Scribd
Upload
7 views2 pages

Data Analytics - Activity 1

The document discusses the critical role of data analytics in real-time disease tracking and prevention during the COVID-19 pandemic, highlighting studies that utilized machine learning methods to predict infection trends. Research by Eltoukhy et al. (2020) and Bali (2020) demonstrated improved accuracy in forecasting COVID-19 cases using algorithms like NARX neural networks and support vector machines. The findings emphasize the need for robust digital health infrastructure and ethical data management to enhance public health decision-making and pandemic preparedness.

Uploaded by

Elizabeth Marqueses
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
7 views2 pages

Data Analytics - Activity 1

The document discusses the critical role of data analytics in real-time disease tracking and prevention during the COVID-19 pandemic, highlighting studies that utilized machine learning methods to predict infection trends. Research by Eltoukhy et al. (2020) and Bali (2020) demonstrated improved accuracy in forecasting COVID-19 cases using algorithms like NARX neural networks and support vector machines. The findings emphasize the need for robust digital health infrastructure and ethical data management to enhance public health decision-making and pandemic preparedness.

Uploaded by

Elizabeth Marqueses
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Marqueses, Elizabeth A,

BS Biology

Data Analytics: A Key Tool in Real-Time Disease Tracking and Prevention

The emergence of COVID-19 unleashed an unprecedented global crisis, significantly affecting lives
and economies worldwide. Recognizing its severity. the World Health Organization (WHO) declared it as
a public health emergency of international concern. This concern highlighted the need of real-time disease
monitoring, where data analytics became an essential tool. Data analytics have been used by the
researchers and healthcare sector, where they analyzed the available datasets to forecast outbreaks,
assess containment strategies, and inform policy decision.

In a study of Eltoukhy, Shaban, Chan, and Abdel-AAL (2020), they uses data analytics for predicting
COVID-19 cases in top affected countries. The authors simultaneously consider historical data and the
external factors.by adopting data analytics, which include developing a nonlinear autoregressive
exogenous input (NARX) neural network-based algorithm. The effectiveness and superiority of the
developed algorithm were demonstrated by conducting experiments using data collected for top five
affected countries in each continent. Their results showed an improved accuracy when compared with
the existing methods. Moreover, the experiments were extended to make future prediction of the
affected COVID-19 cases during the period from August 2020 until September 2020.

Similarly, Bali (2020) uses datasets that comprised of weekly confirmed cases and cumulative
confirmed cases recorded over 35 weeks. Then the data distribution was examined using the latest
available COVID-19 weekly case data, and its parameters were determined based on the statistical
distributions. Additionally, a time series prediction model utilizing machine learning was developed to
map the disease curve and forecast the epidemic trend. Various methods were used, such as linear
regression, multi-layer perceptron, random forest, and support vector machines (SVM). Using RMSE, APE,
and MAPE metrics, the performance of these methods was evaluated, by which SVM demonstrated the
most accurate trend prediction. In this, the author’s study predictions suggested that the global pandemic
would reach its peak by the end of January 2021, with total cumulative infections reaching around 80
million. The result of this study was proved to be accurate based on the recent timeline provided by the
Centers for Disease Control and Prevention (2023), where vaccine shortages occured and the reported
death toll from COVID-19 rises.

These findings highlights the importance of data analytics in advancing biological research and
healthcare. By facilitating real-time disease tracking and predictive modeling, data analytics has enhanced
public health decision-making, resource allocation, and outbreak forecasting. The studies by Bali (2020)
and Eltoukhy et al. (2020) showed how machine learning methods, such support vector machines and
neural networks, can precisely forecast infection trends, enabling immediate interventions.

With the advancement of technology, these models can be improved by adding variables like
population density, climate, and vaccination rates, leading to more effective disease prevention and
pandemic preparedness. Nonetheless, with this advancement comes the need for stronger digital health
infrastructure, real-time data sharing, and ethical data management. In the end, epidemiology data
analytics ultimately goes beyond statistics-–it is an essential tool in preserving lives, enhancing medical
care, and reinforcing global preparedness for future health emergencies.

Figure 1. COVID-19 Data Analytics.

Shown in Figure 1 is a Hierarchical Concept Map of COVID-19 Data Analytics, which outlines key
components involved in analyzing COVID-19-related data. At the top, COVID-19 Data Analytics serves as
the central concept, branching into five main areas. Data collection entails obtaining vital information like
demographics, symptoms, and case numbers. Neural networks and SVM are two methods used in
machine learning for pattern recognition and predictive analysis. Regression and trend analysis are the
main tools used in statistical analysis to decipher data patterns. Using data-driven models, predictive
modeling assists in tracking outbreak trends and predicting cases. Lastly, Public Health Decisions support
policy-making and resource allocation, ensuring effective responses to the pandemic. This methodical
approach demonstrates how different analytical techniques support well-informed decision-making.

References:
Ballı, S. (2020). Data Analysis of Covid-19 Pandemic and Short-Term Cumulative Case Forecasting Using
Machine Learning Time Series Models. Chaos, Solitons & Fractals, 110512.
https://doi.org/10.1016/j.chaos.2020.110512

Centers for Disease Control and Prevention. (2023, March 15). COVID-19 Timeline. Centers for Disease
Control and Prevention; CDC. https://www.cdc.gov/museum/timeline/covid19.html

Eltoukhy, A. E. E., Shaban, I. A., Chan, F. T. S., & Abdel-Aal, M. A. M. (2020). Data Analytics for Predicting
COVID-19 Cases in Top Affected Countries: Observations and Recommendations. International
Journal of Environmental Research and Public Health, 17(19), 7080.
https://doi.org/10.3390/ijerph17197080

You might also like