Neuro-fuzzy technology as a predictor of parathyroid hormone level in hemodialysis patients

Chiou An Chen, Yu Chuan Li, Yuh Feng Lin, Fu Chiu Yu, Wei Hsin Huang, Jainn Shiun Chiu

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Measuring the plasma parathyroid hormone (PTH) concentration is crucial to evaluate renal bone disease in patients with renal failure. Although frequent measurement is needed to avoid inadequate prescription of phosphate binders and vitamin D preparations, artificial intelligence can repeatedly perform the forecasting tasks and may be a satisfactory substitute for laboratory tests. Neurofuzzy technology represents a promising forecasting application in clinical medicine. We therefore constructed a coactive neuro-fuzzy inference system (CANFIS) to predict plasma PTH concentrations in hemodialysis patients. The CANFIS was constructed with clinical parameters (patient age, plasma albumin, calcium, phosphorus, alkaline phosphatase, and calcium-phosphorus product) from a cohort of hemodialysis patients, and plasma PTH concentration measured by radioimmunoassay (RIA) was the supervised outcome. The accuracy of the CANFIS was prospectively compared with RIA in another hospital. Plasma PTH concentrations measured by RIA and predicted by CANFIS were 179.04 ± 38.18 ng/l and 179.34 ± 37.76 ng/l, respectively (p = 0.15). The CANFIS was able to precisely estimate plasma PTH concentrations in hemodialysis patients. These results suggest that the neuro-fuzzy technology, based on limited clinical parameters, is an excellent alternative to RIA for accurately predicting plasma PTH concentration in hemodialysis patients.

Original languageEnglish
Pages (from-to)81-87
Number of pages7
JournalTohoku Journal of Experimental Medicine
Volume211
Issue number1
DOIs
Publication statusPublished - 2007
Externally publishedYes

Fingerprint

Parathyroid Hormone
Fuzzy inference
Renal Dialysis
Technology
Plasmas
Radioimmunoassay
Phosphorus
Calcium
Artificial Intelligence
Bone Diseases
Clinical Medicine
Vitamin D
Serum Albumin
Medicine
Artificial intelligence
Binders
Renal Insufficiency
Prescriptions
Alkaline Phosphatase
Bone

Keywords

  • Fuzzy logic
  • Hemodialysis
  • Neural network
  • Parathyroid hormone

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Neuro-fuzzy technology as a predictor of parathyroid hormone level in hemodialysis patients. / Chen, Chiou An; Li, Yu Chuan; Lin, Yuh Feng; Yu, Fu Chiu; Huang, Wei Hsin; Chiu, Jainn Shiun.

In: Tohoku Journal of Experimental Medicine, Vol. 211, No. 1, 2007, p. 81-87.

Research output: Contribution to journalArticle

Chen, Chiou An ; Li, Yu Chuan ; Lin, Yuh Feng ; Yu, Fu Chiu ; Huang, Wei Hsin ; Chiu, Jainn Shiun. / Neuro-fuzzy technology as a predictor of parathyroid hormone level in hemodialysis patients. In: Tohoku Journal of Experimental Medicine. 2007 ; Vol. 211, No. 1. pp. 81-87.
@article{b5462d0142864a5786fa4409f5bc5f39,
title = "Neuro-fuzzy technology as a predictor of parathyroid hormone level in hemodialysis patients",
abstract = "Measuring the plasma parathyroid hormone (PTH) concentration is crucial to evaluate renal bone disease in patients with renal failure. Although frequent measurement is needed to avoid inadequate prescription of phosphate binders and vitamin D preparations, artificial intelligence can repeatedly perform the forecasting tasks and may be a satisfactory substitute for laboratory tests. Neurofuzzy technology represents a promising forecasting application in clinical medicine. We therefore constructed a coactive neuro-fuzzy inference system (CANFIS) to predict plasma PTH concentrations in hemodialysis patients. The CANFIS was constructed with clinical parameters (patient age, plasma albumin, calcium, phosphorus, alkaline phosphatase, and calcium-phosphorus product) from a cohort of hemodialysis patients, and plasma PTH concentration measured by radioimmunoassay (RIA) was the supervised outcome. The accuracy of the CANFIS was prospectively compared with RIA in another hospital. Plasma PTH concentrations measured by RIA and predicted by CANFIS were 179.04 ± 38.18 ng/l and 179.34 ± 37.76 ng/l, respectively (p = 0.15). The CANFIS was able to precisely estimate plasma PTH concentrations in hemodialysis patients. These results suggest that the neuro-fuzzy technology, based on limited clinical parameters, is an excellent alternative to RIA for accurately predicting plasma PTH concentration in hemodialysis patients.",
keywords = "Fuzzy logic, Hemodialysis, Neural network, Parathyroid hormone",
author = "Chen, {Chiou An} and Li, {Yu Chuan} and Lin, {Yuh Feng} and Yu, {Fu Chiu} and Huang, {Wei Hsin} and Chiu, {Jainn Shiun}",
year = "2007",
doi = "10.1620/tjem.211.81",
language = "English",
volume = "211",
pages = "81--87",
journal = "Tohoku Journal of Experimental Medicine",
issn = "0040-8727",
publisher = "Tohoku University Medical Press",
number = "1",

}

TY - JOUR

T1 - Neuro-fuzzy technology as a predictor of parathyroid hormone level in hemodialysis patients

AU - Chen, Chiou An

AU - Li, Yu Chuan

AU - Lin, Yuh Feng

AU - Yu, Fu Chiu

AU - Huang, Wei Hsin

AU - Chiu, Jainn Shiun

PY - 2007

Y1 - 2007

N2 - Measuring the plasma parathyroid hormone (PTH) concentration is crucial to evaluate renal bone disease in patients with renal failure. Although frequent measurement is needed to avoid inadequate prescription of phosphate binders and vitamin D preparations, artificial intelligence can repeatedly perform the forecasting tasks and may be a satisfactory substitute for laboratory tests. Neurofuzzy technology represents a promising forecasting application in clinical medicine. We therefore constructed a coactive neuro-fuzzy inference system (CANFIS) to predict plasma PTH concentrations in hemodialysis patients. The CANFIS was constructed with clinical parameters (patient age, plasma albumin, calcium, phosphorus, alkaline phosphatase, and calcium-phosphorus product) from a cohort of hemodialysis patients, and plasma PTH concentration measured by radioimmunoassay (RIA) was the supervised outcome. The accuracy of the CANFIS was prospectively compared with RIA in another hospital. Plasma PTH concentrations measured by RIA and predicted by CANFIS were 179.04 ± 38.18 ng/l and 179.34 ± 37.76 ng/l, respectively (p = 0.15). The CANFIS was able to precisely estimate plasma PTH concentrations in hemodialysis patients. These results suggest that the neuro-fuzzy technology, based on limited clinical parameters, is an excellent alternative to RIA for accurately predicting plasma PTH concentration in hemodialysis patients.

AB - Measuring the plasma parathyroid hormone (PTH) concentration is crucial to evaluate renal bone disease in patients with renal failure. Although frequent measurement is needed to avoid inadequate prescription of phosphate binders and vitamin D preparations, artificial intelligence can repeatedly perform the forecasting tasks and may be a satisfactory substitute for laboratory tests. Neurofuzzy technology represents a promising forecasting application in clinical medicine. We therefore constructed a coactive neuro-fuzzy inference system (CANFIS) to predict plasma PTH concentrations in hemodialysis patients. The CANFIS was constructed with clinical parameters (patient age, plasma albumin, calcium, phosphorus, alkaline phosphatase, and calcium-phosphorus product) from a cohort of hemodialysis patients, and plasma PTH concentration measured by radioimmunoassay (RIA) was the supervised outcome. The accuracy of the CANFIS was prospectively compared with RIA in another hospital. Plasma PTH concentrations measured by RIA and predicted by CANFIS were 179.04 ± 38.18 ng/l and 179.34 ± 37.76 ng/l, respectively (p = 0.15). The CANFIS was able to precisely estimate plasma PTH concentrations in hemodialysis patients. These results suggest that the neuro-fuzzy technology, based on limited clinical parameters, is an excellent alternative to RIA for accurately predicting plasma PTH concentration in hemodialysis patients.

KW - Fuzzy logic

KW - Hemodialysis

KW - Neural network

KW - Parathyroid hormone

UR - http://www.scopus.com/inward/record.url?scp=33846104479&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846104479&partnerID=8YFLogxK

U2 - 10.1620/tjem.211.81

DO - 10.1620/tjem.211.81

M3 - Article

C2 - 17202775

AN - SCOPUS:33846104479

VL - 211

SP - 81

EP - 87

JO - Tohoku Journal of Experimental Medicine

JF - Tohoku Journal of Experimental Medicine

SN - 0040-8727

IS - 1

ER -