Predicting Postprandial Glycemic Response from Meal Images, Clinical Variables, and Gut Microbiome Information

Varvara Kondratyeva; Kamilia Zaripova; Nassir Navab; Azade Farshad

cs.AISep 21, 2026

Predicting Postprandial Glycemic Response from Meal Images, Clinical Variables, and Gut Microbiome Information

Authors: Varvara Kondratyeva, Kamilia Zaripova, Nassir Navab, Azade Farshad

Organizations: Technical University of Munich, Munich, Germany · University Hospital Augsburg, Augsburg, Germany · Munich Center for Machine Learning (MCML), Munich, Germany · Aalto University, Espoo, Finland

Abstract

Predicting postprandial glycemic response (PPGR) is fundamental to personalized nutrition and type 2 diabetes management, yet existing approaches typically rely on manually reported dietary intake, limiting their scalability in free-living settings. We propose a multimodal framework that replaces manual dietary logging with image-derived macronutrient estimates and integrates them with clinical variables and gut microbiome information for personalized PPGR prediction. The framework jointly performs image-based macronutrient estimation and glucose prediction, while an attention-based prediction module models interactions between dietary and host-specific information. We evaluate the proposed approach on a real-world dataset comprising meal images, continuous glucose monitoring, clinical variables, and gut microbiome profiles. The proposed model outperforms existing PPGR baselines using image-derived nutritional inputs and approaches the performance of methods that rely on manually reported macronutrients despite using automatically estimated nutritional information. These results demonstrate that combining image-derived nutrition with complementary clinical and gut microbiome information provides a practical foundation for scalable personalized PPGR prediction.

Figures & tables

Figure 1: Overview of the proposed multimodal framework for personalized PPGR prediction. A meal image is processed by the image encoder to produce image-derived macronutrient estimates, which are fused with clinical features using multi-head self-attention. Gut microbiome features condition the fused representation through FiLM modulation before the regression head jointly predicts $\mathrm{iAUC120}$ and the auxiliary target $\mathrm{AUC120}$ .

Model	R	p-value	95% CI
Oracle (GT macronutrients), original cohorts
Zeevi et al.	0.68	$<10^{-10}$	–
Berry et al.	0.77	–	–
Oracle (GT macronutrients), CGMacros dataset
Berry: Clinical + Macronutrients	0.66	$1.82{\times}10^{-8}$	(0.49, 0.80)
Berry: Clinical + Macronutrients + Microbiome	0.58	$1.20{\times}10^{-6}$	(0.42, 0.73)

Table 1: Pearson correlation (

R

) between predicted and measured

\mathrm{iAUC120}

. The upper block uses ground-truth (GT) macronutrients (oracle setting), while the lower block uses image-estimated macronutrients. Published results from Zeevi et al. [ 18 ] and Berry et al. [ 2 ] are shown for reference only.

Model	R	p-value	95% CI
MLP glucose prediction head (no macronutrients)
Clinical only	0.34	$8.18{\times}10^{-3}$	(0.07, 0.65)
Clinical + microbiome	0.53	$1.43{\times}10^{-5}$	(0.05, 0.71)
Attention glucose prediction head (no macronutrients)
Clinical only	0.24	$6.49{\times}10^{-2}$	(-0.04, 0.71)
Clinical + microbiome	0.36	$4.48{\times}10^{-3}$	(0.07, 0.68)

Table 2: Ablation study evaluating glucose prediction without explicit macronutrient features.

Blood Glucose Forecasting

Blood glucose forecasting predicts future glucose levels from continuous glucose monitor data and clinical context to support diabetes care.

See all 20 papers

MetaPlate: Counterfactual-Guided RAG-LLM Tool for Personalized Food Recommendation and Hyperglycemia Prevention
Jun 8, 2026Asiful Arefeen, Carol Johnston, Hassan GhasemzadehClinical Decision Support Generative Recommendation
College of Health Solutions, Arizona State University, Phoenix, AZ 85004, USA · School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ 85281, USA
DietDelta: A Vision-Language Approach for Dietary Assessment via Before-and-After Images
Apr 7, 2026Gautham Vinod, Siddeshwar Raghavan, Bruce Coburn +1
Purdue University, West Lafayette, Indiana, U.S.A.
It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glycemic-Event Prediction
Sep 8, 2026Andrea Apicella, Pasquale Arpaia, Matteo Orefice +2LLM Prompting Blood Glucose Forecasting
Department of Information Engineering, Electrical Engineering, and Applied Mathematics (DIEM), University of Salerno, Fisciano (SA), Italy · Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy

Jun 8, 2026J/K move · Enter open · S save

MetaPlate: Counterfactual-Guided RAG-LLM Tool for Personalized Food Recommendation and Hyperglycemia Prevention

Asiful Arefeen, Carol Johnston, Hassan Ghasemzadeh

College of Health Solutions, Arizona State University, Phoenix, AZ 85004, USA · School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ 85281, USA

Clinical Decision Support Generative Recommendation

Open paper AskPDF arXiv

Postprandial hyperglycemia is a key risk factor for metabolic disorders; however, existing dietary guidance is often static, impractical, and insufficiently personalized, providing recommendations that are difficult to follow or not impactful. While recent advances leverage continuous glucose monitoring (CGM) and machine learning to predict glycemic responses, these approaches are largely predictive and lack actionable guidance. Moreover, recommendation systems are often misaligned with user goals and require extensive input. We present MetaPlate, a counterfactual explanation (CF) guided, context-aware decision-support framework that generates personalized meal recommendations to mitigate postprandial glucose excursions in healthy adults. MetaPlate integrates multimodal data, including CGM readings, wearable-derived physiological signals, and user-provided meal inputs from

25

individuals to model pre-meal context. A machine learning model predicts glucose response, while a CF optimization module adjusts meal composition modifying macronutrient amounts to maintain glucose levels within a target range (

\leq 140

mg/dL). An LLM-based retrieval-augmented generation (RAG) layer enhances interpretability by producing human-readable recommendations using constrained search of the USDA food database. We evaluate MetaPlate via a structured expert-in-the-loop assessment with registered dietitians (RDs), comparing performance before and after prompt refinement. Results show improvements in meal realism, portion suitability, and recommendation likelihood, with expert feedback indicating a shift from clinically implausible outputs to actionable, contextually appropriate recommendations. Our findings emphasize the importance of domain knowledge and structured constraints in LLM-driven systems and highlight the potential of MetaPlate as a real-time personalized dietary decision-support tool.

Abstract

Blood Glucose Forecasting

Explore similar work

MetaPlate: Counterfactual-Guided RAG-LLM Tool for Personalized Food Recommendation and Hyperglycemia Prevention

DietDelta: A Vision-Language Approach for Dietary Assessment via Before-and-After Images

It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glycemic-Event Prediction