Intelligent Surveillance of World Health Organization (WHO) Integrated Disease Surveillance and Response (IDSR) Data in Cameroon Using Multivariate Cross-Correlation

TL;DR

This paper introduces a multivariate cross-correlation approach to analyze infectious disease surveillance data in Cameroon, aiming to identify correlated districts and improve outbreak detection through advanced analytics.

Contribution

It develops a novel multivariate time series cross-correlation method combined with anomaly detection to enhance infectious disease pattern analysis in developing countries.

Findings

Highly correlated districts identified for specific diseases.

Alignment of correlation patterns with outbreak alarms.

Potential for integrated analytics to improve outbreak response.

Abstract

As developing countries continue to face challenges associated with infectious diseases, the need to improve infrastructure to systematically collect data which can be used to understand their outbreak patterns becomes more critical. The World Health Organization (WHO) Integrated Disease Surveillance and Response (IDSR) strategy seeks to drive the systematic collection of surveillance data to strengthen district-level reporting and to translate them into public health actions. Since the analysis of this surveillance data at the central levels of government in many developing nations has traditionally not included advanced analytics, there are opportunities for the development and exploration of computational approaches that can provide proactive insights and improve general health outcomes of infectious disease outbreaks. We propose and demonstrate a multivariate time series cross-correlation analysis as a foundational step towards gaining insight on infectious disease patterns via the pairwise computation of weighted cross-correlation scores for a specified disease across different health districts using surveillance data from Cameroon. Following the computation of weighted cross-correlation scores, we apply an anomaly detection algorithm to assess how outbreak alarm patterns align in highly correlated health districts. We demonstrate how multivariate cross-correlation analysis of weekly surveillance data can provide insight into infectious disease incidence patterns in Cameroon by identifying highly correlated health districts for a given disease. We further demonstrate scenarios in which identification of highly correlated districts aligns with alarms flagged using a standard anomaly detection algorithm, hinting at the potential of end to end solutions combining anomaly detection algorithms for flagging alarms in combination with multivariate cross-correlation analysis.