.png)
When we founded Abbadh Labs, our aim was simple and urgent: turn the enormous, scattered, and mostly under-used data across our institutions into clear, predictive, and actionable insights that people and organisations in Nigeria can actually rely on.
Too often the data exists only as isolated records — paper notes, siloed hospital files, mismatched spreadsheets — and that fragmentation means decisions are slow, incomplete, and sometimes dangerous.
The World Health Organization's country profile and related health system reviews underline persistent gaps in how health data is captured and used for planning and prevention (World Health Organization).
Electronic medical records have been introduced in parts of the system, and yet in many facilities EMR remains little more than a digital ledger — a replacement for paper rather than a tool for continuous, longitudinal care.
Studies of EMR adoption in Nigeria document implementation challenges and missed opportunities to use clinical data for prediction, continuity of care, and system-level learning (Semantic Scholar).
Longitudinal analytics and cohort-based prediction are proven methods to anticipate and prevent such outcomes — when data is linked and analysed properly (SAGE Journals).
The consequences of poor data stewardship extend well beyond clinical care.
Nigeria's public and private sectors lose huge sums to duplication, inefficiency, and fraud when personnel and records aren't reliably maintained. Large-scale payroll and pension audits repeatedly find "ghost workers" and stale records — showing both the scale of the problem and the savings possible when systems work (Premium Times Nigeria).
These weaknesses also ripple into research and education: students and researchers lack consistent, accessible datasets and reliable institutional knowledge, slowing scholarship and weakening the evidence base that should guide policy (SpringerLink).
Hospitals collect patient records. Universities collect academic data. Government agencies collect biometric and workforce data. Yet these systems operate in isolation, rarely speaking to one another, rarely producing insight, and almost never supporting long-term prediction. What should be living intelligence has become static storage.
Our approach is to build infrastructure that connects these fragments into continuous systems of understanding. We began in academia because research is where structure meets evidence. Through SABABAT, we created an intelligent research engine that automates literature synthesis, statistical workflows, data cleaning, and interpretation — giving students and early researchers access to tools that were previously fragmented across multiple platforms.
But this was only the starting point.
Our broader vision extends into healthcare and public systems. We are building an industry-grade analytical layer designed to integrate with clinical records, laboratory results, and longitudinal patient histories — enabling hospitals to move beyond record keeping into predictive care.
This is where applied machine learning and large language models become transformational — not as chatbots, but as analytical companions layered on structured data, capable of summarising trajectories, highlighting anomalies, and forecasting outcomes from years of accumulated records.
The same philosophy applies to governance. Today, civil servants are repeatedly re-verified to eliminate "ghost workers". Families must manually report deaths. Employees re-register year after year. These processes persist because systems are not connected.
A properly designed national data infrastructure would allow lifecycle events — employment, illness, death — to propagate automatically across institutions. Payroll systems would update in real time. Pension systems would reconcile instantly. Fraud would become structurally difficult rather than administratively hunted.
These are not futuristic ideas. They are standard capabilities in data-mature economies. Yet in Nigeria, even individuals living with chronic conditions like sickle cell disease often cannot produce a complete lifelong medical record when seeking care abroad — doctors reconstruct histories through handwritten reports because there is no persistent, interoperable patient data backbone.
Our roadmap moves deliberately from academic intelligence to clinical analytics, and onward to national-scale decision infrastructure. SABABAT represents our academic foundation. Our healthcare platform will focus on clinical analytics and integration. Our future systems will support workforce intelligence, digital identity continuity, and predictive public services.
We are not chasing trends. We are laying foundations.
This work is deeply personal — as a technologist, as a Nigerian, and as someone who has lived within fragmented healthcare systems. It is driven by a belief that data, when treated as infrastructure rather than storage, can save lives, improve governance, and unlock national development.
Abbadh Labs is here to build that future.