Effect of COVID-19 on Stock Market Prediction Using Machine Learning

Share market is a chaotic and ever-changing place for making predictions, as there is no defined procedure to evaluate or forecast the value of a share of a company. Methods like time series, technical, statistical and fundamental analysis are used to predict the price of a share. However, these methods have not proven to be very consistent and precise for making predictions. COVID-19 has further deteriorated the chances to find such a tool as the markets have taken a huge hit in the first quarter of 2020. In this paper, support vector machine and multiple regression algorithms will be implemented for predicting stock market prices. Our aim is to find the machine learning algorithm which can predict the stock prices most accurately before and during the pandemic. The accuracy for every algorithm will be compared and the algorithm which is the most accurate would be considered ideal. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A population-based approach todigital outreach, triage, andmonitoring of ibd patients duringthe covid-19 pandemic

Background In March 2020, the Mount Sinai Health System InflammatoryBowel Disease (IBD) center reported an increase in telephonecall volume, with many IBD patients expressing anxiety aboutbeing on immunosuppressive agents during the COVID-19pandemic. Consistent with GI society and CDCrecommendations, we leveraged the Rx.Universe platform(Rx.Health, New York, NY) to rapidly design and deliver apopulation-based digital navigation program (DNP) to provideoutreach, remote COVID-19 symptom monitoring, triage, andTelehealth to IBD patients. Methods After identifying all IBD patients seen in our IBD center fromElectronic Health Records (Epic Systems), we 'bulk prescribed'the DNP (Rx.Health, New York NY) to 6100 patients'smartphones. Patients were asked to reply to the prompt if theyhad new or worsening COVID-19 symptoms and opted-in toregular digital monitoring through an electronic patientreported outcome (ePRO) instrument. Patient data was screenedby our clinical coordinators, who directly contacted patients viaphone calls and scheduled testing and Telehealth visits with IBDpractitioners when appropriate. Results Of the 6100 patients who were sent the DNP, 1829 patientsopted-in to be regularly monitored using text-based electronicpatient reported outcome (ePRO) instruments. Of those whoresponded affirmatively, 145 patients were identified requiringadditional medical attention and were triaged using Telehealthvisits. Compared to patients who chose not to opt-in, patientswho opted-in were more likely to be female, white, married, onbiologics, and had high inflammatory markers (Table 1). Conclusion As demonstrated by the 30% of patients who opted-in to regularCOVID-19 symptom monitoring, a digital navigation programpopulation approach is an effective and efficient approach toprovide continuity of care and to mitigate COVID-19 exposure ina high-risk, immunosuppressed IBD population. This scalableapproach serves as a model for providing high quality, remotemonitoring to patients during COVID-19 and beyond, as well asachieving 'Treat to Target' goals.