A Formal Specification of a Data Model for Malaria Surveillance in the Developing World
Emmanuel Tuyishimire
TL;DR
The paper addresses the need for digitized, formal malaria surveillance data in developing regions by proposing a Z notation-based data collection architecture that captures malaria heterogeneity through compartments $S$, $P$, $I$, $T$, $R$ and a region-aware status $STATUS$. It presents a comprehensive formal specification of entities (NAME, ADDRESS, IP, USER, DOCTOR, MEDCENTRE, DATACENTRE, NMEDCENTRES) and schemas for updating and querying data, along with a vectorized, per-variant epidemic spread model that uses a Hadamard product to propagate transitions across compartments. Regional data retrieval and determinants retrieval are defined to support province-level analyses and region-specific transmission dynamics, respectively. The work lays groundwork for integrating AI-based diagnosis (e.g., CNNs) and public interfaces for malaria surveillance, aiming to improve data quality, interoperability, and decision support in resource-limited settings.
Abstract
The fourth Industrial Revolution(4IR), together with the COVID-19 pandemic have made a loud call for digitizing diagnosis processes. The world is now convinced that it is imperative to digitize the diagnosis of long standing diseases such as malaria for more efficient treatment and control. It has been seen that malaria control would benefit a lot from digitizing its diagnosis processes such as data gathering. We propose, in this paper, the architecture of a digital data collection system and how it is used to gather data for malaria awareness. The system is formally specified using Z notation, and based on the capability of the system, possible malaria determinants are defined and their retrieving mechanisms are discussed.