African Traditional Medicine (ATM) is widely used in Africa. According to the World Health Organization. African Traditional Medicine plays a crucial role in Sub-Saharan Africa as the first line health system for ca. 80% of the population, thanks to its accessibility, affordability and embeddedness in local tradition.
Gossa Lô, Victor de Boer and Stefan Schlobach investigated how to use Semantic Web technology to formalize data from African traditional medicine, and link it with data on conventional medicine (CM). This resulted in the first knowledge graph for “Linked African Traditional Medicine “. This was presented at the SWAT4LS Conference (Semantic Web Applications and Tools for Healthcare and Life Sciences 2017) in Rome (Italy) on December 6th 2017 by Gossa Lô. The knowledge graph is illustrated with some interesting SPARQL queries and insightful results.
Traditional medicine comprises a heterogeneous set of diagnostic- and therapeutic practices to prevent, diagnose and treat physical and mental illnesses. Despite the fact that knowledge on African traditional medicine is often not scientically validated, integrating it into formal health care systems can result in a deeper understanding of pathology and medical knowledge. Since ATM is orally passed on from generation to generation, there is a risk that this (indigenous) knowledge — which is not commonly stored and linked to other knowledge resources — will soon be lost.
Therefore, bridging the gap between African traditional and conventional medicine through formalization and integration, not only leads to better practice and more safety, but also preserves this valuable knowledge for future generations.
The data for this research were kindly provided by Djibril Ba and Geneviève Baumann from the Hospital for Traditional Medicine Keur Massar in Dakar, Senegal. This hospital has a strong focus of phytotherapy (treatment with medicinal plants) along ATM traditions, and produces about 1000 products and recipes from their own botanical garden.
The research paper can be downloaded as [PDF].