Downloads · 30 days
0
Maheentouqeer1/glycocare-glucose-regression
glycocare-glucose-regression is a machine learning model from Maheentouqeer1. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
0
Access
Public
Updated Nov 8, 2025
Repo size
5.5 MB
Likes
0
Public
Click a slice to open those files.
.pkl5.5 MB · 99%
From the Hugging Face model README
🩺 GlycoCare+ Glucose Regression Model
Author: Maheen Touqeer
Model ID: Maheentouqeer1/glycocare-glucose-regression
Version: 1.0
This model is part of GlycoCare+, a multi-disease AI-powered nutrition assistant for diabetes, blood pressure, and heart health management. It predicts postprandial (after-meal) glucose change (Δ mg/dL) using food-level and user-level features such as portion size, nutritional composition, glycemic index (GI), and personal health parameters.
Model type: Random Forest Regressor
Framework: scikit-learn
Input features:
portion_grams – from portion estimator (YOLO + MiDaS)pre_meal_glucoseage, weight_kg, diabetes_type, medication_flag, activity_level, time_of_daymaster_food_items.csv:
cal_per_100g, carbs_g_per_100g, protein_g_per_100g, fat_g_per_100g, gi, density_g_per_mlOutput:
postprandial_glucose_delta – predicted change in glucose level (mg/dL)
Training dataset: meal_training_data.csv (synthetic meal-level data generated using master food metadata)
Reference dataset: master_food_items.csv (61 Pakistani dishes with nutrition, GI, density, and disease labels)
Samples: 250 meals
Performance:
Goal: Estimate glucose change after a meal with clinically meaningful precision (±5–6 mg/dL).
| File | Description |
|---|---|
glucose_regression_model.pkl | Trained RandomForest regression model |
meal_training_data.csv | Training dataset (synthetic) |
master_food_items.csv | Master nutrition + disease metadata |
glucose_predictor.py | Loader and inference script |
from huggingface_hub import hf_hub_download
import joblib, pandas as pd
# Load model
model_path = hf_hub_download(repo_id="Maheentouqeer1/glycocare-glucose-regression", filename="glucose_regression_model.pkl")
model = joblib.load(model_path)
# Predict glucose change
sample = {
"portion_grams": 300,
"pre_meal_glucose": 110,
"age": 35,
"weight_kg": 70,
"diabetes_type": 2,
"medication_flag": 1,
"activity_level": "moderate",
"time_of_day": "lunch",
"cal_per_100g": 160,
"carbs_g_per_100g": 28,
"protein_g_per_100g": 12,
"fat_g_per_100g": 5,
"gi": 65,
"density_g_per_ml": 0.96
}
prediction = model.predict(pd.DataFrame([sample]))
print("Predicted glucose delta:", round(prediction[0], 2), "mg/dL")
Maheen Touqeer Creator of GlycoCare+ 🔗 huggingface.co/Maheentouqeer1