LassaAI — One-Page Summary

Model Performance (National model, 2024 out-of-time hold-out)

0.880

Model AUROC

0.849

Naive baseline AUROC

0.93

Precision

0.85

F1 Score

±1%

vs NCDC published

Target: whether the next 4 weeks carry above-median confirmed burden. Trained on real, cross-validated NCDC weekly data (train ≤2023, test 2024). The model beats a naive persistence baseline by only ~0.03 AUROC; the result does not establish added skill beyond explicit seasonality. All model-performance metrics are retrospective. Under protocol v1.1, the 2026–27 prospective study must beat the strongest pre-specified persistence-or-seasonal comparator with dependence-aware uncertainty; the study was frozen on 2026-09-23 and no scored season forecasts have been logged yet.

2026 surveillance status. Latest directly verified NCDC checkpoint, cumulative through Epi Week 40: 8,414 suspected · 1,138 confirmed · 6 probable · 268 confirmed-case deaths. Source: official NCDC Week 40 sitrep. The committed weekly series used by the prospective study runs through Epi Week 38. These 2026 surveillance figures are separate from the 2020–2025 retrospective model-development dataset. Newer weeks are added only after direct primary-document verification.

What LassaAI Does

National Early-Warning Model

Predicts elevated (above-median) national transmission over the next 4 weeks
Trained on real NCDC weekly data, 2020–2025 (cross-validated ±~1% vs published totals)
2024 hold-out AUROC 0.88 vs 0.85 persistence baseline — retrospective only; not evidence of added skill beyond seasonality
Per-state view is illustrative pending real per-state weekly data (future work)
Live dashboard: gailabai.com/lassa

Research-use risk-scoring prototype

Literature-informed probability score over clinical and epidemiological inputs for research/method evaluation only
Symptom weights are informed by published Lassa fever literature; the prototype has not been prospectively validated for clinical use
Freely accessible: gailabai.com/lassa-copilot
Always recommends RT-PCR confirmation

Dataset

Item	Value
Time period	2020–2025 (national weekly)
Observations	313 epidemiological weeks
Confirmed cases (2020–25)	6,456
Case source	NCDC Weekly Epidemiological Reports (cross-validated)
Per-state / clinical	SORMAS 2018–2021 (CC-BY, DOI 10.5281/zenodo.7309567)
Elevated-week rate	56% (balanced, non-degenerate target)
Latest verified 2026 checkpoint	Epi Week 40: 8,414 suspected; 1,138 confirmed; 6 probable; 268 confirmed-case deaths
Preprint (open access)	Zenodo, CC-BY · DOI 10.5281/zenodo.21122486

Top Feature Importance

Feature importance is loading from the frozen v1.1 model's importance file.

The national model uses no meteorological covariates; national-average weather is not epidemiologically meaningful.

Proposed Research Partnership

We are preparing a NIH Fogarty International Center R21 application (up to $275,000 / 2 years) with two aims:

Aim 1 (Year 1): Prospective validation with NCDC — 12-month blinded prediction logging vs. confirmed case outcomes
Aim 2 (Year 2): Clinical validation of the Copilot at a Nigerian Lassa fever treatment centre (target: ISTH Irrua or FMC Owo)

Application deadline: October 16, 2026 (LOI due September 16, 2026)

Most-Affected States (endemic ranking)

From the individual-level SORMAS 2018–2021 data, the endemic states rank Edo > Ondo > Ebonyi > Bauchi, consistent with published NCDC reporting. Edo (ISTH Irrua) and Ondo (FMC Owo / ILFRC) host the principal treatment and reference centres.

Validated per-state weekly case counts are not yet available — NCDC publishes them as image tables not amenable to extraction. Obtaining structured per-state data (proposed in partnership with NCDC) to build and prospectively validate a per-state model is the immediate next step. No per-state cumulative totals are shown here because none have been validated.

Key Limitations (Disclosed)

(1) Retrospective only — prospective validation not yet complete. (2) Confirmed cases only — true Lassa incidence substantially higher. (3) State-capital weather — rural microclimates may differ. (4) Reporting variability — testing capacity varies by state and year. (5) Risk-scoring prototype — not prospectively validated for diagnosis, triage, treatment, or clinical decision-making.

Research use only. LassaAI is not a medical device and the risk-scoring prototype is not validated for diagnosis, triage, treatment, or clinical decision-making. Qualified healthcare professionals should follow approved local protocols and laboratory confirmation.