Applying an artificial neural network to predict total body water in hemodialysis patients

Jainn Shiun Chiu, Chee Fah Chong, Yuh Feng Lin, Chia Chao Wu, Yuh Feng Wang, Yu Chuan Li

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Background: Estimating total body water (TBW) is crucial in determining dry weight and dialytic dose for hemodialysis patients. Several anthropometric equations have been used to predict TBW, but a more accurate method is needed. We developed an artificial neural network (ANN) to predict TBW in hemodialysis patients. Methods: Demographic data, anthropometric measurements, and multifrequency bioelectrical impedance analysis (MF-BIA) were investigated in 54 patients. TBW measured by MF-BIA (TBW-BIA) was the reference. The predictive value of TBW based on ANN and five anthropometric equations (58% of actual body weight, Watson formula. Hume formula, Chertow formula, and Lee formula) was evaluated. Results: Predictive TBW values derived from anthropometric equations were significantly higher than TBW-BIA (31.341 ± 6.033 liters). The only non-significant difference was between TBW-ANN (31.468 ± 5.301 liters) and TBW-BIA (p = 0.639). ANN had the strongest Pearson's correlation coefficient (0.911) and smallest root mean square error (2.480); its peak centered most closely to zero with the shortest tails in an empirical cumulative distribution plot when compared with the other five equations. Conclusion: ANN could surpass traditional anthropometric equations and serve as a feasible alternative method of TBW estimation for chronic hemodialysis patients.

Original languageEnglish
Pages (from-to)507-513
Number of pages7
JournalAmerican Journal of Nephrology
Volume25
Issue number5
DOIs
Publication statusPublished - Sep 2005

Fingerprint

Body Water
Renal Dialysis
Electric Impedance
Body Weight
Demography
Weights and Measures

Keywords

  • Anthropometry
  • Bioelectrical impedance
  • Body water
  • Hemodialysis
  • Neural network

ASJC Scopus subject areas

  • Nephrology

Cite this

Applying an artificial neural network to predict total body water in hemodialysis patients. / Chiu, Jainn Shiun; Chong, Chee Fah; Lin, Yuh Feng; Wu, Chia Chao; Wang, Yuh Feng; Li, Yu Chuan.

In: American Journal of Nephrology, Vol. 25, No. 5, 09.2005, p. 507-513.

Research output: Contribution to journalArticle

Chiu, Jainn Shiun ; Chong, Chee Fah ; Lin, Yuh Feng ; Wu, Chia Chao ; Wang, Yuh Feng ; Li, Yu Chuan. / Applying an artificial neural network to predict total body water in hemodialysis patients. In: American Journal of Nephrology. 2005 ; Vol. 25, No. 5. pp. 507-513.
@article{d5d4302d448d4074894f4bb012562960,
title = "Applying an artificial neural network to predict total body water in hemodialysis patients",
abstract = "Background: Estimating total body water (TBW) is crucial in determining dry weight and dialytic dose for hemodialysis patients. Several anthropometric equations have been used to predict TBW, but a more accurate method is needed. We developed an artificial neural network (ANN) to predict TBW in hemodialysis patients. Methods: Demographic data, anthropometric measurements, and multifrequency bioelectrical impedance analysis (MF-BIA) were investigated in 54 patients. TBW measured by MF-BIA (TBW-BIA) was the reference. The predictive value of TBW based on ANN and five anthropometric equations (58{\%} of actual body weight, Watson formula. Hume formula, Chertow formula, and Lee formula) was evaluated. Results: Predictive TBW values derived from anthropometric equations were significantly higher than TBW-BIA (31.341 ± 6.033 liters). The only non-significant difference was between TBW-ANN (31.468 ± 5.301 liters) and TBW-BIA (p = 0.639). ANN had the strongest Pearson's correlation coefficient (0.911) and smallest root mean square error (2.480); its peak centered most closely to zero with the shortest tails in an empirical cumulative distribution plot when compared with the other five equations. Conclusion: ANN could surpass traditional anthropometric equations and serve as a feasible alternative method of TBW estimation for chronic hemodialysis patients.",
keywords = "Anthropometry, Bioelectrical impedance, Body water, Hemodialysis, Neural network",
author = "Chiu, {Jainn Shiun} and Chong, {Chee Fah} and Lin, {Yuh Feng} and Wu, {Chia Chao} and Wang, {Yuh Feng} and Li, {Yu Chuan}",
year = "2005",
month = "9",
doi = "10.1159/000088279",
language = "English",
volume = "25",
pages = "507--513",
journal = "American Journal of Nephrology",
issn = "0250-8095",
publisher = "S. Karger AG",
number = "5",

}

TY - JOUR

T1 - Applying an artificial neural network to predict total body water in hemodialysis patients

AU - Chiu, Jainn Shiun

AU - Chong, Chee Fah

AU - Lin, Yuh Feng

AU - Wu, Chia Chao

AU - Wang, Yuh Feng

AU - Li, Yu Chuan

PY - 2005/9

Y1 - 2005/9

N2 - Background: Estimating total body water (TBW) is crucial in determining dry weight and dialytic dose for hemodialysis patients. Several anthropometric equations have been used to predict TBW, but a more accurate method is needed. We developed an artificial neural network (ANN) to predict TBW in hemodialysis patients. Methods: Demographic data, anthropometric measurements, and multifrequency bioelectrical impedance analysis (MF-BIA) were investigated in 54 patients. TBW measured by MF-BIA (TBW-BIA) was the reference. The predictive value of TBW based on ANN and five anthropometric equations (58% of actual body weight, Watson formula. Hume formula, Chertow formula, and Lee formula) was evaluated. Results: Predictive TBW values derived from anthropometric equations were significantly higher than TBW-BIA (31.341 ± 6.033 liters). The only non-significant difference was between TBW-ANN (31.468 ± 5.301 liters) and TBW-BIA (p = 0.639). ANN had the strongest Pearson's correlation coefficient (0.911) and smallest root mean square error (2.480); its peak centered most closely to zero with the shortest tails in an empirical cumulative distribution plot when compared with the other five equations. Conclusion: ANN could surpass traditional anthropometric equations and serve as a feasible alternative method of TBW estimation for chronic hemodialysis patients.

AB - Background: Estimating total body water (TBW) is crucial in determining dry weight and dialytic dose for hemodialysis patients. Several anthropometric equations have been used to predict TBW, but a more accurate method is needed. We developed an artificial neural network (ANN) to predict TBW in hemodialysis patients. Methods: Demographic data, anthropometric measurements, and multifrequency bioelectrical impedance analysis (MF-BIA) were investigated in 54 patients. TBW measured by MF-BIA (TBW-BIA) was the reference. The predictive value of TBW based on ANN and five anthropometric equations (58% of actual body weight, Watson formula. Hume formula, Chertow formula, and Lee formula) was evaluated. Results: Predictive TBW values derived from anthropometric equations were significantly higher than TBW-BIA (31.341 ± 6.033 liters). The only non-significant difference was between TBW-ANN (31.468 ± 5.301 liters) and TBW-BIA (p = 0.639). ANN had the strongest Pearson's correlation coefficient (0.911) and smallest root mean square error (2.480); its peak centered most closely to zero with the shortest tails in an empirical cumulative distribution plot when compared with the other five equations. Conclusion: ANN could surpass traditional anthropometric equations and serve as a feasible alternative method of TBW estimation for chronic hemodialysis patients.

KW - Anthropometry

KW - Bioelectrical impedance

KW - Body water

KW - Hemodialysis

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=26444610828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26444610828&partnerID=8YFLogxK

U2 - 10.1159/000088279

DO - 10.1159/000088279

M3 - Article

C2 - 16155360

AN - SCOPUS:26444610828

VL - 25

SP - 507

EP - 513

JO - American Journal of Nephrology

JF - American Journal of Nephrology

SN - 0250-8095

IS - 5

ER -