Hypervolemia Screening for Dialysis Patient Healthcare Using Meta Learning Model-Based Intelligent Scaler

Wei Ling Chen, Hsiang Yueh Lai, Pi Yun Chen, Chung-Dann Kan, Chia Hung Lin

Research output: Contribution to journalArticle

Abstract

Sodium intake and diet are the main factors controlling fluid volume balance and changes in body weight for dialysis patients. Inadequate dry weight controls will lead to various complications. Sometimes, inadequate fluid volume removal will cause hypotension during dialysis treatment. Therefore, maintaining adequate body weight, water volume balance, and blood pressure are important in the healthcare of dialysis patients. The anthropometric method is a non-invasive and mathematical statistical model to estimate the total body water with the patient characteristics, including gender, age, height, and weight. In the experienced anthropometric methods, Watson standard formula is a well known criterion and has < 2% margin error for estimating TBW in different populations. For multipatient use in hypervolemia and hypovolemia screening, the enrolled dialysis patients will gradually increase, thus, new criterions are required to meet the modified individual standard with varying patient characteristics. This study proposes a meta-learning model-based intelligent scaler. When new subjects or existing subjects update new training patterns in the current active database, an incremental learning scheme is used to retrain the generalized regression neural network, updating new training patterns or adding incremental ones. The meta-learning model also possesses learning-to-optimization capability using the particle swarm optimization algorithm. Through incremental training patterns, this intelligent scaler can gradually enhance optimization that can be applicable to individuals of all gender and age groups. The experimental results indicate that the proposed screening model provides an assistive tool for maintaining an appropriate BMI and dry weight in the healthcare of dialysis patients.

Original languageEnglish
Pages (from-to)16-27
Number of pages12
JournalSmart Science
Volume7
Issue number1
DOIs
Publication statusPublished - 2019 Jan 2

Fingerprint

Meta-learning
Dialysis
Healthcare
Screening
Model-based
Weight control
Water
Fluid
Incremental Learning
Fluids
Optimization
Blood pressure
Blood Pressure
Nutrition
Complications
Particle Swarm Optimization Algorithm
Sodium
Margin
Particle swarm optimization (PSO)
Statistical Model

All Science Journal Classification (ASJC) codes

  • Chemistry (miscellaneous)
  • Modelling and Simulation
  • Energy (miscellaneous)
  • Engineering(all)
  • Fluid Flow and Transfer Processes
  • Computer Networks and Communications
  • Computational Mathematics

Cite this

Chen, Wei Ling ; Lai, Hsiang Yueh ; Chen, Pi Yun ; Kan, Chung-Dann ; Lin, Chia Hung. / Hypervolemia Screening for Dialysis Patient Healthcare Using Meta Learning Model-Based Intelligent Scaler. In: Smart Science. 2019 ; Vol. 7, No. 1. pp. 16-27.
@article{8fca178f98f54af7ab6c8f3168125ede,
title = "Hypervolemia Screening for Dialysis Patient Healthcare Using Meta Learning Model-Based Intelligent Scaler",
abstract = "Sodium intake and diet are the main factors controlling fluid volume balance and changes in body weight for dialysis patients. Inadequate dry weight controls will lead to various complications. Sometimes, inadequate fluid volume removal will cause hypotension during dialysis treatment. Therefore, maintaining adequate body weight, water volume balance, and blood pressure are important in the healthcare of dialysis patients. The anthropometric method is a non-invasive and mathematical statistical model to estimate the total body water with the patient characteristics, including gender, age, height, and weight. In the experienced anthropometric methods, Watson standard formula is a well known criterion and has < 2{\%} margin error for estimating TBW in different populations. For multipatient use in hypervolemia and hypovolemia screening, the enrolled dialysis patients will gradually increase, thus, new criterions are required to meet the modified individual standard with varying patient characteristics. This study proposes a meta-learning model-based intelligent scaler. When new subjects or existing subjects update new training patterns in the current active database, an incremental learning scheme is used to retrain the generalized regression neural network, updating new training patterns or adding incremental ones. The meta-learning model also possesses learning-to-optimization capability using the particle swarm optimization algorithm. Through incremental training patterns, this intelligent scaler can gradually enhance optimization that can be applicable to individuals of all gender and age groups. The experimental results indicate that the proposed screening model provides an assistive tool for maintaining an appropriate BMI and dry weight in the healthcare of dialysis patients.",
author = "Chen, {Wei Ling} and Lai, {Hsiang Yueh} and Chen, {Pi Yun} and Chung-Dann Kan and Lin, {Chia Hung}",
year = "2019",
month = "1",
day = "2",
doi = "10.1080/23080477.2018.1517293",
language = "English",
volume = "7",
pages = "16--27",
journal = "Smart Science",
issn = "2308-0477",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

Hypervolemia Screening for Dialysis Patient Healthcare Using Meta Learning Model-Based Intelligent Scaler. / Chen, Wei Ling; Lai, Hsiang Yueh; Chen, Pi Yun; Kan, Chung-Dann; Lin, Chia Hung.

In: Smart Science, Vol. 7, No. 1, 02.01.2019, p. 16-27.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Hypervolemia Screening for Dialysis Patient Healthcare Using Meta Learning Model-Based Intelligent Scaler

AU - Chen, Wei Ling

AU - Lai, Hsiang Yueh

AU - Chen, Pi Yun

AU - Kan, Chung-Dann

AU - Lin, Chia Hung

PY - 2019/1/2

Y1 - 2019/1/2

N2 - Sodium intake and diet are the main factors controlling fluid volume balance and changes in body weight for dialysis patients. Inadequate dry weight controls will lead to various complications. Sometimes, inadequate fluid volume removal will cause hypotension during dialysis treatment. Therefore, maintaining adequate body weight, water volume balance, and blood pressure are important in the healthcare of dialysis patients. The anthropometric method is a non-invasive and mathematical statistical model to estimate the total body water with the patient characteristics, including gender, age, height, and weight. In the experienced anthropometric methods, Watson standard formula is a well known criterion and has < 2% margin error for estimating TBW in different populations. For multipatient use in hypervolemia and hypovolemia screening, the enrolled dialysis patients will gradually increase, thus, new criterions are required to meet the modified individual standard with varying patient characteristics. This study proposes a meta-learning model-based intelligent scaler. When new subjects or existing subjects update new training patterns in the current active database, an incremental learning scheme is used to retrain the generalized regression neural network, updating new training patterns or adding incremental ones. The meta-learning model also possesses learning-to-optimization capability using the particle swarm optimization algorithm. Through incremental training patterns, this intelligent scaler can gradually enhance optimization that can be applicable to individuals of all gender and age groups. The experimental results indicate that the proposed screening model provides an assistive tool for maintaining an appropriate BMI and dry weight in the healthcare of dialysis patients.

AB - Sodium intake and diet are the main factors controlling fluid volume balance and changes in body weight for dialysis patients. Inadequate dry weight controls will lead to various complications. Sometimes, inadequate fluid volume removal will cause hypotension during dialysis treatment. Therefore, maintaining adequate body weight, water volume balance, and blood pressure are important in the healthcare of dialysis patients. The anthropometric method is a non-invasive and mathematical statistical model to estimate the total body water with the patient characteristics, including gender, age, height, and weight. In the experienced anthropometric methods, Watson standard formula is a well known criterion and has < 2% margin error for estimating TBW in different populations. For multipatient use in hypervolemia and hypovolemia screening, the enrolled dialysis patients will gradually increase, thus, new criterions are required to meet the modified individual standard with varying patient characteristics. This study proposes a meta-learning model-based intelligent scaler. When new subjects or existing subjects update new training patterns in the current active database, an incremental learning scheme is used to retrain the generalized regression neural network, updating new training patterns or adding incremental ones. The meta-learning model also possesses learning-to-optimization capability using the particle swarm optimization algorithm. Through incremental training patterns, this intelligent scaler can gradually enhance optimization that can be applicable to individuals of all gender and age groups. The experimental results indicate that the proposed screening model provides an assistive tool for maintaining an appropriate BMI and dry weight in the healthcare of dialysis patients.

UR - http://www.scopus.com/inward/record.url?scp=85053356066&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053356066&partnerID=8YFLogxK

U2 - 10.1080/23080477.2018.1517293

DO - 10.1080/23080477.2018.1517293

M3 - Article

VL - 7

SP - 16

EP - 27

JO - Smart Science

JF - Smart Science

SN - 2308-0477

IS - 1

ER -