How we measure accuracy & ensure patient safety
Nefra's nutrient estimation pipeline is validated against reference laboratory analyses using the following protocol:
Clinical validation study is in planning. The targets below represent our acceptance criteria; measured results will be published here once the pilot study is complete.
| Nutrient | MAE Target | Sensitivity | Specificity | Status |
|---|---|---|---|---|
| Potassium (K) | ≤ 30 mg | ≥ 90% | ≥ 85% | Pilot planned |
| Phosphorus (P) | ≤ 25 mg | ≥ 88% | ≥ 85% | Pilot planned |
| Sodium (Na) | ≤ 50 mg | ≥ 90% | ≥ 87% | Pilot planned |
| Protein | ≤ 3 g | ≥ 85% | ≥ 82% | Pilot planned |
| Fluid | ≤ 50 ml | ≥ 85% | ≥ 80% | Pilot planned |
| Calories | ≤ 40 kcal | ≥ 88% | ≥ 85% | Pilot planned |
| Source | Region | Entries |
|---|---|---|
| USDA FoodData Central | United States | ~380,000 |
| McCance & Widdowson's | United Kingdom | ~3,500 |
| IFCT (NIN) | India | ~1,500 |
| Standard Tables of Food (MEXT) | Japan | ~2,500 |
| NutriSurvey DOST-FNRI | Philippines | ~1,600 |
When Nefra's AI confidence falls below 75%, the estimated uncertainty exceeds 15%, or the food is classified as high-risk for CKD patients (e.g., banana, coconut water, dal, miso), the app:
ai_uncertainty_log for post-market surveillanceThis human-in-the-loop system ensures that no critical dietary decision is made on unreliable AI output alone.
Nefra is a decision-support tool providing estimated nutritional data.
It is not a substitute for professional medical advice. Always consult your nephrologist or renal dietitian.