Abstract

AimTo identify, predict and validate distinct glycaemic trajectories among patients with newly diagnosed type 2 diabetes treated in primary care, as a first step towards more effective patient-centred care.

MethodsWe conducted a retrospective study in two cohorts, using routinely collected individual patient data from primary care practices obtained from two large Dutch diabetes patient registries. Participants included adult patients newly diagnosed with type 2 diabetes between January 2006 and December 2014 (development cohort, n=10528; validation cohort, n=3777). Latent growth mixture modelling identified distinct glycaemic 5-year trajectories. Machine learning models were built to predict the trajectories using easily obtainable patient characteristics in daily clinical practice.

ResultsThree different glycaemic trajectories were identified: (1) stable, adequate glycaemic control (76.5% of patients); (2) improved glycaemic control (21.3% of patients); and (3) deteriorated glycaemic control (2.2% of patients). Similar trajectories could be discerned in the validation cohort. Body mass index and glycated haemoglobin and triglyceride levels were the most important predictors of trajectory membership. The predictive model, trained on the development cohort, had a receiver-operating characteristic area under the curve of 0.96 in the validation cohort, indicating excellent accuracy.

ConclusionsThe developed model can effectively explain heterogeneity in future glycaemic response of patients with type 2 diabetes. It can therefore be used in clinical practice as a quick and easy tool to provide tailored diabetes care.

Original languageEnglish
Pages (from-to)681-688
Number of pages8
JournalDiabetes, Obesity and Metabolism
Volume20
Issue number3
DOIs
Publication statusPublished - Mar 2018

Keywords

  • cohort study
  • database research
  • diabetes
  • glycaemic control
  • primary care
  • type 2
  • DISEASE MANAGEMENT
  • ALL-CAUSE
  • CARE
  • MIXTURE
  • PATIENT
  • TRAJECTORIES
  • MORTALITY
  • MEDICINE
  • MELLITUS
  • OUTCOMES
  • Humans
  • Middle Aged
  • Triglycerides/metabolism
  • Male
  • Netherlands
  • Female
  • Retrospective Studies
  • Risk Assessment/methods
  • Body Mass Index
  • Diabetes Mellitus, Type 2/blood
  • Blood Glucose/metabolism
  • Treatment Outcome
  • Hypoglycemic Agents/therapeutic use
  • Glycated Hemoglobin A/metabolism

Cite this

@article{1ba2857070384e67acb0d6e12c9cecfc,
title = "A risk score including body mass index, glycated haemoglobin and triglycerides predicts future glycaemic control in people with type 2 diabetes",
abstract = "AimTo identify, predict and validate distinct glycaemic trajectories among patients with newly diagnosed type 2 diabetes treated in primary care, as a first step towards more effective patient-centred care.MethodsWe conducted a retrospective study in two cohorts, using routinely collected individual patient data from primary care practices obtained from two large Dutch diabetes patient registries. Participants included adult patients newly diagnosed with type 2 diabetes between January 2006 and December 2014 (development cohort, n=10528; validation cohort, n=3777). Latent growth mixture modelling identified distinct glycaemic 5-year trajectories. Machine learning models were built to predict the trajectories using easily obtainable patient characteristics in daily clinical practice.ResultsThree different glycaemic trajectories were identified: (1) stable, adequate glycaemic control (76.5{\%} of patients); (2) improved glycaemic control (21.3{\%} of patients); and (3) deteriorated glycaemic control (2.2{\%} of patients). Similar trajectories could be discerned in the validation cohort. Body mass index and glycated haemoglobin and triglyceride levels were the most important predictors of trajectory membership. The predictive model, trained on the development cohort, had a receiver-operating characteristic area under the curve of 0.96 in the validation cohort, indicating excellent accuracy.ConclusionsThe developed model can effectively explain heterogeneity in future glycaemic response of patients with type 2 diabetes. It can therefore be used in clinical practice as a quick and easy tool to provide tailored diabetes care.",
keywords = "cohort study, database research, diabetes, glycaemic control, primary care, type 2, DISEASE MANAGEMENT, ALL-CAUSE, CARE, MIXTURE, PATIENT, TRAJECTORIES, MORTALITY, MEDICINE, MELLITUS, OUTCOMES, Humans, Middle Aged, Triglycerides/metabolism, Male, Netherlands, Female, Retrospective Studies, Risk Assessment/methods, Body Mass Index, Diabetes Mellitus, Type 2/blood, Blood Glucose/metabolism, Treatment Outcome, Hypoglycemic Agents/therapeutic use, Glycated Hemoglobin A/metabolism",
author = "Hertroijs, {Dorijn FL} and Elissen, {Arianne MJ} and Brouwers, {Martijn CGJ} and Schaper, {Nicolaas C} and Sebastian K{\"o}hler and Popa, {Mirela C} and Stylianos Asteriadis and Hendriks, {Steven H} and Bilo, {Henk J} and Dirk Ruwaard",
year = "2018",
month = "3",
doi = "10.1111/dom.13148",
language = "English",
volume = "20",
pages = "681--688",
journal = "Diabetes Obesity & Metabolism",
issn = "1462-8902",
publisher = "Wiley",
number = "3",

}

TY - JOUR

T1 - A risk score including body mass index, glycated haemoglobin and triglycerides predicts future glycaemic control in people with type 2 diabetes

AU - Hertroijs, Dorijn FL

AU - Elissen, Arianne MJ

AU - Brouwers, Martijn CGJ

AU - Schaper, Nicolaas C

AU - Köhler, Sebastian

AU - Popa, Mirela C

AU - Asteriadis, Stylianos

AU - Hendriks, Steven H

AU - Bilo, Henk J

AU - Ruwaard, Dirk

PY - 2018/3

Y1 - 2018/3

N2 - AimTo identify, predict and validate distinct glycaemic trajectories among patients with newly diagnosed type 2 diabetes treated in primary care, as a first step towards more effective patient-centred care.MethodsWe conducted a retrospective study in two cohorts, using routinely collected individual patient data from primary care practices obtained from two large Dutch diabetes patient registries. Participants included adult patients newly diagnosed with type 2 diabetes between January 2006 and December 2014 (development cohort, n=10528; validation cohort, n=3777). Latent growth mixture modelling identified distinct glycaemic 5-year trajectories. Machine learning models were built to predict the trajectories using easily obtainable patient characteristics in daily clinical practice.ResultsThree different glycaemic trajectories were identified: (1) stable, adequate glycaemic control (76.5% of patients); (2) improved glycaemic control (21.3% of patients); and (3) deteriorated glycaemic control (2.2% of patients). Similar trajectories could be discerned in the validation cohort. Body mass index and glycated haemoglobin and triglyceride levels were the most important predictors of trajectory membership. The predictive model, trained on the development cohort, had a receiver-operating characteristic area under the curve of 0.96 in the validation cohort, indicating excellent accuracy.ConclusionsThe developed model can effectively explain heterogeneity in future glycaemic response of patients with type 2 diabetes. It can therefore be used in clinical practice as a quick and easy tool to provide tailored diabetes care.

AB - AimTo identify, predict and validate distinct glycaemic trajectories among patients with newly diagnosed type 2 diabetes treated in primary care, as a first step towards more effective patient-centred care.MethodsWe conducted a retrospective study in two cohorts, using routinely collected individual patient data from primary care practices obtained from two large Dutch diabetes patient registries. Participants included adult patients newly diagnosed with type 2 diabetes between January 2006 and December 2014 (development cohort, n=10528; validation cohort, n=3777). Latent growth mixture modelling identified distinct glycaemic 5-year trajectories. Machine learning models were built to predict the trajectories using easily obtainable patient characteristics in daily clinical practice.ResultsThree different glycaemic trajectories were identified: (1) stable, adequate glycaemic control (76.5% of patients); (2) improved glycaemic control (21.3% of patients); and (3) deteriorated glycaemic control (2.2% of patients). Similar trajectories could be discerned in the validation cohort. Body mass index and glycated haemoglobin and triglyceride levels were the most important predictors of trajectory membership. The predictive model, trained on the development cohort, had a receiver-operating characteristic area under the curve of 0.96 in the validation cohort, indicating excellent accuracy.ConclusionsThe developed model can effectively explain heterogeneity in future glycaemic response of patients with type 2 diabetes. It can therefore be used in clinical practice as a quick and easy tool to provide tailored diabetes care.

KW - cohort study

KW - database research

KW - diabetes

KW - glycaemic control

KW - primary care

KW - type 2

KW - DISEASE MANAGEMENT

KW - ALL-CAUSE

KW - CARE

KW - MIXTURE

KW - PATIENT

KW - TRAJECTORIES

KW - MORTALITY

KW - MEDICINE

KW - MELLITUS

KW - OUTCOMES

KW - Humans

KW - Middle Aged

KW - Triglycerides/metabolism

KW - Male

KW - Netherlands

KW - Female

KW - Retrospective Studies

KW - Risk Assessment/methods

KW - Body Mass Index

KW - Diabetes Mellitus, Type 2/blood

KW - Blood Glucose/metabolism

KW - Treatment Outcome

KW - Hypoglycemic Agents/therapeutic use

KW - Glycated Hemoglobin A/metabolism

U2 - 10.1111/dom.13148

DO - 10.1111/dom.13148

M3 - Article

VL - 20

SP - 681

EP - 688

JO - Diabetes Obesity & Metabolism

JF - Diabetes Obesity & Metabolism

SN - 1462-8902

IS - 3

ER -