Prediction model for cardiovascular events or all-cause mortality in incident dialysis patients

Daijo Inaguma, Daichi Morii, Daijiro Kabata, Hiroyuki Yoshida, Akihito Tanaka, Eri Koshi-Ito, Kazuo Takahashi, Hiroki Hayashi, Shigehisa Koide, Naotake Tsuboi, Midori Hasegawa, Ayumi Shintani, Yukio Yuzawa

Research output: Contribution to journalArticle

Abstract

Some variables including age, comorbidity of diabetes, and so on at dialysis initiation are associated with patient prognosis. Cardiovascular (CV) events are a major cause of death, and adequate models that predict prognosis in dialysis patients are warranted. Therefore, we created models using some variables at dialysis initiation. We used a database of 1,520 consecutive dialysis patients (median age, 70 years; 492 women [32.4%]) from a multicenter prospective cohort study. We established the primary endpoint as a composite of the incidence of first CV events or all-cause death. A multivariable Cox proportional hazard regression model was used to construct a model. We considered a complex and a simple model. We used area under the receiver operating characteristic curve (AUROC) to assess and compare the predictive performances of the prediction models and evaluated the improvement in discrimination using the complex model versus the simple model using net reclassification improvement (NRI). We then assessed integrated discrimination improvement (IDI) to evaluate improvements in average sensitivity and specificity. Of 392 deaths, 152 were CV-related. Totally, 506 CV events occurred during the follow-up period (median 1,285 days). Finally, 692 patients reached the primary endpoint. Baseline data were set at dialysis initiation. AUROC for the primary endpoint was 0.737 (95% confidence interval [CI], 0.712–0.761) in the simple model and 0.765 (95% CI, 0.741–0.788) in the complex model. There were significant intergroup differences in NRI (0.44; 95% CI, 0.34–0.53; p < 0.001) and IDI (0.02; 95% CI, 0.02–0.03; p < 0.001). We prepared a Shiny R application for each model to automatically calculate the predicted occurrence probability (https://statacademy.shinyapps.io/App_inaguma_20190717/). The complex model made more accurate predictions than the simple model. However, the intergroup difference was not significant. Hence, the simple model was more useful than the complex model. The tool was useful in a real-world clinical setting because it required only routinely available variables. Moreover, we emphasized that the tool could predict the incidence of CV events or all-cause mortality for individual patients. In the future, we must confirm its external validity in other prospective cohorts.

Original languageEnglish
Article numbere0221352
JournalPloS one
Volume14
Issue number8
DOIs
Publication statusPublished - 01-01-2019

Fingerprint

Cardiovascular Models
Dialysis
dialysis
prediction
Mortality
Confidence Intervals
ROC Curve
Cause of Death
confidence interval
Incidence
endpoints
Proportional Hazards Models
Comorbidity
Cohort Studies
Databases
Prospective Studies
death
taxonomic revisions
Sensitivity and Specificity
prognosis

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • General

Cite this

Inaguma, Daijo ; Morii, Daichi ; Kabata, Daijiro ; Yoshida, Hiroyuki ; Tanaka, Akihito ; Koshi-Ito, Eri ; Takahashi, Kazuo ; Hayashi, Hiroki ; Koide, Shigehisa ; Tsuboi, Naotake ; Hasegawa, Midori ; Shintani, Ayumi ; Yuzawa, Yukio. / Prediction model for cardiovascular events or all-cause mortality in incident dialysis patients. In: PloS one. 2019 ; Vol. 14, No. 8.
@article{ade85b06169840f4bdcec26d02fd63a7,
title = "Prediction model for cardiovascular events or all-cause mortality in incident dialysis patients",
abstract = "Some variables including age, comorbidity of diabetes, and so on at dialysis initiation are associated with patient prognosis. Cardiovascular (CV) events are a major cause of death, and adequate models that predict prognosis in dialysis patients are warranted. Therefore, we created models using some variables at dialysis initiation. We used a database of 1,520 consecutive dialysis patients (median age, 70 years; 492 women [32.4{\%}]) from a multicenter prospective cohort study. We established the primary endpoint as a composite of the incidence of first CV events or all-cause death. A multivariable Cox proportional hazard regression model was used to construct a model. We considered a complex and a simple model. We used area under the receiver operating characteristic curve (AUROC) to assess and compare the predictive performances of the prediction models and evaluated the improvement in discrimination using the complex model versus the simple model using net reclassification improvement (NRI). We then assessed integrated discrimination improvement (IDI) to evaluate improvements in average sensitivity and specificity. Of 392 deaths, 152 were CV-related. Totally, 506 CV events occurred during the follow-up period (median 1,285 days). Finally, 692 patients reached the primary endpoint. Baseline data were set at dialysis initiation. AUROC for the primary endpoint was 0.737 (95{\%} confidence interval [CI], 0.712–0.761) in the simple model and 0.765 (95{\%} CI, 0.741–0.788) in the complex model. There were significant intergroup differences in NRI (0.44; 95{\%} CI, 0.34–0.53; p < 0.001) and IDI (0.02; 95{\%} CI, 0.02–0.03; p < 0.001). We prepared a Shiny R application for each model to automatically calculate the predicted occurrence probability (https://statacademy.shinyapps.io/App_inaguma_20190717/). The complex model made more accurate predictions than the simple model. However, the intergroup difference was not significant. Hence, the simple model was more useful than the complex model. The tool was useful in a real-world clinical setting because it required only routinely available variables. Moreover, we emphasized that the tool could predict the incidence of CV events or all-cause mortality for individual patients. In the future, we must confirm its external validity in other prospective cohorts.",
author = "Daijo Inaguma and Daichi Morii and Daijiro Kabata and Hiroyuki Yoshida and Akihito Tanaka and Eri Koshi-Ito and Kazuo Takahashi and Hiroki Hayashi and Shigehisa Koide and Naotake Tsuboi and Midori Hasegawa and Ayumi Shintani and Yukio Yuzawa",
year = "2019",
month = "1",
day = "1",
doi = "10.1371/journal.pone.0221352",
language = "English",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "8",

}

Inaguma, D, Morii, D, Kabata, D, Yoshida, H, Tanaka, A, Koshi-Ito, E, Takahashi, K, Hayashi, H, Koide, S, Tsuboi, N, Hasegawa, M, Shintani, A & Yuzawa, Y 2019, 'Prediction model for cardiovascular events or all-cause mortality in incident dialysis patients', PloS one, vol. 14, no. 8, e0221352. https://doi.org/10.1371/journal.pone.0221352

Prediction model for cardiovascular events or all-cause mortality in incident dialysis patients. / Inaguma, Daijo; Morii, Daichi; Kabata, Daijiro; Yoshida, Hiroyuki; Tanaka, Akihito; Koshi-Ito, Eri; Takahashi, Kazuo; Hayashi, Hiroki; Koide, Shigehisa; Tsuboi, Naotake; Hasegawa, Midori; Shintani, Ayumi; Yuzawa, Yukio.

In: PloS one, Vol. 14, No. 8, e0221352, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction model for cardiovascular events or all-cause mortality in incident dialysis patients

AU - Inaguma, Daijo

AU - Morii, Daichi

AU - Kabata, Daijiro

AU - Yoshida, Hiroyuki

AU - Tanaka, Akihito

AU - Koshi-Ito, Eri

AU - Takahashi, Kazuo

AU - Hayashi, Hiroki

AU - Koide, Shigehisa

AU - Tsuboi, Naotake

AU - Hasegawa, Midori

AU - Shintani, Ayumi

AU - Yuzawa, Yukio

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Some variables including age, comorbidity of diabetes, and so on at dialysis initiation are associated with patient prognosis. Cardiovascular (CV) events are a major cause of death, and adequate models that predict prognosis in dialysis patients are warranted. Therefore, we created models using some variables at dialysis initiation. We used a database of 1,520 consecutive dialysis patients (median age, 70 years; 492 women [32.4%]) from a multicenter prospective cohort study. We established the primary endpoint as a composite of the incidence of first CV events or all-cause death. A multivariable Cox proportional hazard regression model was used to construct a model. We considered a complex and a simple model. We used area under the receiver operating characteristic curve (AUROC) to assess and compare the predictive performances of the prediction models and evaluated the improvement in discrimination using the complex model versus the simple model using net reclassification improvement (NRI). We then assessed integrated discrimination improvement (IDI) to evaluate improvements in average sensitivity and specificity. Of 392 deaths, 152 were CV-related. Totally, 506 CV events occurred during the follow-up period (median 1,285 days). Finally, 692 patients reached the primary endpoint. Baseline data were set at dialysis initiation. AUROC for the primary endpoint was 0.737 (95% confidence interval [CI], 0.712–0.761) in the simple model and 0.765 (95% CI, 0.741–0.788) in the complex model. There were significant intergroup differences in NRI (0.44; 95% CI, 0.34–0.53; p < 0.001) and IDI (0.02; 95% CI, 0.02–0.03; p < 0.001). We prepared a Shiny R application for each model to automatically calculate the predicted occurrence probability (https://statacademy.shinyapps.io/App_inaguma_20190717/). The complex model made more accurate predictions than the simple model. However, the intergroup difference was not significant. Hence, the simple model was more useful than the complex model. The tool was useful in a real-world clinical setting because it required only routinely available variables. Moreover, we emphasized that the tool could predict the incidence of CV events or all-cause mortality for individual patients. In the future, we must confirm its external validity in other prospective cohorts.

AB - Some variables including age, comorbidity of diabetes, and so on at dialysis initiation are associated with patient prognosis. Cardiovascular (CV) events are a major cause of death, and adequate models that predict prognosis in dialysis patients are warranted. Therefore, we created models using some variables at dialysis initiation. We used a database of 1,520 consecutive dialysis patients (median age, 70 years; 492 women [32.4%]) from a multicenter prospective cohort study. We established the primary endpoint as a composite of the incidence of first CV events or all-cause death. A multivariable Cox proportional hazard regression model was used to construct a model. We considered a complex and a simple model. We used area under the receiver operating characteristic curve (AUROC) to assess and compare the predictive performances of the prediction models and evaluated the improvement in discrimination using the complex model versus the simple model using net reclassification improvement (NRI). We then assessed integrated discrimination improvement (IDI) to evaluate improvements in average sensitivity and specificity. Of 392 deaths, 152 were CV-related. Totally, 506 CV events occurred during the follow-up period (median 1,285 days). Finally, 692 patients reached the primary endpoint. Baseline data were set at dialysis initiation. AUROC for the primary endpoint was 0.737 (95% confidence interval [CI], 0.712–0.761) in the simple model and 0.765 (95% CI, 0.741–0.788) in the complex model. There were significant intergroup differences in NRI (0.44; 95% CI, 0.34–0.53; p < 0.001) and IDI (0.02; 95% CI, 0.02–0.03; p < 0.001). We prepared a Shiny R application for each model to automatically calculate the predicted occurrence probability (https://statacademy.shinyapps.io/App_inaguma_20190717/). The complex model made more accurate predictions than the simple model. However, the intergroup difference was not significant. Hence, the simple model was more useful than the complex model. The tool was useful in a real-world clinical setting because it required only routinely available variables. Moreover, we emphasized that the tool could predict the incidence of CV events or all-cause mortality for individual patients. In the future, we must confirm its external validity in other prospective cohorts.

UR - http://www.scopus.com/inward/record.url?scp=85071077005&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071077005&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0221352

DO - 10.1371/journal.pone.0221352

M3 - Article

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 8

M1 - e0221352

ER -