COVID-19 Prediction Models and Unexploited Data
- PDF / 268,823 Bytes
- 4 Pages / 595.276 x 790.866 pts Page_size
- 99 Downloads / 173 Views
EDUCATION & TRAINING
COVID-19 Prediction Models and Unexploited Data K. C. Santosh 1 Received: 23 June 2020 / Accepted: 11 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract For COVID-19, predictive modeling, in the literature, uses broadly SEIR/SIR, agent-based, curve-fitting techniques/models. Besides, machine-learning models that are built on statistical tools/techniques are widely used. Predictions aim at making states and citizens aware of possible threats/consequences. However, for COVID-19 outbreak, state-of-the-art prediction models are failed to exploit crucial and unprecedented uncertainties/factors, such as a) hospital settings/capacity; b) test capacity/rate (on a daily basis); c) demographics; d) population density; e) vulnerable people; and f) income versus commodities (poverty). Depending on what factors are employed/considered in their models, predictions can be short-term and long-term. In this paper, we discuss how such continuous and unprecedented factors lead us to design complex models, rather than just relying on stochastic and/or discrete ones that are driven by randomly generated parameters. Further, it is a time to employ data-driven mathematically proved models that have the luxury to dynamically and automatically tune parameters over time. Keywords COVID-19 . Prediction model . Data visualization . And machine learning
Background Since December 2019, the novel Coronavirus (identified in Wuhan, China) threats globally as its spreading rate is found to be exponential. The following statement from World Health Organization (WHO) situation status report provides an idea of how sensitive the issue is: Based on world health statistics, the COVI-19 pandemic is causing significant loss of life, disrupting livelihoods, and threatening the recent advances in heath and progress towards global sustainable development goals (source: report no. 114). Besides, they reported a clear guidance on considerations on adjusting public health and social measures. In this situation, prediction tools can help project different scenarios, such as a) number of possible confirmed (new) cases; b) number of possible hospitalized cases; and c) number of possible death This article is part of the topical collection on Education & Training * K. C. Santosh [email protected] 1
Department of Computer Science, University of South Dakota, 414 E Clark St, Vermillion, SD 57069, USA
cases (just to name a few). As a consequence, prediction tools are useful for several different purposes. As an example, number of possible hospitalized cases based on the severity level can help determine the need of numbers of ventilators and other sophisticated medical equipment. Further, states need to shape their health system responses in accordance with the need. For this, prediction models require to have important properties like epidemiological characteristics (of the diseases), such as incubation period, transmissibility, asympotomaticity, and severity. Other features, such as social distan
Data Loading...
