XGBoost · SHAP · AI-Powered Clinical Interpretation · PHC CDST

Early-Warning Stroke Risk
Prediction for Nigeria

An explainable AI screening tool for frontline PHC workers managing hypertensive patients. Enter patient details to receive an instant risk assessment with contributing factors.

⚠ This tool is designed for non-diagnostic screening only. All results must be reviewed by a qualified clinician before any clinical decision is made.
📋
Patient Assessment Form
Clinical & Demographic Inputs
Demographics
Blood Pressure
First recorded BP when HTN was diagnosed
Most recent BP reading taken today
Lifestyle
Comorbidities
📊
Risk Assessment Results
XGBoost · Calibrated Probability · SHAP Factors
🏥
Ready to Assess
Complete the patient form on the left and click
Assess Stroke Risk to generate results.
Running XGBoost model...
—
STROKE RISK SCORE
0%THRESHOLD100%
—
Recommended Action
—
SBP Change
—
Pulse Pressure
—
Comorbidity Score
Top Contributing Factors
Feature importance × patient value direction
AI Clinical Interpretation
Loading...
Generating guideline-grounded interpretation...
AHA/ASA · WHO PEN · Nigeria PHC Protocol
0.743
AUC-ROC
97.9×
Imbalance ratio
SMOTE
Resampling
N=10K
Training size
Model score–based risk band. Not a clinical diagnosis.
Threshold: —% | Sensitivity: 5% | Specificity: 99%
Model Card
StrokeRisk AI — Nigeria PHC CDST
0.743
AUC-ROC (test set)
10,092
Training patients
XGBoost
Algorithm + Isotonic Calibration
GPT-4o
AI-Powered Guideline-Grounded Clinical Interpreter
🔒

Model Monitoring Dashboard

Administrator access required. Enter the admin password to view data drift metrics, prediction logs, and model performance monitoring.

Incorrect password. Access denied.

📊 Model Monitoring Dashboard

StrokeRisk AI · Nigeria PHC CDST · Admin View
—
Total Predictions
This session
—
High Risk Flags
—
—
New Patient Assessments
SBP Delta = 0
—
Feature Drift Status
—
Feature Distribution Drift — Session vs Training Reference
Feature Training Mean Session Mean Δ Deviation Drift Status Inputs (N)
Recent Prediction Log (Session)
# Time Age SBP Last SBP Delta Patient Type Risk Score Risk Band
⚠ This dashboard monitors session-level data only. No patient identifiers are stored. All inputs are anonymous aggregates for model performance monitoring purposes. Data drift thresholds: Warning ≥ 15% deviation from training mean. Alert ≥ 30%.
⚠ Non-Diagnostic Screening Tool
StrokeRisk AI is designed for population-level risk screening in primary health care settings and is not intended to replace clinical judgement or serve as a diagnostic instrument. Results must be interpreted by a qualified clinician in the context of full patient history. Quantium Insights LLC bears no clinical liability for decisions made based solely on this tool.

Quantium Insights LLC · Dr. Amobi Andrew Onovo, PhD, MPH · dramobionovo@quantiuminsights.com · www.quantiuminsights.com