DEMO MODE — Pre-computed ResNet-50 inference results. No live backend.
← Back to MediSecure AI
Critical safety notice
⚠ THIS AI SYSTEM IS NOT A CERTIFIED MEDICAL DEVICE

MediSecure AI (ResNet-50 + Federated DP-SGD, v4.0) has not received clearance from NAFDAC, the FDA, CE, or any equivalent regulatory body. All outputs are decision support tools only. Clinical verification required.

Legal · Medical Disclaimer

Medical Disclaimer

Last updated:

1. Not a medical device

The MediSecure AI platform, its models, and any outputs produced are for research and educational purposes only. They have not been reviewed or approved by the National Agency for Food and Drug Administration and Control (NAFDAC), the Federal Ministry of Health, the United States Food and Drug Administration (FDA), the European CE marking system, or any other regulatory body.

Use of the system for clinical decision-making without independent prospective validation is strictly prohibited by these terms.

2. No clinical advice

Information produced by this platform is not a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of a qualified, licensed healthcare provider with any questions you may have regarding a medical condition.

3. Emergency

If you think you may have a medical emergency, call your doctor, go to the emergency department, or call your local emergency number immediately. MediSecure AI does not provide emergency medical services.

Nigeria emergency lines: 112 (national), 767 (Lagos), 0803 200 3913 (Abuja).

4. Model performance

The published AUC-ROC (0.947) and F1 (0.891) figures are measured on a held-out validation set within the Kermany et al. (2018) research dataset. Real-world performance on novel hospital populations, demographics, and imaging equipment may differ materially.

5. Privacy guarantees

While differential privacy provides formal mathematical guarantees against re-identification (see our Privacy Policy), no system is perfectly secure. Use the platform with appropriate clinical and operational care.

6. Data source

The model was trained on the publicly available pediatric chest X-ray dataset of Kermany et al. (2018). No real Nigerian patient data was collected for this research artefact. Any future deployment requires institutional ethics review and patient consent consistent with the Nigeria Data Protection Act 2023.

Academic attribution
Anyoha, E.C. (2026, August). Design and Implementation of a Secure AI-Driven Medical Diagnosis System Using Privacy-Preserving Machine Learning. Final Year Project, CSC 492. Department of Computer Science, Faculty of Natural Sciences, Caritas University, Amorji-Nike, Enugu, Nigeria. Supervisor: Dr. Ugo Nwankwo. HOD: Prof. Arinze Nwaeze.