The emergence of COVID-19 as a global pandemic has posed a critical health threat to numerous low-and-middle-income countries (LMICs) and the well-being of their populations. Timely and precise data are imperative for adapting health policies and strategies to effectively combat this threat. However, obtaining such data is a challenge, particularly under lockdown restrictions, necessitating innovative approaches to data collection and aggregation.

Leveraging Artificial Intelligence (AI) and Data Science (DS) innovations is paramount to acquire accurate, real-time data from diverse sources in LMICs. Additionally, addressing methodological gaps in data integration and enhancing information and research capacity is essential for informed decision-making and effective public health policy formulation. Integrated Disease Surveillance and Response (IDSR) is a pivotal strategy for the early detection and efficient management of infectious disease outbreaks. It entails the systematic collection, analysis, and dissemination of surveillance data from diverse sources. Endorsed by the World Health Organization (WHO) and the Centers for Disease Control and Prevention (CDC), IDSR is globally utilized to proactively prevent, detect, and address public health threats. In Malawi, Kenya and Uganda, IDSR program is implemented by the Ministry of Health.

The data collected can include information on cases and deaths, risk factors, and transmission patterns, as well as information on public health measures such as testing, contact tracing, and quarantine. The IDSR Case Based Reporting Form may vary depending on the specific needs and resources of each country. The Implementation Network for Sharing Population Information from Research Entities (INSPIRE) is a global initiative aimed at improving public health by facilitating the sharing of population-level health data among researchers and public health authorities. INSPIRE has build a data hub for standardizing and harmonizing IDSR COVID-19 data and implemented the Observational Medical Outcomes Partnership (OMOP) using a Common Data Model (CDM).

OMOP CDM facilitates comprehensive analysis across multiple datasets and support sharing of FAIR (Findable, Accessible, Interoperable, Reusable) data which will be used for evidence-informed policy decision making. (2022)