Prediction of glycaemic control and quality of life in people with type 2 diabetes using glucose-lowering drugs with machine learning - The Maastricht study

Aug 5, 2026

Aims to evaluate whether machine learning can identify people with type 2 diabetes who are unlikely to achieve adequate glycaemic control and who are likely to experience deterioration in quality of life (QoL) within one year. Data from The Maastricht Study were used, including 842 participants with HbA1c information and 964 participants with QoL information. Multiple machine-learning algorithms with feature-selection methods were assessed to build prediction models for these outcomes. Findings support targeted attention for patients at risk of failing guideline-based goals and worsening QoL.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Background

Aim

Methods

Data sources and participants

Algorithms and feature selection

Results

Conclusion

EUR Research Information Portal Prediction of glycaemic control and quality of life in people with type 2 diabetes using glucose-lowering drugs with machine learning-The Maastricht study Published in: Diabetes Obesity & Metabolism Publication status and date: E-pub ahead of print: 17/07/2025 DOI (link to publisher): 10.1111/dom.16598 Document Version Publisher's PDF, also known as Version of record Document License/Available under: CC BY-NC-ND Citation for the published version (APA): Werkman, N. C. C. , Nielen, J. T. H. , Tapia-Galisteo, J. , Somolinos-Simon, F. J. , Hernando, M. E. , Wang, J. , Jiu, L. , Goettsch, W. G. , Bosma, H. , Schram, M. T. , van Greevenbroek, M. M. J. , Wesselius, A. , Stehouwer, C. D. A. , Driessen, J. H. M. , & Garcia-Saez, G. (2025) . Prediction of glycaemic control and quality of life in people with type 2 diabetes using glucoselowering drugs with machine learning-The Maastricht study. Diabetes Obesity & Metabolism, 27(10), 5524-5537. Advance online publication. [https://doi.org/10.1111/dom.16598](https://doi.org/10.1111/dom.16598) Link to publication on the EUR Research Information Portal Terms and Conditions of Use Except as permitted by the applicable copyright law, you may not reproduce or make this material available to any third party without the prior written permission from the copyright holder(s) . Copyright law allows the following uses of this material without prior permission: • you may download, save and print a copy of this material for your personal use only; • you may share the EUR portal link to this material. In case the material is published with an open access license (e.g. a Creative Commons (CC) license), other uses may be allowed. Please check the terms and conditions of the specific license. Take-down policy If you believe that this material infringes your copyright and/or any other intellectual property rights, you may request its removal by contacting us at the following email address: [openaccess.library@eur.nl. Please](openaccess.library@eur.nl. Please) provide us with all the relevant information, including the reasons why you believe any of your rights have been infringed. In case of a legitimate complaint, we will make the material inaccessible and/or remove it from the website. Received: 27 March 2025 Revised: 18 June 2025 Accepted: 27 June 2025 DOI: 10.1111/dom.16598 O R IG INA L ARTI CLE Prediction of glycaemic control and quality of life in people with type 2 diabetes using glucose-lowering drugs with machine learning—The Maastricht study Nikki C. C. Werkman PhD 1,2 | Johannes T. H. Nielen PhD 1,2 | José Tapia-Galisteo PhD 3,4 | Francisco J. Somolinos-Simón PhD 3 | Maria Elena Hernando PhD 3,4 | Junfeng Wang PhD 5 | Li Jiu PhD 5 | Wim G. Goettsch PhD 5,6 | Hans Bosma PhD 7 | Miranda T. Schram PhD 1,8,9,10 | Marleen M. J. van Greevenbroek PhD 1,8 | Anke Wesselius PhD 11 | Coen D. A. Stehouwer PhD 1,8 | Johanna H. M. Driessen PhD 1,2 | Gema Garcia-Sáez PhD 3,4 1Department of Clinical Pharmacy, Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, The Netherlands 2Department of Clinical Pharmacy and Toxicology, Maastricht University Medical Center+, Maastricht, The Netherlands 3Bioengineering and Telemedicine Group, Centro de Tecnología Biomédica, ETSI de Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain 4CIBER-BBN: Networking Research Center for Bioengineering, Biomaterials and Nanomedicine, Madrid, Spain 5Division of Pharmacoepidemiology and Clinical Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht University, Utrecht, The Netherlands 6National Health Care Institute, Diemen, The Netherlands 7School for Public Health and Primary Care (CAPHRI), Maastricht University, Maastricht, The Netherlands 8Department of Internal Medicine, Maastricht University Medical Center+, Maastricht, The Netherlands 9School for Mental Health & Neuro

FAQs

What problem does the study address?

Type 2 diabetes patients receive the same guideline treatment, yet some have difficulty reaching glycaemic control goals and maintaining quality of life. The study targets early identification of people unlikely to meet both outcomes within one year.

How was the prediction approach evaluated?

The study used data from The Maastricht Study and assessed several machine-learning algorithms combined with feature selection methods.

Which outcomes are being predicted and over what timeframe?

The model predicts inadequate glycaemic control and deterioration in quality of life within one year using information such as HbA1c values and QoL measures.

Aug 5, 2026

Upload by Evangeline