Ayesan Rewane’s research while affiliated with Rush University Medical Center and other places

Background: COVID-19 pandemic has dramatically engulfed the world causing catastrophic damage to human society. Several therapeutic and vaccines have been suggested for the disease in the past months, with over 150 clinical trials currently running or under process. Nevertheless, these trials are extremely expensive and require a long time, which presents the need for alternative cost-effective methods to tackle this urgent requirement for validated therapeutics and vaccines. Bearing this in mind, here we assess the use of in silico clinical trials as a significant development in the field of clinical research, which holds the possibility to reduce the time and cost needed for clinical trials on COVID-19 and other diseases. Methods: Using the PubMed database, we analyzed six relevant scientific articles regarding the possible application of in silico clinical trials in testing the therapeutic and investigational methods of managing different diseases. Results: Successful use of in silico trials was observed in many of the reviewed evidence. Conclusion: In silico clinical trials can be used in refining clinical trials for COVID-19 infection.

This cohort study examines antibody responses in infection-naive and previously infected individuals after 1 and 2 doses of the BNT162b2 vaccine.

Abstract Background: COVID-19 pandemic has dramatically engulfed the world causing millions of deaths in almost all human populations. Several therapeutic and vaccines have been suggested for the disease with over 150 clinical trials currently running or under process. Nevertheless, these trials are hugely expensive and require a very long time, which presents the need for alternative cost-effective methods to tackle this urgent requirement for a validated therapeutics and vaccines. Bearing this in mind, here we assess the use of in silico clinical trials as a significant development in the field of clinical research which holds the possibility to reduce the time and cost needed in clinical trials on COVID-19 and other diseases. Material& Methods: Using the PubMed database, we analyzed eight relevant scientific articles regarding the possible application of in silico clinical trials in testing the therapeutic and investigational methods related to different diseases. Results: Successful uses of in silico trials were observed in all of the reviewed articles. Conclusion: In silico clinical trials can be effectively used in refining clinical trials for the COVID-19 pandemic. Poster Link: https://events.labroots.com/event/Coronavirus2020/en-us/contents/647765/share?rid=PosterHall&nid=1142199

This study aimed to identify the best features that predict COVID-19 infection risk status (“Low”, “Medium”, “High”) of an individual, using statistical feature selection methods and interpretable Machine learning models. The research analyzed a publicly available dataset obtained from a web-based COVID-19 risk assessment calculator. Fifty-seven (57) of the 59 features in the dataset were first filtered for multicollinearity using the Pearson Correlation Coefficient, and are further shrunk to 55 features with LASSO GLM. A class imbalance was identified in the dataset, same was addressed with SMOTE resampling technique. Multiple interpretable ML algorithms were explored during the classification phase. The best classifier predictions were saved as a new instance and were perturbed with a single Decision tree classifier. To further build trust and explainability of the best model, the XGBoost classifier was utilized as a global surrogate model to train predictions of the best model. The XGBoost individual’s explanation was done using the SHAP explainable AI framework. Random Forest classifier with a validation accuracy score of 96.35 % from 55 features reduced by feature selection emerged as the best classifier model. The decision tree classifier approximated the best classifier correctly with a prediction accuracy score of 92.23 % and Matthew’s correlation coefficient of 0.8960. The XGBoost classifier approximated the best classifier model with a prediction score of 99.7 %. This study identified COVID-19 positive, COVID-19 contacts, COVID-19 symptoms, health workers, and public transport count as the five major predictors of COVID-19 risk exposure status of an individual.

COVID-19 has rapidly spread across the globe and was declared a pandemic by the World Health Organization (WHO). The COVID-19 infection continues to spread across Africa. In Africa, mobile phone applications have been used for the surveillance and reporting of infectious diseases such as malaria, measles, polio, and other notifiable diseases as mandated by the WHO. A good example is the early warning alert and response system. We developed an eight-question triage tool using the Nigerian Centre for Disease Control surveillance case definitions for new coronavirus disease. Based on the assessed risk level we offered advice and guidance on the next steps. A user-administered tool such as this is vital to COVID19 control. It is also significant in relieving the burden on health systems, providing information on national health guidelines for prevention and control, fostering the participation of citizens, and giving them the next steps, pandemic control efforts become more effective.

Background: COVID-19 pandemic has dramatically engulfed the word causing catastrophic damage to the human society. Several therapeutic and vaccines has been suggested for the disease with over 150 clinical trial currently running or under process. Nevertheless, these trials are hugely expensive and require a very long times, which present the need for an alternative cost effective methods to tackle this urgent requirements for validated therapeutics and vaccine. Bearing this in mind, here we assess the use of in silico clinical trials as a significant development in the field of clinical research which hold the possibility to reduce the time and cost needed in clinical trials on COVID-19 and other disease. Methods: Here we analyzed six relevant scientific articles regarding possible application of in silico clinical trial in testing the therapeutic and investigational methods managing different diseases using PubMed database. Finding: Successful uses of in silico trials was observed in many of the reviewed evidence. Interpretation: we deduced from this review that more focus and fund should be put on in silico clinical trials as it help in refinement and partial replacing of the current long conventional clinical trials on COVID-19. Abstract: Background: COVID-19 pandemic has dramatically engulfed the word causing catastrophic damage to the human society. Several therapeutic and vaccines has been suggested for the disease with over 150 clinical trial currently running or under process. Nevertheless, these trials are hugely expensive and require a very long times, which present the need for an alternative cost effective methods to tackle this urgent requirements for validated therapeutics and vaccine. Bearing this in mind, here we assess the use of in silico clinical trials as a significant development in the field of clinical research which hold the possibility to reduce the time and cost needed in clinical trials on COVID-19 and other disease. Methods: Here we analyzed six relevant scientific articles regarding possible application of in silico clinical trial in testing the therapeutic and investigational methods managing different diseases using PubMed database. Finding: Successful uses of in silico trials was observed in many of the reviewed evidence. Interpretation: we deduced from this review that more focus and fund should be put on in silico clinical trials as it help in refinement and partial replacing of the current long conventional clinical trials on COVID-19. Funding: no funding was acquired for this paper.

Since the outbreak of the Coronaviruses (CoV) in Wuhan China, it continues to spread across countries like wildfire, defiling all the measures put in places by government and individuals to curb it. Corona virus belongs to a large family of viruses that cause illness ranging from the common cold to more severe diseases such as Middle East Respiratory Syndrome (MERS-CoV) and Severe Acute Respiratory Syndrome (SARS-CoV). Common symptoms of the infection include respiratory difficulties, fever, cough, shortness of breath and breathing difficulties. In more complicated cases, infection may lead to pneumonia, severe acute respiratory syndrome, kidney failure and even death. The continuous rise in the spread of the virus has continue to pose great setback to the entire scientific community and humanity. The difficulties in containing the spread of the virus across localities is challenging and required drastic measures. It is in the light of this that this research proposed an urgent end-to-end data driven modeling approach that will utilize tweets, open public healthcare data and online survey applications to collect data that will be feed to a Supervised Machine learning model in order to ascertain individual’s exposure risk status. Individuals exposed to the virus or noticed some symptoms of the infection and perhaps scared of reporting to local authorities can utilize this platform to join in curbing the spread of the virus. This will develop a more fast and efficient way for individuals to predicts their risk status with regards to the activities and symptoms they developed from present to past two-three weeks. This information can assist healthcare officials to identify/report emergence cases and ensure they access timely health care and self-isolation methods in their respective locations. This aimed to enhance citizens know their current and future risk status in their respective locations for continuous monitoring by healthcare officials so as to avoid spreading the virus further among loved ones, neighbors, etc. and to make it easy for healthcare officials to redistribute healthcare facilities. Creating a data driven model application that will bring the stakeholders and government closer to its’ citizens at such a time as this with regards to curbing the spread of the COVID19 virus is paramount, in order to assist them in designing the best policies, timely response and mitigating measures across the globe. Keywords: Supervised Machine Learning, COVID19, Percentage Risk of COVID19, Monitoring, Health status