Population exacerbation incidence contains predictive information of acute exacerbations in patients with chronic obstructive pulmonary disease in telecare

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

Objective Chronic obstructive pulmonary disease (COPD) is a major global burden largely resulting from acute exacerbations. We investigated whether the incidences of patient and population exacerbations contain predictive information for continuous prediction of exacerbations in COPD patients. Methods Data analysis was performed using home measurements from 1225 patients included in the large-scale telehomecare trial TeleCare North, where data supported 84 exacerbations occurring in 57 patients. Twenty-nine predictors were extracted and validated in two prediction models based on logistic regression. One model without and one model with inclusion of patient and population exacerbation incidences as potential predictors. The predictors were then evaluated by discriminative abilities between periods with and without exacerbation. Results The optimal predictor combinations provided an average area under the receiver operation characteristics curve of 0.63 with exclusion; inclusion of the population exacerbation incidence provided a curve of 0.74 (p < 0.05). These results were based on a two-fold patient dependent cross-validation. Discussion The present study has presented how the population exacerbation incidence contains predictive information in the continuous prediction of exacerbations in COPD patients. A system capable of predicting acute exacerbations could potentially prevent some cases of COPD-related complications and increase the health-related quality of life among COPD patients in telecare.

OriginalsprogEngelsk
TidsskriftInternational Journal of Medical Informatics
Vol/bind111
Sider (fra-til)72-76
ISSN1386-5056
DOI
StatusUdgivet - 2018

Fingerprint

Chronic Obstructive Pulmonary Disease
Incidence
Population
Logistic Models
Quality of Life

Citer dette

@article{df97defa859a4b66b22f97278d9279c1,
title = "Population exacerbation incidence contains predictive information of acute exacerbations in patients with chronic obstructive pulmonary disease in telecare",
abstract = "Objective Chronic obstructive pulmonary disease (COPD) is a major global burden largely resulting from acute exacerbations. We investigated whether the incidences of patient and population exacerbations contain predictive information for continuous prediction of exacerbations in COPD patients. Methods Data analysis was performed using home measurements from 1225 patients included in the large-scale telehomecare trial TeleCare North, where data supported 84 exacerbations occurring in 57 patients. Twenty-nine predictors were extracted and validated in two prediction models based on logistic regression. One model without and one model with inclusion of patient and population exacerbation incidences as potential predictors. The predictors were then evaluated by discriminative abilities between periods with and without exacerbation. Results The optimal predictor combinations provided an average area under the receiver operation characteristics curve of 0.63 with exclusion; inclusion of the population exacerbation incidence provided a curve of 0.74 (p < 0.05). These results were based on a two-fold patient dependent cross-validation. Discussion The present study has presented how the population exacerbation incidence contains predictive information in the continuous prediction of exacerbations in COPD patients. A system capable of predicting acute exacerbations could potentially prevent some cases of COPD-related complications and increase the health-related quality of life among COPD patients in telecare.",
author = "Larsen, {Thomas Kronborg} and Lasse Mark and Cichosz, {Simon Lebech} and Secher, {Pernille Heyckendorff} and Ole Hejlesen",
year = "2018",
doi = "10.1016/j.ijmedinf.2017.12.026",
language = "English",
volume = "111",
pages = "72--76",
journal = "International Journal of Medical Informatics",
issn = "1386-5056",
publisher = "Elsevier",

}

TY - JOUR

T1 - Population exacerbation incidence contains predictive information of acute exacerbations in patients with chronic obstructive pulmonary disease in telecare

AU - Larsen, Thomas Kronborg

AU - Mark, Lasse

AU - Cichosz, Simon Lebech

AU - Secher, Pernille Heyckendorff

AU - Hejlesen, Ole

PY - 2018

Y1 - 2018

N2 - Objective Chronic obstructive pulmonary disease (COPD) is a major global burden largely resulting from acute exacerbations. We investigated whether the incidences of patient and population exacerbations contain predictive information for continuous prediction of exacerbations in COPD patients. Methods Data analysis was performed using home measurements from 1225 patients included in the large-scale telehomecare trial TeleCare North, where data supported 84 exacerbations occurring in 57 patients. Twenty-nine predictors were extracted and validated in two prediction models based on logistic regression. One model without and one model with inclusion of patient and population exacerbation incidences as potential predictors. The predictors were then evaluated by discriminative abilities between periods with and without exacerbation. Results The optimal predictor combinations provided an average area under the receiver operation characteristics curve of 0.63 with exclusion; inclusion of the population exacerbation incidence provided a curve of 0.74 (p < 0.05). These results were based on a two-fold patient dependent cross-validation. Discussion The present study has presented how the population exacerbation incidence contains predictive information in the continuous prediction of exacerbations in COPD patients. A system capable of predicting acute exacerbations could potentially prevent some cases of COPD-related complications and increase the health-related quality of life among COPD patients in telecare.

AB - Objective Chronic obstructive pulmonary disease (COPD) is a major global burden largely resulting from acute exacerbations. We investigated whether the incidences of patient and population exacerbations contain predictive information for continuous prediction of exacerbations in COPD patients. Methods Data analysis was performed using home measurements from 1225 patients included in the large-scale telehomecare trial TeleCare North, where data supported 84 exacerbations occurring in 57 patients. Twenty-nine predictors were extracted and validated in two prediction models based on logistic regression. One model without and one model with inclusion of patient and population exacerbation incidences as potential predictors. The predictors were then evaluated by discriminative abilities between periods with and without exacerbation. Results The optimal predictor combinations provided an average area under the receiver operation characteristics curve of 0.63 with exclusion; inclusion of the population exacerbation incidence provided a curve of 0.74 (p < 0.05). These results were based on a two-fold patient dependent cross-validation. Discussion The present study has presented how the population exacerbation incidence contains predictive information in the continuous prediction of exacerbations in COPD patients. A system capable of predicting acute exacerbations could potentially prevent some cases of COPD-related complications and increase the health-related quality of life among COPD patients in telecare.

U2 - 10.1016/j.ijmedinf.2017.12.026

DO - 10.1016/j.ijmedinf.2017.12.026

M3 - Journal article

VL - 111

SP - 72

EP - 76

JO - International Journal of Medical Informatics

JF - International Journal of Medical Informatics

SN - 1386-5056

ER -