Data analytics and knowledge management approach for COVID-19 prediction and control

Area of Science:

• Public Health
• Epidemiology
• Health Informatics

Background:

• Coronavirus Disease (COVID-19) remains a global health threat, necessitating innovative digital solutions for prediction and control.
• Effective data management and real-time surveillance are crucial for combating infectious disease outbreaks.
• The Delhi-National Capital Region (NCR) faced significant challenges in managing the COVID-19 pandemic.

Purpose of the Study:

• To develop and implement a strategic technical solution for COVID-19 surveillance and control in Delhi-NCR.
• To elucidate the Delhi COVID-19 Data Management Framework and the integrated Command and Control Center (iCCC) mechanism.
• To forecast COVID-19 spread using time-series data for informed policy-making.

Main Methods:

• Development of the Delhi COVID-19 Data Management Framework.
• Implementation of an integrated Command and Control Center (iCCC) with administrative, medical, and field operation modules.
• Application of the Auto-Regressive Integrated Moving Average (ARIMA) model for time-series forecasting of COVID-19 spread.

Main Results:

• The iCCC repository provided essential time-series data for analysis.
• ARIMA modeling effectively forecasted logistics requirements, active cases, positive patients, and death rates.
• The generated intelligence enabled real-time policy formulation and implementation by the Delhi government.

Conclusions:

• The integrated digital solution significantly enhanced COVID-19 surveillance and control capabilities in Delhi-NCR.
• The strategic framework and forecasting model contributed to a drastic reduction in COVID-19 cases and fatalities.
• This approach provides a scalable model for managing future public health emergencies.