The INSPIRE network: Building a data science platform

Evidence-based health policy needs FAIR data from multiple sources, with high quality data management and analysis by African data scientists.

The Big Data ecosystem provides the strength to integrate data from multiple sources and utilise advanced artificial intelligence for the analysis.

The INSPIRE network has used an OMOP database to share open-access longitudinal population-based health data, and the environment to use these data effectively in low-and-middle income countries (LMIC).

This proposal outlines the areas to achieve the aim of establishing the infrastructure to systematically integrate and share public health data.

Firstly the proposal develops the Secretariat to link to stakeholder, including national data offices, data providers and international data scientists.

Secondly the proposal will develop several technical components, to develop standardized vocabularies, and the mechanism (ETL) for bringing data into the OMOP database, and making data available for analysts to use. Thirdly is developing the human resources needed by training new data scientists, building a community of practice.

This proposal builds on initial work by INDEPTH and ALPHA network.

It learns from the SAPRIN experience in South Africa, and will feed into the NIH Data Science Initiatives in Africa, and the proposed Wellcome Trust African Population Cohorts Consortium.