Nutramilo Insulin Score

NIS v1.1.9 — open algorithm for estimating the insulinogenic potential of a meal

Reference implementation of the Nutramilo Insulin Score (NIS) — an open-source algorithm designed to estimate the relative insulinogenic potential of a meal from its nutritional composition. NIS is intended for research, educational use, software development, and exploratory nutritional analysis. It should not be interpreted as a clinically validated predictor of postprandial insulin response.

⚠️ Scientific status

NIS v1.1.9 represents an exploratory methodology. The algorithm is intended for comparative analysis of meals and hypothesis generation rather than diagnostic or therapeutic decision-making.

View on PyPI Citable DOI (Zenodo)DOI Source on GitHub

Why NIS exists

Glycemic Index measures post-prandial glucose but not insulin response. NIS proposes an exploratory approach to estimating a meal's insulinogenic potential from its macronutrient composition — particularly useful for comparative analysis of meals with high protein or dairy content.

Unlike proprietary algorithms, NIS is open-source (Apache 2.0). Any clinician, researcher or developer can audit, cite, and integrate it into their own software free of charge.

The formula

NIS is computed in 4 steps: (1) macronutrient weights yield a raw PIRU (Predicted Insulin Response Unit); (2) source-type aware adjusters for fiber, protein type, fat type; (3) piecewise PIRU → % calibration; (4) clamping to 5–145% range.

PIRU_raw  = 0.69 × protein_g + max(carbs_g - fiber_g, 0)
PIRU_adj  = PIRU_raw × source_factor(protein_type, fat_type)
NIS_%     = piecewise(PIRU_adj)        # piecewise calibration
NIS_%     = clamp(NIS_%, 5, 145)

Scope & limitations

NIS is an exploratory research tool. It is not a clinically validated predictor of postprandial insulin in any individual patient. It is intended to support:

Comparative analysis between meals (hypothesis-generating studies)
Educational applications for patients and students
Software integration into nutrition tracker applications
Exploratory nutritional analysis for researchers

NOT intended for:

✕Clinical diagnosis of metabolic conditions
✕Predicting postprandial insulin in individual patients
✕Therapeutic decisions (including insulin dosing)
✕Replacing medical consultation or laboratory testing

Reproducibility

Install locally, compute one NIS, verify the DOI. All code is Apache 2.0 + mandatory NOTICE citation.

1. Install

pip install nutramilo-nis

2. Compute

from nutramilo_nis import compute_nis, NIS_VERSION

result = compute_nis(
    carbs_g=50, protein_g=20, fat_g=10, fiber_g=5,
    protein_type="whey", fat_type="seed-oil",
)
print(result["nis_percent"], NIS_VERSION)
# 37.4 1.1.9

3. Cite (BibTeX)

@software{nutramilo_nis_v119_2026,
  author       = {Inkov, Ivan and {International Sci Ink Press Ltd EOOD}},
  title        = {Nutramilo Insulin Score (NIS) v1.1.9},
  year         = 2026,
  publisher    = {Zenodo},
  version      = {v1.1.9},
  doi          = {10.5281/zenodo.20571802},
  url          = {https://doi.org/10.5281/zenodo.20571802},
  license      = {Apache-2.0},
}

Version & compatibility

Version	Date	Changes	Math freeze?
v1.1.9	2026-02	Current production (Zenodo DOI release).	✓
v1.1.1+	2025-09	Coefficients frozen (math freeze).	✓
v1.0.0	2025-04	Initial public release.	—

Versions 1.x.y under math freeze guarantee coefficients do not change between minor/patch releases — only documentation/typing/optimisations.

Literature basis

Holt et al. (1997) — An insulin index of foods: the insulin demand…
PMID 9356547
Am J Clin Nutr
Original Food Insulin Index methodology. Source for the insulin-response-per-food concept (n=38 foods).
Bao et al. (2011) — Food insulin index: physiologic basis for predicting…
PMID 21346091
Am J Clin Nutr
Mixed-meal study. Conceptual basis for evaluating composite meals.
Nilsson et al. (2004) — Glycemic index and insulinemic index of…
PMID 15531674
Am J Clin Nutr
Protein-dose and dairy comparisons.
Boirie et al. (1997) — Slow and fast dietary proteins differently…
PMID 9405716
PNAS
Slow vs fast digesting proteins — insulin response kinetics.
Trichopoulou et al. (2003) — Mediterranean diet and survival…
PMID 12826634
NEJM
Contextual framework for index interpretation in Mediterranean diet.

Licence

Apache License 2.0 — commercial and academic use permitted, no warranty. The NOTICE file must be preserved and the DOI 10.5281/zenodo.20571802 cited for scientific use.

Trademarks: NIS™, Nutramilo Insulin Score™, Nutramilo™ — International Sci Ink Press Ltd EOOD, EUIPO. Educational tool — NOT a medical device under MDR Regulation (EU) 2017/745.

← Back to Nutramilo Science Full methodology