Metadvice resources
Publications
By David Herzig, Tommi Arffman, Maurice Rupp, Thomas .Castiglione, Philippine Des Courtils, Arina Lozhkina, Lia Bally, André Jaun, 18 Nov 2024
Insulin resistance plays an important role in metabolic disorders. HOMA-IR, a widely used measure of insulin resistance, requires quantification of fasting glucose and insulin, limiting its use to clinical settings. Continuous glucose monitoring (CGM) systems allow insights into glucose levels at minimal burden, yet with standard time-in-range and average-based metrics, detailed insights into glucose-insulin homeostasis are lacking. We aimed to develop a method to estimate insulin resistance based on free living CGM only, offering an accessible surrogate marker.
By Andrew Krentz, Lisa Fournier, Thomas Castiglione, Vasa Ćurčin, Camil Hamdane, Tianyi Liu, André Jaun, 10 October 2024
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 Yaron Dibner, Nicolas Brandt, Vasa Ćurčin, Andrew Krentz, Arina Lozhkina, Alexandre Luster, Arthur Père, André Jaun, 30 August 2024
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.
By Yaron Dibner, Nicolas Brandt, Andrew Krentz, Arina Lozhkina, Alexandre Luster, Arthur Père, André Jaun, 17 June 2024
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.
By Andrew Krentz, Lisa Fournier, Thomas Castiglione, Vasa Ćurčin, Camil Hamdane, Tianyi Liu, André Jaun, 30 May 2024
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.
By Andrew J Krentz, Gabe Haddon-Hill, Xiaoyan Zou, Natalie Pankova, André Jaun, 30 August 2022
Hypercholesterolemia gap analysis between NICE guidelines and UK primary care.