Neural network technology to predict intracellular water volume

J. S. Chiu, C. A. Chen, C. H. Lee, Y. C. Li, Y. F. Lin, Y. F. Wang, Fu Chiu Yu

Research output: Contribution to journalArticle

Abstract

Artificial neural network (ANN) is increasingly applied in clinical medicine. We therefore constructed an ANN to predict intracellular water (ICW) volume in 44 healthy Taiwaners. Demographic and anthropometric data were recorded as predictors, and ICW volume measured by bioelectrical impedance analysis (ICW-BIA) was the reference. ICW volume predicted by ANN (ICW-ANN) was compared with ICW-BIA. ICW-BIA (21.26 ± 0.58l) and ICW-ANN (21.25 ± 0.57l) was insignificantly different (p = 0.76). ICW-BIA and ICW-ANN were strongly correlated (r = 0.94, p <0.0001) with a significant agreement (mean difference, 0.01; lower and upper limits of agreement, -2.31 and 2.33) in Bland-Altman plot. Passing-Bablok regression was described as ICW-BIA = 1.04 × ICW-ANN-0.49, with 95% confidence interval for slope 0.94-1.14 and for intercept -2.76-1.49, indicating that both methods were interchangeable. ANN provided an excellent alternative of BIA to predict ICW volume in healthy subjects.

Original languageEnglish
Pages (from-to)1231-1238
Number of pages8
JournalInternational Journal of Clinical Practice
Volume60
Issue number10
DOIs
Publication statusPublished - Oct 2006

Fingerprint

Technology
Water
Clinical Medicine
Electric Impedance
Healthy Volunteers
Demography
Confidence Intervals

Keywords

  • Anthropometry
  • Bioelectrical impedance
  • Intracellular water
  • Neural network

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Neural network technology to predict intracellular water volume. / Chiu, J. S.; Chen, C. A.; Lee, C. H.; Li, Y. C.; Lin, Y. F.; Wang, Y. F.; Yu, Fu Chiu.

In: International Journal of Clinical Practice, Vol. 60, No. 10, 10.2006, p. 1231-1238.

Research output: Contribution to journalArticle

Chiu, J. S. ; Chen, C. A. ; Lee, C. H. ; Li, Y. C. ; Lin, Y. F. ; Wang, Y. F. ; Yu, Fu Chiu. / Neural network technology to predict intracellular water volume. In: International Journal of Clinical Practice. 2006 ; Vol. 60, No. 10. pp. 1231-1238.
@article{6cf3741969584d5e9817289a2c55c7b3,
title = "Neural network technology to predict intracellular water volume",
abstract = "Artificial neural network (ANN) is increasingly applied in clinical medicine. We therefore constructed an ANN to predict intracellular water (ICW) volume in 44 healthy Taiwaners. Demographic and anthropometric data were recorded as predictors, and ICW volume measured by bioelectrical impedance analysis (ICW-BIA) was the reference. ICW volume predicted by ANN (ICW-ANN) was compared with ICW-BIA. ICW-BIA (21.26 ± 0.58l) and ICW-ANN (21.25 ± 0.57l) was insignificantly different (p = 0.76). ICW-BIA and ICW-ANN were strongly correlated (r = 0.94, p <0.0001) with a significant agreement (mean difference, 0.01; lower and upper limits of agreement, -2.31 and 2.33) in Bland-Altman plot. Passing-Bablok regression was described as ICW-BIA = 1.04 × ICW-ANN-0.49, with 95{\%} confidence interval for slope 0.94-1.14 and for intercept -2.76-1.49, indicating that both methods were interchangeable. ANN provided an excellent alternative of BIA to predict ICW volume in healthy subjects.",
keywords = "Anthropometry, Bioelectrical impedance, Intracellular water, Neural network",
author = "Chiu, {J. S.} and Chen, {C. A.} and Lee, {C. H.} and Li, {Y. C.} and Lin, {Y. F.} and Wang, {Y. F.} and Yu, {Fu Chiu}",
year = "2006",
month = "10",
doi = "10.1111/j.1742-1241.2005.00761.x",
language = "English",
volume = "60",
pages = "1231--1238",
journal = "International Journal of Clinical Practice",
issn = "1368-5031",
publisher = "Wiley-Blackwell",
number = "10",

}

TY - JOUR

T1 - Neural network technology to predict intracellular water volume

AU - Chiu, J. S.

AU - Chen, C. A.

AU - Lee, C. H.

AU - Li, Y. C.

AU - Lin, Y. F.

AU - Wang, Y. F.

AU - Yu, Fu Chiu

PY - 2006/10

Y1 - 2006/10

N2 - Artificial neural network (ANN) is increasingly applied in clinical medicine. We therefore constructed an ANN to predict intracellular water (ICW) volume in 44 healthy Taiwaners. Demographic and anthropometric data were recorded as predictors, and ICW volume measured by bioelectrical impedance analysis (ICW-BIA) was the reference. ICW volume predicted by ANN (ICW-ANN) was compared with ICW-BIA. ICW-BIA (21.26 ± 0.58l) and ICW-ANN (21.25 ± 0.57l) was insignificantly different (p = 0.76). ICW-BIA and ICW-ANN were strongly correlated (r = 0.94, p <0.0001) with a significant agreement (mean difference, 0.01; lower and upper limits of agreement, -2.31 and 2.33) in Bland-Altman plot. Passing-Bablok regression was described as ICW-BIA = 1.04 × ICW-ANN-0.49, with 95% confidence interval for slope 0.94-1.14 and for intercept -2.76-1.49, indicating that both methods were interchangeable. ANN provided an excellent alternative of BIA to predict ICW volume in healthy subjects.

AB - Artificial neural network (ANN) is increasingly applied in clinical medicine. We therefore constructed an ANN to predict intracellular water (ICW) volume in 44 healthy Taiwaners. Demographic and anthropometric data were recorded as predictors, and ICW volume measured by bioelectrical impedance analysis (ICW-BIA) was the reference. ICW volume predicted by ANN (ICW-ANN) was compared with ICW-BIA. ICW-BIA (21.26 ± 0.58l) and ICW-ANN (21.25 ± 0.57l) was insignificantly different (p = 0.76). ICW-BIA and ICW-ANN were strongly correlated (r = 0.94, p <0.0001) with a significant agreement (mean difference, 0.01; lower and upper limits of agreement, -2.31 and 2.33) in Bland-Altman plot. Passing-Bablok regression was described as ICW-BIA = 1.04 × ICW-ANN-0.49, with 95% confidence interval for slope 0.94-1.14 and for intercept -2.76-1.49, indicating that both methods were interchangeable. ANN provided an excellent alternative of BIA to predict ICW volume in healthy subjects.

KW - Anthropometry

KW - Bioelectrical impedance

KW - Intracellular water

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=33748547543&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748547543&partnerID=8YFLogxK

U2 - 10.1111/j.1742-1241.2005.00761.x

DO - 10.1111/j.1742-1241.2005.00761.x

M3 - Article

C2 - 16981968

AN - SCOPUS:33748547543

VL - 60

SP - 1231

EP - 1238

JO - International Journal of Clinical Practice

JF - International Journal of Clinical Practice

SN - 1368-5031

IS - 10

ER -