Metadvice resources


Type 2 diabetes, hypertension, and hypercholesterolemia often develop in tandem with risk factors that appear to be more than additive. This work studies early therapeutic intervention beyond the silos that are created when looking at each morbidity separately.

We tested the hypothesis that machine learning could identify individuals in a UK primary care setting for whom personalised cholesterol-lowering therapy might be more appropriate than guideline-based recommendations.

By Lia Bally, David Herzig, Camillo Piazza, Lucas Brunschwig, Zeina Gabr, Yaron Dibner and André Jaun, 1 July 2023

Combining clinical guidelines with continuous learning from real world evidence data has the potential to effectively implement precision medicine by clinicians caring for people with diabetes. Such AI-driven platforms that integrate data from electronic health records are available and are readily extendable to include data from wearable technologies.

By David Herzig, Lia Bally, Thomas Castiglione, Philippine Des Courtils and André Jaun, 1 July 2023

Continuous glucose monitoring (CGM) provides a wealth of data for diagnostic and therapeutic decision-making in diabetes care. Current clinical treatment guidelines are based on standard time in range statistics. The goal of this study was to build a model, leveraging CGM data only, to characterise glucose-insulin regulation in patients with type 2 diabetes.

By Andrew Krentz, Lucas Brunschwig, Yaron Dibner, Hugo Michel and André Jaun, 18 June 2023

A proof-of-concept analysis that demonstrates the utility of a neural network to predict the development of one or more comorbidities based on data routinely collected in primary care, published in Diabetes, a journal of the American Diabetes Association.