A modelling approach for correcting reporting delays in disease surveillance data

Area of Science:

• Epidemiology
• Biostatistics
• Public Health

Background:

• Real-time epidemic tracking is hindered by reporting delays from various sources.
• Timely data correction is essential for effective public health decision-making and warnings.

Purpose of the Study:

• To propose a flexible Bayesian hierarchical modeling approach for correcting epidemic reporting delays.
• To quantify the uncertainty associated with these corrections.
• To demonstrate the model's efficiency in real-time data analysis.

Main Methods:

• Bayesian hierarchical modeling.
• Integrated Nested Laplace Approximation (INLA) for fast computation.
• Application to real-world infectious disease data.

Main Results:

• The proposed model effectively corrects reporting delays in epidemic data.
• The method provides accurate quantification of uncertainty in corrected data.
• Fast implementation allows for timely analysis crucial for public health.

Conclusions:

• Bayesian hierarchical modeling with INLA offers a robust and efficient solution for addressing reporting delays in epidemic surveillance.
• This approach enhances the reliability of real-time epidemiological data for informed decision-making.
• The model's applicability is demonstrated on dengue and severe acute respiratory infection datasets.