Live Outbreak Surveillance · Nigeria

Lassa Fever Outbreak Intelligence

ML-powered outbreak prediction for all 37 Nigerian states. Combines NCDC epidemiological surveillance data, ERA5 climate reanalysis, and antiviral drug discovery — all updated weekly.

▶ Run Lassa Analysis ✚ Clinical Copilot ⇓ Outbreak Forecast ⇪ One-Page Summary
0.9994
Test AUROC (2024–25 holdout)
37
Nigerian states tracked
753
Epi-weeks of training data
High-risk states this week
2012
Training data from
Outbreak Forecast — Next 4 Weeks
Loading...
Fetching forecast
Lassa Virus Target Proteins
Viral Pathogen Mode
GPC
Glycoprotein Complex
Viral entry — primary vaccine and antibody target. Mediates fusion with host cell membrane.
NP
Nucleoprotein
RNA synthesis and immune evasion. Suppresses host innate immune response via IFN antagonism.
L
RNA-dependent RNA Polymerase
Viral replication. Primary target for antivirals: favipiravir, ribavirin, and molnupiravir all inhibit L activity.
Z
Matrix Protein (RING)
Viral budding. RING-domain zinc-finger protein; drives virion assembly and release from host cells.
Antiviral Drug Pipeline
Loading...
Fetching pipeline
Weekly PubMed Surveillance
Automated · Weekly
Fetching alert config
Prediction Model
XGBoost · Temporal CV

Binary classification: will a state report >5 confirmed Lassa cases in the next 4 weeks? Trained with strict temporal cross-validation — no data leakage between train/validate/test splits.

0.9994
Test AUROC
1.000
Test Recall
0.910
Test Precision
0.953
Test F1
0
Missed outbreaks (FN)
27,417
Training rows
19
Features
2012–2025
Data coverage

Top features: 8-week rolling case mean (49.6%), 1-week lag cases (26.1%), 4-week rolling mean (13.6%), dry season timing (3.5% combined). Weather variables (rainfall, humidity, temperature) contribute <3% — recent case history dominates, consistent with Lassa's focal rodent-reservoir transmission ecology.

Limitations: Confirmed-case counts under-report true incidence — Lassa is difficult to diagnose clinically and PCR access is uneven across states — so both the prediction target and the dominant case-history features inherit surveillance bias. Ideal predictors such as rodent-reservoir ecology are not yet available at scale, so rainfall serves only as a partial environmental surrogate. Case data 2012–2015 are seed estimates (not direct NCDC surveillance counts). Weather is from ERA5 reanalysis at state capital coordinates — intra-state variation not captured. Model should be treated as a screening tool, not a replacement for NCDC field surveillance.

Run a Lassa Virus Analysis

Enter LASV protein targets into GaiaLab's AI analysis pipeline. The viral pathogen mode routes GPC, NP, L, and Z through a Lassa-specific drug repurposing engine with known antiviral candidates pre-loaded.

GPC NP L Z
▶ Analyze Lassa Virus Targets