Critical Review of Data Analytics Techniques used in the Expanded Program on Immunization (EPI)

Area of Science:

• Public Health
• Data Science
• Machine Learning

Background:

• Immunization is crucial for reducing child mortality but faces low coverage in developing nations.
• Lack of immunization data analysis hinders effective public health interventions.
• Free accessibility of vaccines does not guarantee high coverage rates.

Purpose of the Study:

• Critically review machine learning (ML) data analytics for immunization.
• Identify gaps in current ML applications for immunization data.
• Explore potential for ML to improve vaccination coverage.

Main Methods:

• Literature review of ML-based data analytics techniques in immunization.
• Analysis of existing approaches considering Expanded Program on Immunization (EPI) complexities.
• Assessment of data repository limitations in developing countries.

Main Results:

• Current ML approaches often overlook EPI complexities like cold chain and data quality.
• Lack of centralized data repositories impedes comprehensive immunization data analytics.
• Existing data analytics techniques are not fully exploiting the potential of immunization data.

Conclusions:

• Integrating ML and AI with non-centralized immunization data can enhance vaccination coverage.
• Predictive analytics can forecast future immunization trends and patterns.
• Addressing data complexity and centralization is key to leveraging ML for improved immunization programs.