# Beyond Binary Classification: Multiclass Machine Learning for Diabetes and Prediabetes Risk Prediction Using NHANES

DevFeed: [Beyond Binary Classification: Multiclass Machine Learning for Diabetes and Prediabetes Risk Prediction Using NHANES](<https://devfeed.tech/articles/beyond-binary-classification-multiclass-machine-learning-for-diabetes-and-prediabetes-risk-prediction-using-nhanes-133146.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16756>)

Author: Aman Mujahid, Anita Penkova

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Transformers](<https://devfeed.tech/topics/transformers.md>)

Tags: [classification](<https://devfeed.tech/tags/classification.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [diabetes](<https://devfeed.tech/tags/diabetes.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [performance](<https://devfeed.tech/tags/performance.md>), [precision](<https://devfeed.tech/tags/precision.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [risk](<https://devfeed.tech/tags/risk.md>), [supervised-learning](<https://devfeed.tech/tags/supervised-learning.md>), [transformer](<https://devfeed.tech/tags/transformer.md>)

## AI overview

Using NHANES data for 15,356 adults, the study compares conventional and transformer models that classify people as normal, prediabetic, or diabetic from demographic, clinical, and lifestyle variables. HbA1c defines the labels but is excluded from model inputs to prevent leakage. Multiclass performance reaches 0.72 accuracy and 0.70 macro-F1, but prediabetes is hardest to identify (F1 0.53-0.56), consistent with its overlap with both neighboring states. Binary normal-versus-prediabetes F1 is 0.62-0.64; combining prediabetes and diabetes in a broader screening class raises F1 to 0.73-0.74 across models. The similar results across model types suggest that class overlap, rather than architecture, is the greater obstacle. The abstract describes a trade-off: three-class prediction better represents risk progression, while broader binary screening scores higher.

## Source excerpt

arXiv:2611.16756v1 Announce Type: new Abstract: Detecting diabetes risk early is important for preventing disease progression. Most existing machine learning approaches focus on binary classification, which limits their ability to capture intermediate risk states such as prediabetes. We develop a supervised learning framework to classify adults as normal, prediabetic, or diabetic using National Health and Nutrition Examination Survey data. The framework uses routinely collected demographic, clinical, and lifestyle variables from 15,356 adults, with glycated hemoglobin (HbA1c) used only to define labels and excluded from input features to prevent leakage. We compare conventional machine learning and transformer-based models and examine two binary formulations: normal versus prediabetes, and normal versus combined prediabetes and diabetes. Models are evaluated on a held-out test set using precision, sensitivity, specificity, and F1 score. In the multiclass setting, performance is broadly consistent across models, with accuracy up to 0.72 and macro-averaged F1 of 0.70. Prediabetes remains the most challenging class, with F1 scores of 0.54 to 0.56 for conventional models and 0.53 to 0.55 for transformers, reflecting its overlap with both neighboring states. When the task is reduced to normal versus prediabetes, F1 scores rise modestly to 0.62 to 0.64. A more substantial improvement is observed under a broader screening formulation combining prediabetes and diabetes, with F1 scores of 0.73 to 0.74 across all models. These findings suggest that feature overlap along the biological continuum between normal and diabetic states contributes more to the difficulty of prediabetes detection than model architecture. Multiclass prediction provides a more clinically informative representation of metabolic risk progression but highlights a trade-off between clinically meaningful stratification and predictive accuracy.