Multi-adaptive neural-fuzzy system as a novel predictor of in-vivo blood side dialyser urea clearance
International Journal of Computer Applications in TechnologyPublished 1 January 2013
Ahmad Taher Azar
Citations8
SJR quartileQ3
SJR score0.22
SNIP0.36
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The results suggest that the neuro-fuzzy technology, based on limited clinical parameters, is an excellent alternative method for accurately predicting arterial and venous urea concentrations in hemodialysis patients.
Abstract
The blood urea concentration has been used as a surrogate marker for toxin elimination in hemodialysed patients, and several indices based on it have been proposed in recent years for monitoring treatment adequacy. Measuring urea nitrogen concentrations at the inlet and outlet of dialyser is crucial to evaluate the in-vivo blood side dialyser urea clearance during hemodialysis. Although frequent measurement is needed to avoid inadequate dialysis efficiency, artificial intelligence can repeatedly perform the forecasting tasks and may be a satisfactory substitute for laboratory tests. Neuro-fuzzy technology represents a promising forecasting application in clinical medicine. In this study, two fuzzy models have been proposed to predict dialyser inlet and outlet urea concentrations in order to estimate dialyser clearance without blood sampling. The model is of multi-input single-output (MISO) type. Multi-adaptive neuro-fuzzy inference system (MANFIS) technique of fuzzy-based systems has been employed. The performance of the model is authenticated by evaluating the predicted results with the practical results obtained by conducting the confirmation experiments. The results suggest that the neuro-fuzzy technology, based on limited clinical parameters, is an excellent alternative method for accurately predicting arterial and venous urea concentrations in hemodialysis patients. The proposed model can be used for intelligent online adaptive system.
Keywords
Computer ScienceEngineering
The LancetSTATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT
47,620 Citations1986J Martin Bland, DouglasG. Altman
An alternative approach, based on graphical techniques and simple calculations, is described, together with the relation between this analysis and the assessment of repeatability.
IEEE Transactions on Systems Man and CyberneticsFuzzy identification of systems and its applications to modeling and control
19,403 Citations1985Tomohiro Takagi, Michio Sugeno
A mathematical tool to build a fuzzy model of a system where fuzzy implications and reasoning are used is presented and two applications of the method to industrial processes are discussed: a water cleaning process and a converter in a steel-making process.
IEEE Transactions on Systems Man and CyberneticsANFIS: adaptive-network-based fuzzy inference system
16,152 Citations1993Jyh‐Shing Roger Jang
The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy inference system) is presented, which is a fuzzy inference System implemented in the framework of adaptive networks.
IEEE Transactions on Systems Man and CyberneticsOutline of a New Approach to the Analysis of Complex Systems and Decision Processes
8,667 Citations1973Lotfi A. Zadeh
By relying on the use of linguistic variables and fuzzy algorithms, the approach provides an approximate and yet effective means of describing the behavior of systems which are too complex or too ill-defined to admit of precise mathematical analysis.
International Journal of Human-Computer StudiesAn Experiment in Linguistic Synthesis with a Fuzzy Logic Controller
5,636 Citations1999E.H. Mamdani, S. ASSILIAN
Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence
4,637 Citations1996Jyh‐Shing Roger Jang, Chuen–Tsai Sun
Proceedings of the IEEENeuro-fuzzy modeling and control
2,315 Citations1995Jyh‐Shing Roger Jang, Chuen–Tsai Sun
The essential part of neuro-fuzzy synergisms comes from a common framework called adaptive networks, which unifies both neural networks and fuzzy models, which possess certain advantages over neural networks.
Wiley eBooksUnderstanding robust and exploratory data analysis
1,876 Citations1983David C. Hoaglin, Frederick Mosteller +1 more
IEEE Transactions on Neural NetworksSelf-learning fuzzy controllers based on temporal backpropagation
903 Citations1992Jyh‐Shing Roger Jang
A generalized control strategy that enhances fuzzy controllers with self-learning capability for achieving prescribed control objectives in a near-optimal manner is presented and the inverted pendulum system is employed as a testbed to demonstrate the effectiveness of the proposed control scheme and the robustness of the acquired fuzzy controller.
CERN Document Server (European Organization for Nuclear Research)Neurofuzzy Adaptive Modelling and Control
789 Citations1993Martin Brown, C.J. Harris
This book provides a unified description of several adaptive neural and fuzzy networks and introduces the associative memory class of systems - which describe the similarities and differences existing between fuzzy and neural algorithms.
The LancetIntroduction to neural networks
608 Citations1995Simon S. Cross, Robert F. Harrison +1 more
Applied Soft ComputingA novel approach for ANFIS modelling based on full factorial design
291 Citations2007Mrinal Buragohain, Chitralekha Mahanta
By employing the proposed method the number of data required for learning in the ANFIS network could be significantly reduced and thereby computation time as well as computation complexity is remarkably reduced.
ComputerCommonsense Knowledge Representation Based on Fuzzy Logic
169 Citations1983Zadeh
The approach to the representation of commonsense knowledge described in this article is based on the idea that propositions characterizing commomsense knowledge are for the most part, dispositions -- that is, propositions with implied fuzzy quantifiers.
Nephrology Dialysis TransplantationSolute fluxes in different treatment modalities
116 Citations2000J. K. Leypoldt
The principles governing solute flux or transport in different artificial kidney treatment modalities are reviewed and it was shown that the clearance of small solutes depends largely on the dialysate flow rate and is similar when using either haemodialysis or haemmodiafiltration, while clearance of middle molecules, especially low-molecular-weight proteins, depends mainly on convective transport induced by high ultrafiltration rates.
Journal of Biomechanical EngineeringSimultaneous Convective and Diffusive Mass Transfers in a Hemodialyser
94 Citations1990Michel Y. Jaffrin, Luhui Ding +1 more
Clearances of creatinin, vitamin B12, and myoglobin have been calculated as a function of blood and ultrafiltrate flow rate and were found to be in good agreement with in vitro measurements.
Artificial OrgansConvective Mass Transfer in Hemodialysis
89 Citations1995Michel Y. Jaffrin
A surprising result is that the convective contribution to the clearance is, in the limit of dominant ultrafiltration, independent of the solute sieving coefficient, in contrast to the model of Villaroel et al.
Journal of Membrane ScienceMathematical modeling of fluid and solute transport in hemodialysis and peritoneal dialysis
85 Citations2006Jacek Waniewski
Current approaches to modeling of transport processes in dialysis, including alternative and complementary versions, are described and discussed.
Artificial Intelligence in MedicineNeural computation in medicine
80 Citations1993James A. Reggia
The nature of a neural model is explained and work in neural computation involving problems in medical informatics and modelling of psychiatric and neurological phenomena is reviewed.
Artificial OrgansTheoretical Description of Mass Transport in Medical Membrane Devices
49 Citations1995Andrzej Weryński, Jacek Waniewski
The application of the one-dimensional theory of mass transport to the derivation of mathematical formulas for clearances of a variety of membrane mass exchangers, namely hemodialyzers, hemofilters, plasma separators, and the cascade filtration procedure has been reviewed.
Artificial OrgansTheoretical Basis and Experimental Verification of the Impact of Ultrafiltration on Dialyzer Clearance
39 Citations1991Jacek Waniewski, Andrzej Weryński +4 more
The theoretical results were confirmed in experiments carried out in vitro for hollow-fiber dialyzers and small molecular weightsolutes (urea, creatinine, sodium, TcO4) as well as middle molecular weight solutes (vitamin B12).
PubMedMeasurement of the transmittance coefficient spectrum of Cuprophan and RP69 membranes: applications to middle molecule removal via ultrafiltration.
39 Citations1976Green Dm, Antwiler Gd +3 more
A membrane model illustrating a semi-empirical correlation between permeability and transmittance has been developed and can be completely characterized by a simple Gaussian distribution employing 2 parameters, the selectivity and the mean molecular diameter.
American Journal of Kidney DiseasesPrediction of equilibrated postdialysis BUN by an artificial neural network in high-efficiency hemodialysis
36 Citations1998Guh Jy, Chih‐Yu Yang +3 more
Low-flow ANN can accurately predict both Ceq and eKt/V60 regardless of the degree of urea rebound, which is usually underestimated with an overestimation of the KT/V.
Nephrology Dialysis TransplantationArtificial neural networks improve the prediction of Kt/V, follow-up dietary protein intake and hypotension risk in haemodialysis patients
30 Citations2004Luca Gabutti, D. Vadilonga +3 more
The use of ANN significantly improves the ability of experienced nephrologists to estimate the KT/V and the follow-up PCR and to detect a Kt/V < 1.00 g/kg/day and the occurrence of intradialytic hypotension.
Kidney InternationalUsefulness of artificial neural networks to predict follow-up dietary protein intake in hemodialysis patients
27 Citations2004Luca Gabutti, Michel Burnier +4 more
The use of ANN significantly improves the ability of the experienced nephrologist to estimate and to detect an unsatisfactory follow-up PCR and the interinstitutional performance of the ANN is positively influenced by the size and the variability of the population used to build the mathematical model.
Blood PurificationUsing Artificial Intelligence to Predict the Equilibrated Postdialysis Blood Urea Concentration
25 Citations2001Elmer A. Fernández, Rodolfo Valtuille +2 more
A supervised neural network is proposed to predict the equilibrated postdialysis blood urea (eqU) at 60 min after the end of hemodialysis and is shown to be better than the currently accepted methods.
Artificial OrgansEvaluation of the Impact of Ultrafiltration on Dialyzer Clearance
24 Citations1979Andrzej Weryński
The influence of ultrafiltration on dialyzer clearance is analyzed and the results obtained theoretically are verified with experimental data.
Clinical NephrologyComparison of different methods for hemodialysis evaluation by means of ROC curves: from artificial intelligence to current methods
21 Citations2005Elmer A. Fernández, Rodolfo Valtuille +2 more
The ANN method is found to be superior to the Smye method for estimation of equilibrated urea, and the results presented here suggest that ANN methods could be useful tools in the analysis of nephrology data.
International Journal of Computer Applications in TechnologyApplication of interval type-2 fuzzy neural networks to predict short-term traffic flow
19 Citations2012Liang Zhao
This paper presents a new prediction model based on interval type-2 fuzzy neural network (IT2FNN) and self-organising learning algorithm that determines its own form by the self- Organising structure identification and parameter optimisation algorithm.
Advances in biochemical engineering, biotechnologyApplication of Knowledge Information Processing Methods to Biochemical Engineering, Biomedical and Bioinformatics Fields
14 Citations2004Taizo Hanai, Hiroyuki Honda
In biochemical and biomedical engineering fields there are a variety of phenomena with many complex chemical reactions, in which many genes and proteins affect transcription or enzyme activity of others, it is difficult to analyze and estimate many of these phenomena using conventional mathematical models.
International Journal of Intelligent Systems Technologies and ApplicationsAdaptive neuro-fuzzy system as a novel approach for predicting post-dialysis urea rebound
13 Citations2011Ahmad Taher Azar
A novel technique for predicting equilibrated urea concentration and PDUR in the form of a Takagi-Sugeno-Kang fuzzy inference system is presented and a comparative analysis suggests that the proposed modelling approach outperforms other traditional urea kinetic models.
International Journal of System Dynamics ApplicationsStatistical Methods and Artificial Neural Networks Techniques in Electromyography
12 Citations2012Ahmad Taher Azar, Valentina Emilia Bălaş
Using the same feature vectors, a neural network classifier has proved that there are significant differences in the masseter muscle activity before and after patients wearing trial denture base.
Artificial Neural Network for accurate prediction of post-dialysis urea rebound
12 Citations2010Ahmad Taher Azar, Valentina Emilia Bălaş +1 more
A supervised Artificial Neural Network is proposed for predicting equilibrated urea concentration taken at 30 min after the end of the hemodialysis (HD) session in order to predict PDUR, and a comparative analysis suggests that the proposed modeling approach outperforms other traditional urea kinetic models (UKM) and the previous work using ANN.
International Journal of Computer Applications in TechnologyUsing neural networks to monitor supply chain behaviour
12 Citations2011Reinaldo Moraga, Luis Rabelo +2 more
A new trend-prediction methodology that recognises behavioural patterns and predicts future performance based on those patterns is proposed that could improve dramatically the capabilities of current dashboard-monitoring systems.
PubMedArtificial neural network for prediction of equilibrated dialysis dose without intradialytic sample.
10 Citations2011Ahmad Taher Azar, Khaled Wahba
It is concluded that the use of the ANN urea estimation yields accurate results when used to calculate ( eq Kt/V) 60, which is similar to the results obtained with the Daugirdas' formula and the ANN.
Journal of NephrologyPredicting intradialytic hypotension from experience, statistical models and artificial neural networks
10 Citations2005Luca Gabutti, Matthias Macháček +2 more
ANNs are superior to nephrologists in predicting IDH episodes; however when supported by a statistical analysis, nephrologyists reach ANNs in their prediction ability.
Medical & Biological Engineering & ComputingDialysate-side urea kinetics. Neural network predicts dialysis dose during dialysis
9 Citations2003Elmer A. Fernández, Rodolfo Valtuille +2 more
A neural network (NN) method is presented for early prediction of the total dialysis dose, expressed as Kt/V, from dialysate-side urea kinetics in haemodialysed patients.
Artificial OrgansComparison of Standard and Artificial Neural Network Estimators of Hemodialysis Adequacy
8 Citations2005Elmer A. Fernández, Rodolfo Valtuille +2 more
The ANN was a reliable and accurate tool for URR monitoring, better than the Smye and the modified URR methods, and the current adequacy limits should be reviewed for both URR and Kt/V.
Neuro-Fuzzy System for Post-Dialysis Urea Rebound Prediction
5 Citations2008Ahmad Taher Azar, Ahmed H. Kandil +3 more
The results are highly promising, and a comparative analysis suggests that the proposed modeling approach outperforms artificial neural networks and other traditional urea kinetic models (UKM).
International Journal of Computer Applications in TechnologyA robust self-tuning fuzzy PI scheme for DTC induction motor drive
4 Citations2011K. Sujatha, K. Vaisakh
Simulation results show that the proposed STPIFLC for DTC IM drive gives remarkably improved performance and high robustness compared with those obtained by the application of a conventional controller (PI).
International Journal of Computer Applications in TechnologyNew improved FLANN approach for dynamic modelling of sensors
2 Citations2011Songling Huang, Kuan sheng Hao +1 more
An improved functional link artificial neural networks (FLANN) is presented and applied to the dynamic modelling for sensors and the simulation and experimental results show that the improved FLANN method has higher convergence rate and more robustness.