2 pandemic for the care of cancer patients. Experimental Procedures: CAPTURE is a multicenter, UK-based longitudinal cohort study that commencedrecruitment in May 2020. Study participants are recruited from a broad range of cancer types and cancerinterventions and irrespective of their SARS-CoV-2 status, in order to capture both the nominator and thedenominator. In addition to cancer patients, the study participants also include health care workers (HCW) for thepurpose of studying transmission dynamics. Detailed clinical, epidemiologic, and demographic data are collectedfrom all participants alongside a range of biologic samples that underpin case definitions and will facilitate immunemonitoring. All participants will be followed up longitudinally for up to five years. Results: The overarching aim is to establish a prospective and unbiased understanding of the susceptibility andmorbidity of COVID-19 in cancer patients and the patterns of viral nosocomial transmission. We will follow uppatients long-term to understand the extent and duration of immunity and how immunity is impacted by cancer type, stage, and therapy. Our comprehensive sampling will help to draw a detailed picture of immune response to SARS-CoV-2 in cancer patients by monitoring active infection, antibody response, and T-cell activation, supplemented bydetailed immunophenotyping, transcriptome, TCR/BCR sequencing, and germline profiling for HLA typing andidentification of disease-associated polymorphisms. Finally, while there is a well-established correlation of circulatingcytokine levels and Covid-19 severity, CAPTURE will identify early indicators of a maladapted inflammatoryresponse in cancer patients by cytokine and chemokine profiling to establish early biomarkers of disease severity.Within the first month, we have recruited 95 participants (54% cancer patients, 46% HCWs) with matching swabs, plasma, PBMC, and whole blood for RNA sequencing. Two longitudinal samples were collected on average. Resultsfrom antigen and antibody profiling within this cohort will be presented at the meeting. Conclusion: CAPTURE will provide a detailed understanding of the interaction between immune response toSARS-CoV-2, cancer, and cancer treatments. Results will be informative in a wider health care context in order tominimize harm and maximize cancer outcomes in a sustainable manner. Furthermore, given inherent and iatrogenicdefects in discreet immune cell subsets, this is a key patient cohort to inform a wider understanding of the immuneresponse to SARS-CoV-2.