Multimodal AI correlates of glucose spikes in people with normal glucose regulation, pre-diabetes and type 2 diabetes

刊登時間

The researchers conducted a prospective, site-less clinical trial, The PRediction Of Glycemic RESponse Study, to collect multimodal data from a diverse group of participants with a range of abnormal glucose homeostasis, from normoglycemia to prediabetes to type 2 diabetes (T2D).

Multimodal data included continuous glucose monitor (CGM) data alongside gut microbiome, diet, physical activity and genetic information.

The aim of this work was to investigate the determinants of abnormal glucose spikes across different diabetes states and to leverage multimodal data to define multimodal glycemic risk profiles that can potentially change our approach to preventing and treating T2D by enhancing early diagnosis and improving monitoring of prediabetes and prediction of T2D.

We found significant differences in the distribution of glucose spike metrics among different diabetes states, with longer expected time for spike resolution and higher values of nocturnal hypoglycemia in T2D.

We identified significant correlations between mean glucose level and gut microbiome diversity, and between expected time for spike resolution and resting heart rate.

Our multimodal glycemic risk profiles, validated in 1,955 normoglycemic and 114 prediabetic individuals from an independent cohort, improved risk stratification by highlighting substantial variability among individuals with the same value of HbA1c.

These findings lay the foundation for alternative approaches that could potentially revolutionize the way complex diseases such as T2D are prevented, diagnosed and treated.

【MORE】