Data-Driven Deep-Learning Algorithm for Asymptomatic COVID-19 Model with Varying Mitigation Measures and Transmission
K D Olumoyin1, A Q M Khaliq1, K M Furati2
1Department of Mathematical Sciences, Middle Tennessee State University, Murfreesboro, TN 37132, USA.
Epidemiologia (Basel, Switzerland)
|November 23, 2022
Summary
This study introduces an AI algorithm to track time-varying COVID-19 transmission rates, accounting for asymptomatic cases and mitigation strategies. It demonstrates how interventions like vaccination and social distancing impact infection dynamics.
Area of Science:
- Epidemiology
- Artificial Intelligence
- Infectious Disease Modeling
Background:
- Traditional epidemiological models struggle with time-varying parameters during pandemics.
- Infectiousness changes over time due to mitigation measures and disease dynamics.
- Accurate modeling requires accounting for asymptomatic and unreported infections.
Purpose of the Study:
- To develop an Epidemiology-Informed Neural Network (EINNs) algorithm to learn time-varying transmission rates for COVID-19.
- To model the impact of pharmaceutical and non-pharmaceutical interventions on disease transmission.
- To estimate the proportion of asymptomatic infectives and their role in spread.
Main Methods:
- Utilized an AI-driven approach (EINNs) to analyze COVID-19 data.
- Incorporated cumulative and daily symptomatic case data for model training.
- Simulated the effects of interventions like early detection, contact tracing, social distancing, and vaccination.
Main Results:
- The EINNs algorithm successfully learned time-varying transmission rates under various mitigation scenarios.
- Simulations demonstrated the significant impact of non-pharmaceutical interventions on the basic reproduction number.
- Vaccination effectiveness in reducing COVID-19 transmission was quantitatively demonstrated.
- The algorithm accurately estimated the proportion of asymptomatic infectives.
Conclusions:
- Epidemiology-Informed Neural Networks provide a robust framework for modeling infectious diseases with time-varying parameters.
- The study highlights the critical role of asymptomatic transmission and the effectiveness of layered mitigation strategies.
- The developed algorithm offers a data-driven tool for pandemic response and policy evaluation.
Related Concept Videos
01:18Steps in Outbreak Investigation
170
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
170
01:25Statistical Methods for Analyzing Epidemiological Data
480
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
480