Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 6 de 6
Open Forum Infectious Diseases ; 8(SUPPL 1):S298, 2021.
Article in English | EMBASE | ID: covidwho-1746602


Background. The COVID-19 pandemic has brought to light the importance of contact tracing in outbreak management. Digital technologies have been leveraged to enhance contact tracing in community settings. However, within complex hospital environments, where patient and staff movement and interpersonal interactions are central to care delivery, tools for contact tracing and cluster detection remain limited. We aimed to develop a system to promptly, identify contacts in infectious disease exposures and detect infectious disease clusters. Methods. We prototyped a 3D mapping tool 3-Dimensional Disease Outbreak Surveillance System (3D-DOSS), to have a spatial representation of patients in the hospital inpatient locations. Based on the AutoCAD drawings, the hospital physical spaces are built within a game-development software to obtain accurate digital replicas. This concept borrows from the way gamers interact with the virtual world/space, to mimic the interactions in physical space, like the SIMS franchise. Clinical, laboratory and patient movement data is then integrated into the virtual map to develop syndromic and disease surveillance systems. Risk assignment to individuals exposed is through mathematical modeling based on distance coordinates, room type and ventilation parameters and whether the disease is transmitted via contact, droplet or airborne route. Results. We have mapped acute respiratory illness (ARI) data for the period September to December 2018. We identified an influenza cluster of 10 patients in November 2018. In a COVID-19 exposure involving a healthcare worker (HCW), we identified 44 primary and 162 secondary contacts who were then managed as per our standard exposure management protocols. MDRO outbreaks could also be mapped. Conclusion. Through early identification of at-risk contacts and detection of infectious disease clusters, the system can potentially facilitate interventions to prevent onward transmission. The system can also support security, environmental cleaning, bed assignment and other operational processes. Simulations of novel diseases outbreaks can enhance preparedness planning as health systems that had been better prepared have been more resilient in this current pandemic.

Intelligent Systems Conference, IntelliSys 2021 ; 296:877-884, 2022.
Article in English | Scopus | ID: covidwho-1391762


A novel coronavirus disease has emerged (later named COVID-19) and caused the world to enter a new reality, with many direct and indirect factors influencing it. Some are human-controllable (e.g. interventional policies, mobility and the vaccine);some are not (e.g. the weather). We have sought to test how a change in these human-controllable factors might influence two measures: the number of daily cases against economic impact. If applied at the right level and with up-to-date data to measure, policymakers would be able to make targeted interventions and measure their cost. This study aims to provide a predictive analytics framework to model, predict and simulate COVID-19 propagation and the socio-economic impact of interventions intended to reduce the spread of the disease such as policy and/or vaccine. It allows policymakers, government representatives and business leaders to make better-informed decisions about the potential effect of various interventions with forward-looking views via scenario planning. We have leveraged a recently launched open-source COVID-19 big data platform and used published research to find potentially relevant variables (features) and leveraged in-depth data quality checks and analytics for feature selection and predictions. An advanced machine learning pipeline has been developed armed with a self-evolving model, deployed on a modern machine learning architecture. It has high accuracy for trend prediction (back-tested with r-squared) and is augmented with interpretability for deeper insights. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.