You're pledging to donate if the project hits its minimum goal and gets approved. If not, your funds will be returned.
This project investigates why populations in low- and middle-income countries are often missing from the health datasets that increasingly support AI systems, biosurveillance platforms, and epidemiological forecasting models. Through an 8–12 week field pilot in healthcare facilities in Kinshasa, Democratic Republic of the Congo, we will map clinical data workflows and identify where routine clinical information becomes lost, unstructured, or invisible before it can enter AI-relevant data ecosystems.
Beyond documenting the problem, the project's primary goal is to implement and evaluate a lightweight structured data capture solution designed to fit within existing clinical workflows. By testing a practical intervention in real healthcare settings, we aim to determine the minimum infrastructure required for routine clinical activity to become AI-ready and biosurveillance-ready data.
The project will generate empirical evidence on both the causes of data exclusion and the effectiveness of low-cost approaches to improving representation. Expected outputs include workflow maps, documentation of data invisibility points, a reusable structured data capture template, an anonymized pilot dataset, and operational recommendations for strengthening participation of underrepresented populations in AI-enabled health intelligence systems.
This project investigates why populations in low- and middle-income countries (LMICs) are often absent from the health datasets used by AI systems, biosurveillance platforms, and epidemiological forecasting models. The goal is to identify where routine clinical information becomes lost, inaccessible, or unusable before it can contribute to AI-relevant data ecosystems.
To achieve this, we will conduct an 8–12 week field pilot in healthcare facilities in Kinshasa, Democratic Republic of the Congo. The project will map clinical data workflows, identify points of data loss and invisibility, and test a lightweight structured data capture workflow designed to fit existing clinical practices. The pilot will generate evidence on how data exclusion occurs in practice and evaluate practical interventions that may improve representation in future health datasets.
The requested $10,000 will support field implementation of the pilot project. Funding will be allocated to:
Field research and clinical workflow mapping ($3,000)
Development and deployment of structured data capture tools ($2,500)
Healthcare worker training and implementation support ($1,500)
Data validation and analysis ($1,000)
Stakeholder engagement and partnership development ($1,000)
Reporting, dissemination, and contingency costs ($1,000)
These activities will enable data collection across participating facilities, pilot deployment, evaluation of outcomes, and dissemination of findings.
I serve as the principal investigator and lead all aspects of the project, including research design, stakeholder engagement, implementation planning, and evaluation.
I am an alumnus of the London School of Hygiene & Tropical Medicine, with training in public health and health economics. My professional experience includes data management, data quality assurance, predictive analytics, health economic evaluation, and development of decision-support tools for healthcare stakeholders.
I have worked as a data analyst on international development projects, including contributions to the United Nations Industrial Development Organization (UNIDO) Annual Report for Madagascar. My technical background includes data governance, data integrity frameworks, large-scale dataset management, predictive modeling, cost-effectiveness analysis, dashboard development, and design of monitoring systems for healthcare and laboratory environments.
Over the past 4 months, I have independently developed the full research and implementation framework for this project, including the pilot protocol, workflow mapping tools, interview guides, ethics and governance framework, data quality assessment methodology, reporting templates, and a synthetic validation dataset. An overview of the work is available and can be seen on GitHub : https://github.com/Beeotics/Health-Data-Pilot.
Preliminary stakeholder engagement has been completed during project development. Discussions were conducted with healthcare professionals and facility leadership in Kinshasa, and multiple facilities have expressed interest in participating in the pilot subject to implementation planning and required approvals.
The project builds directly on my experience in health data quality, healthcare analytics, and the practical challenges of transforming routine clinical information into structured, decision-ready data systems.
The most likely risks are operational rather than technical. Potential challenges include limited participation from healthcare facilities, competing demands on healthcare workers' time, difficulties maintaining adoption of structured data capture workflows, or delays in obtaining institutional approvals.
If the project fails, the primary consequence would be insufficient evidence to validate the proposed intervention or draw robust conclusions about the mechanisms of data invisibility.
However, even a partially successful implementation would likely generate useful insights into workflow constraints, data quality challenges, and barriers to participation in AI-relevant health data systems. The project does not depend on achieving large-scale deployment to produce valuable findings.
To date, the project has not received external funding. Development of the research framework, pilot protocol, stakeholder engagement activities, and implementation planning has been conducted through the principal investigator's independent efforts and unpaid work.
The requested grant would represent the first external funding used to move the project from design and validation into field implementation.