Population Health · Evidence · Impact
Anonymised, NDPA-compliant population health signals derived from LifeGate's AI triage and licensed physician review network — built for Government, NGOs, Researchers, and Hospitals.
What This Is
LifeGate's EDIS engine and physician review network generate a continuous stream of validated health signals across Nigeria. This dashboard surfaces those signals — aggregated, de-identified, and structured — as a public good.
Every data point is backed by a licensed, MDCN-verified physician. Not raw AI output. Not self-reports.
All data is anonymised and aggregated under NDPA 2023. No personal or patient-identifiable information is ever exposed.
Signals update continuously from the live LifeGate platform — not periodic batch reports collected weeks after the fact.
Condition signals are mapped to state and LGA level — enabling regional health planning and outbreak geo-fencing.
Dashboard Modules
Six analytics modules — each designed around a specific public health decision-making need.
Month-on-month condition volume — identify seasonal spikes such as malaria peaks and respiratory illness patterns to support pre-emptive procurement of drugs and diagnostic kits.
State-level condition prevalence — informs where to deploy mobile health units, vaccines, and specialist outreach to highest-need regions.
Weekly telemedicine consultation volumes, physician review rates, and digital health adoption by state — justifying universal digital health infrastructure investment across Nigeria.
States with high disease burden but insufficient specialist coverage — identifying conditions chronically under-resourced in specific geographies to guide health infrastructure deployment.
SLA breach rates and physician-to-case ratios by state — reveals healthcare access deserts for targeted workforce and resource deployment.
Anonymised condition burden by age group and sex — identifying which populations carry the highest disease load for precision targeting of community health programs.
Follow-up completion and dropout rates by age, sex, and state — flagging populations with low health-seeking persistence for targeted re-engagement and outreach programs.
Built for institutions
FMOH · NCDC · State Ministries of Health
WHO · MSF · CHAI · Gates Foundation
Universities · Public Health Schools · Think Tanks
Tertiary Hospitals · HMOs · Private Networks
Access-controlled · Institutional only
This dashboard is available to verified institutional stakeholders. Government bodies, accredited research institutions, registered NGOs, and licensed healthcare facilities may apply.
Select access tier
Loading tiers…
Your details
Your access request has been received. We'll review and respond within 2–3 business days. A receipt has been sent to your email.
Save your reference — use the Check Status tab to track approval and retrieve your API key once approved.
Check your application status
Cross-correlating symptom burden with geographic and socioeconomic proxies at state level — quantifying inequalities in disease severity, healthcare access, and physician response time across Nigeria. These metrics directly inform resource allocation and equity policy.
Per-state composite of urgency severity, escalation rate, prescription coverage, and repeat-patient burden — each a validated proxy for underlying socioeconomic health inequality (k-anonymised, min. 3 cases per state).
| # | State | Cases | Severity Index ↑ worse | HIGH/CRIT % | Escalation % | Rx Coverage | AI Confidence | Repeat Pts % | Top Condition |
|---|---|---|---|---|---|---|---|---|---|
| Loading… | |||||||||
Median and p90 physician assignment latency by state — a direct measure of healthcare access inequality. The inequality ratio shows how much slower each state is relative to the national median.
Anonymised, physician-adjudicated health records from a real-world telemedicine platform — bridging patient-reported outcomes and clinically confirmed diagnoses. Rare in Nigeria and across sub-Saharan Africa. Suitable for AI benchmarking, comorbidity research, and health equity studies.
Physician-adjudicated cases and repeat-patient longitudinal records available in the dataset.
Benchmark for evaluating AI diagnostic accuracy in real-world, low-resource clinical settings. Override rate = physician rejected AI output; Approval rate = physician confirmed.
| Confidence Band | Cases | Reviewed | Approved | Override Rate | Approval Rate |
|---|---|---|---|---|---|
| Loading… | |||||
Condition pairs co-occurring in the same patient — population-scale comorbidity signal for research (min. 3 patients per pair, k-anonymised).
Labelled corpus for training and evaluating diagnostic AI: each case carries physician adjudication — full approval (AI accepted as-is), edited approval (physician revised output), or rejection (full AI override). Rare ground-truth signal for AI benchmarking in Nigerian clinical contexts.
| Urgency | Reviewed | Approved | Rejected | Rejection Rate |
|---|---|---|---|---|
| Loading… | ||||
Empirical data on when EDIS triggers physician handoff: escalation rates by urgency tier, AI confidence at the moment of escalation vs non-escalation, and top conditions requiring clinical review. Key open variable for health AI deployment research.
Aggregate audit trail metrics and Nigeria Data Protection Act (NDPA) compliance indicators — supporting regulatory reporting to NDPC, WHO, and Africa CDC. All figures are anonymised platform-level statistics.
Data subject counts are platform-level aggregates. No personally identifiable information is exposed through this dashboard.