An omics-based machine learning approach to predict diabetes progression: a RHAPSODY study
Diabetologia, vol. 67, pp. 885–894
Abstract
Abstract Aims/hypothesis People with type 2 diabetes are heterogeneous in their disease trajectory, with some progressing more quickly to insulin initiation than others. Although classical biomarkers such as age, HbA1c and diabetes duration are associated with glycaemic progression, it is unclear how well such variables predict insulin initiation or requirement and whether newly identified markers have added predictive value. Methods In two prospective cohort studies as part of IMI-RHAPSODY, we investigated whether clinical variables and three types of molecular markers (metabolites, lipids, proteins) can predict time to insulin requirement using different machine learning approaches (lasso, ridge, GRridge, random forest). Clinical variables included age, sex, HbA1c, HDL-cholesterol and C-peptide. Models were run with unpenalised clinical variables (i.e. always included in the model without weights) or penalised clinical variables, or without clinical variables. Model development was performed in one cohort and the model was applied in a second cohort. Model performance was evaluated using Harrel’s C statistic. Results Of the 585 individuals from the Hoorn Diabetes Care System (DCS) cohort, 69 required insulin during follow-up (1.0–11.4 years); of the 571 individuals in the Genetics of Diabetes Audit and Research in Tayside Scotland (GoDARTS) cohort, 175 required insulin during follow-up (0.3–11.8 years). Overall, the clinical variables and proteins were selected in the different models most often, followed by the metabolites. The most frequently selected clinical variables were HbA1c (18 of the 36 models, 50%), age (15 models, 41.2%) and C-peptide (15 models, 41.2%). Base models (age, sex, BMI, HbA1c) including only clinical variables performed moderately in both the DCS discovery cohort (C statistic 0.71 [95% CI 0.64, 0.79]) and the GoDARTS replication cohort (C 0.71 [95% CI 0.69, 0.75]). A more extensive model including HDL-cholesterol and C-peptide performed better in both cohorts (DCS, C 0.74 [95% CI 0.67, 0.81]; GoDARTS, C 0.73 [95% CI 0.69, 0.77]). Two proteins, lactadherin and proto-oncogene tyrosine-protein kinase receptor, were most consistently selected and slightly improved model performance. Conclusions/interpretation Using machine learning approaches, we show that insulin requirement risk can be modestly well predicted by predominantly clinical variables. Inclusion of molecular markers improves the prognostic performance beyond that of clinical variables by up to 5%. Such prognostic models could be useful for identifying people with diabetes at high risk of progressing quickly to treatment intensification. Data availability Summary statistics of lipidomic, proteomic and metabolomic data are available from a Shiny dashboard at https://rhapdata-app.vital-it.ch . Graphical Abstract
Authors 12
-
Leiden University Medical Center · Amsterdam Public Health · Amsterdam University Medical Centers · Amsterdam Cardiovascular Sciences · Vrije Universiteit Amsterdam
Affiliation as printed
Amsterdam Cardiovascular Sciences, Amsterdam, the Netherlands
Amsterdam Public Health, Amsterdam, the Netherlands
Department of Cell and Chemical Biology, Leiden University Medical Center, Leiden, the Netherlands
Department of Epidemiology and Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
-
Amsterdam University Medical Centers · Vrije Universiteit Amsterdam
Affiliation as printed
Department of Epidemiology and Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
-
Affiliation as printed
Population Health & Genomics, School of Medicine, University of Dundee, Dundee, UK
-
Leiden University Medical Center · Delft University of Technology
Affiliation as printed
Delft Bioinformatics Lab, Delft University of Technology, Delft, the Netherlands
Department of Cell and Chemical Biology, Leiden University Medical Center, Leiden, the Netherlands
-
SIB Swiss Institute of Bioinformatics
Affiliation as printed
Vital-IT Group, SIB Swiss Institute of Bioinformatics, Lausanne, Switzerland
-
Amsterdam Public Health · Amsterdam University Medical Centers · Amsterdam Cardiovascular Sciences · Vrije Universiteit Amsterdam
Affiliation as printed
Amsterdam Cardiovascular Sciences, Amsterdam, the Netherlands
Amsterdam Public Health, Amsterdam, the Netherlands
Department of General Practice, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
-
Nanyang Technological University · Imperial College London · Université de Montréal
Affiliation as printed
CRCHUM, Faculty of Medicine, Université de Montréal, Montréal, QC, Canada
Department of Metabolism, Digestion and Reproduction, Faculty of Medicine, Imperial College London, London, UK
Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Republic of Singapore
-
SIB Swiss Institute of Bioinformatics
Affiliation as printed
Vital-IT Group, SIB Swiss Institute of Bioinformatics, Lausanne, Switzerland
-
Affiliation as printed
Population Health & Genomics, School of Medicine, University of Dundee, Dundee, UK
-
Leen M. ‘t Hart Aachen Department of Biomedical Data Sciences Section of Molecular Epidemiology Department of Cell and Chemical Biology
Leiden University Medical Center · Amsterdam University Medical Centers · Vrije Universiteit Amsterdam
Affiliation as printed
Department of Biomedical Data Sciences, Section of Molecular Epidemiology, Leiden University Medical Center, Leiden, the Netherlands
Department of Cell and Chemical Biology, Leiden University Medical Center, Leiden, the Netherlands
Department of Epidemiology and Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
-
Amsterdam Public Health · Amsterdam University Medical Centers · Vrije Universiteit Amsterdam
Affiliation as printed
Amsterdam Public Health, Amsterdam, the Netherlands
Department of Epidemiology and Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
-
Joline W. J. Beulens corresponding
University Medical Center Utrecht · Amsterdam Public Health · Amsterdam University Medical Centers · Amsterdam Cardiovascular Sciences · Vrije Universiteit Amsterdam
Affiliation as printed
Amsterdam Cardiovascular Sciences, Amsterdam, the Netherlands. j.beulens@amsterdamumc.nl
Amsterdam Public Health, Amsterdam, the Netherlands. j.beulens@amsterdamumc.nl
Department of Epidemiology and Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands. j.beulens@amsterdamumc.nl
Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht, the Netherlands. j.beulens@amsterdamumc.nl
Amsterdam Cardiovascular Sciences, Amsterdam, the Netherlands
Cited by 9 stored of 9
9 results
No patents citing this paper on Lens.org (checked 2026-10-11).