Forskning
Udskriv Udskriv
Switch language
Region Hovedstaden - en del af Københavns Universitetshospital
Udgivet

Nationwide prediction of type 2 diabetes comorbidities

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Harvard

Dworzynski, P, Aasbrenn, M, Rostgaard, K, Melbye, M, Gerds, TA, Hjalgrim, H & Pers, TH 2020, 'Nationwide prediction of type 2 diabetes comorbidities', Scientific Reports, bind 10, nr. 1, 1776, s. 1776. https://doi.org/10.1038/s41598-020-58601-7

APA

Dworzynski, P., Aasbrenn, M., Rostgaard, K., Melbye, M., Gerds, T. A., Hjalgrim, H., & Pers, T. H. (2020). Nationwide prediction of type 2 diabetes comorbidities. Scientific Reports, 10(1), 1776. [1776]. https://doi.org/10.1038/s41598-020-58601-7

CBE

MLA

Vancouver

Author

Dworzynski, Piotr ; Aasbrenn, Martin ; Rostgaard, Klaus ; Melbye, Mads ; Gerds, Thomas Alexander ; Hjalgrim, Henrik ; Pers, Tune H. / Nationwide prediction of type 2 diabetes comorbidities. I: Scientific Reports. 2020 ; Bind 10, Nr. 1. s. 1776.

Bibtex

@article{9843f1dcb9a3494c988274c0d98b9c51,
title = "Nationwide prediction of type 2 diabetes comorbidities",
abstract = "Identification of individuals at risk of developing disease comorbidities represents an important task in tackling the growing personal and societal burdens associated with chronic diseases. We employed machine learning techniques to investigate to what extent data from longitudinal, nationwide Danish health registers can be used to predict individuals at high risk of developing type 2 diabetes (T2D) comorbidities. Leveraging logistic regression-, random forest- and gradient boosting models and register data spanning hospitalizations, drug prescriptions and contacts with primary care contractors from >200,000 individuals newly diagnosed with T2D, we predicted five-year risk of heart failure (HF), myocardial infarction (MI), stroke (ST), cardiovascular disease (CVD) and chronic kidney disease (CKD). For HF, MI, CVD, and CKD, register-based models outperformed a reference model leveraging canonical individual characteristics by achieving area under the receiver operating characteristic curve improvements of 0.06, 0.03, 0.04, and 0.07, respectively. The top 1,000 patients predicted to be at highest risk exhibited observed incidence ratios exceeding 4.99, 3.52, 1.97 and 4.71 respectively. In summary, prediction of T2D comorbidities utilizing Danish registers led to consistent albeit modest performance improvements over reference models, suggesting that register data could be leveraged to systematically identify individuals at risk of developing disease comorbidities.",
keywords = "Cardiovascular Diseases/epidemiology, Comorbidity, Denmark/epidemiology, Diabetes Mellitus, Type 2/epidemiology, Female, Heart Failure/epidemiology, Humans, Male, Middle Aged, Myocardial Infarction/epidemiology, Registries, Renal Insufficiency, Chronic/epidemiology, Stroke/epidemiology",
author = "Piotr Dworzynski and Martin Aasbrenn and Klaus Rostgaard and Mads Melbye and Gerds, {Thomas Alexander} and Henrik Hjalgrim and Pers, {Tune H}",
year = "2020",
month = feb,
day = "4",
doi = "10.1038/s41598-020-58601-7",
language = "English",
volume = "10",
pages = "1776",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

RIS

TY - JOUR

T1 - Nationwide prediction of type 2 diabetes comorbidities

AU - Dworzynski, Piotr

AU - Aasbrenn, Martin

AU - Rostgaard, Klaus

AU - Melbye, Mads

AU - Gerds, Thomas Alexander

AU - Hjalgrim, Henrik

AU - Pers, Tune H

PY - 2020/2/4

Y1 - 2020/2/4

N2 - Identification of individuals at risk of developing disease comorbidities represents an important task in tackling the growing personal and societal burdens associated with chronic diseases. We employed machine learning techniques to investigate to what extent data from longitudinal, nationwide Danish health registers can be used to predict individuals at high risk of developing type 2 diabetes (T2D) comorbidities. Leveraging logistic regression-, random forest- and gradient boosting models and register data spanning hospitalizations, drug prescriptions and contacts with primary care contractors from >200,000 individuals newly diagnosed with T2D, we predicted five-year risk of heart failure (HF), myocardial infarction (MI), stroke (ST), cardiovascular disease (CVD) and chronic kidney disease (CKD). For HF, MI, CVD, and CKD, register-based models outperformed a reference model leveraging canonical individual characteristics by achieving area under the receiver operating characteristic curve improvements of 0.06, 0.03, 0.04, and 0.07, respectively. The top 1,000 patients predicted to be at highest risk exhibited observed incidence ratios exceeding 4.99, 3.52, 1.97 and 4.71 respectively. In summary, prediction of T2D comorbidities utilizing Danish registers led to consistent albeit modest performance improvements over reference models, suggesting that register data could be leveraged to systematically identify individuals at risk of developing disease comorbidities.

AB - Identification of individuals at risk of developing disease comorbidities represents an important task in tackling the growing personal and societal burdens associated with chronic diseases. We employed machine learning techniques to investigate to what extent data from longitudinal, nationwide Danish health registers can be used to predict individuals at high risk of developing type 2 diabetes (T2D) comorbidities. Leveraging logistic regression-, random forest- and gradient boosting models and register data spanning hospitalizations, drug prescriptions and contacts with primary care contractors from >200,000 individuals newly diagnosed with T2D, we predicted five-year risk of heart failure (HF), myocardial infarction (MI), stroke (ST), cardiovascular disease (CVD) and chronic kidney disease (CKD). For HF, MI, CVD, and CKD, register-based models outperformed a reference model leveraging canonical individual characteristics by achieving area under the receiver operating characteristic curve improvements of 0.06, 0.03, 0.04, and 0.07, respectively. The top 1,000 patients predicted to be at highest risk exhibited observed incidence ratios exceeding 4.99, 3.52, 1.97 and 4.71 respectively. In summary, prediction of T2D comorbidities utilizing Danish registers led to consistent albeit modest performance improvements over reference models, suggesting that register data could be leveraged to systematically identify individuals at risk of developing disease comorbidities.

KW - Cardiovascular Diseases/epidemiology

KW - Comorbidity

KW - Denmark/epidemiology

KW - Diabetes Mellitus, Type 2/epidemiology

KW - Female

KW - Heart Failure/epidemiology

KW - Humans

KW - Male

KW - Middle Aged

KW - Myocardial Infarction/epidemiology

KW - Registries

KW - Renal Insufficiency, Chronic/epidemiology

KW - Stroke/epidemiology

U2 - 10.1038/s41598-020-58601-7

DO - 10.1038/s41598-020-58601-7

M3 - Journal article

C2 - 32019971

VL - 10

SP - 1776

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 1776

ER -

ID: 61824936