MyMedR

Displaying publications 1 - 20 of 418 in total

Abstract:

Sort:

Application of autonomous neural network systems to medical pattern classification tasks

Lim CP, Harrison RF, Kennedy RL

Artif Intell Med, 1997 Nov;11(3):215-39.
PMID: 9413607

This paper presents a study of the application of autonomously learning multiple neural network systems to medical pattern classification tasks. In our earlier work, a hybrid neural network architecture has been developed for on-line learning and probability estimation tasks. The network has been shown to be capable of asymptotically achieving the Bayes optimal classification rates, on-line, in a number of benchmark classification experiments. In the context of pattern classification, however, the concept of multiple classifier systems has been proposed to improve the performance of a single classifier. Thus, three decision combination algorithms have been implemented to produce a multiple neural network classifier system. Here the applicability of the system is assessed using patient records in two medical domains. The first task is the prognosis of patients admitted to coronary care units; whereas the second is the prediction of survival in trauma patients. The results are compared with those from logistic regression models, and implications of the system as a useful clinical diagnostic tool are discussed.

Matched MeSH terms: Neural Networks (Computer)*
Use of artificial neural networks to predict drug dissolution profiles and evaluation of network performance using similarity factor

Peh KK, Lim CP, Quek SS, Khoh KH

Pharm Res, 2000 Nov;17(11):1384-8.
PMID: 11205731

PURPOSE: To use artificial neural networks for predicting dissolution profiles of matrix-controlled release theophylline pellet preparation, and to evaluate the network performance by comparing the predicted dissolution profiles with those obtained from physical experiments using similarity factor.
METHODS: The Multi-Layered Perceptron (MLP) neural network was used to predict the dissolution profiles of theophylline pellets containing different ratios of microcrystalline cellulose (MCC) and glyceryl monostearate (GMS). The concepts of leave-one-out as well as a time-point by time-point estimation basis were used to predict the rate of drug release for each matrix ratio. All the data were used for training, except for one set which was selected to compare with the predicted output. The closeness between the predicted and the reference dissolution profiles was investigated using similarity factor (f2).
RESULTS: The f2 values were all above 60, indicating that the predicted dissolution profiles were closely similar to the dissolution profiles obtained from physical experiments.
CONCLUSION: The MLP network could be used as a model for predicting the dissolution profiles of matrix-controlled release theophylline pellet preparation in product development.

Matched MeSH terms: Neural Networks (Computer)*
Theoretically-derived molecular descriptors important in human intestinal absorption

Agatonovic-Kustrin S, Beresford R, Yusof AP

J Pharm Biomed Anal, 2001 May;25(2):227-37.
PMID: 11275432

A quantitative structure-human intestinal absorption relationship was developed using artificial neural network (ANN) modeling. A set of 86 drug compounds and their experimentally-derived intestinal absorption values used in this study was gathered from the literature and a total of 57 global molecular descriptors, including constitutional, topological, chemical, geometrical and quantum chemical descriptors, calculated for each compound. A supervised network with radial basis transfer function was used to correlate calculated molecular descriptors with experimentally-derived measures of human intestinal absorption. A genetic algorithm was then used to select important molecular descriptors. Intestinal absorption values (IA%) were used as the ANN's output and calculated molecular descriptors as the inputs. The best genetic neural network (GNN) model with 15 input descriptors was chosen, and the significance of the selected descriptors for intestinal absorption examined. Results obtained with the model that was developed indicate that lipophilicity, conformational stability and inter-molecular interactions (polarity, and hydrogen bonding) have the largest impact on intestinal absorption.
Role of genetic algorithms and artificial neural networks in predicting the phase behavior of colloidal delivery systems

Agatonovic-Kustrin S, Alany RG

Pharm Res, 2001 Jul;18(7):1049-55.
PMID: 11496944

PURPOSE: A genetic neural network (GNN) model was developed to predict the phase behavior of microemulsion (ME), lamellar liquid crystal (LC), and coarse emulsion forming systems (W/O EM and O/W EM) depending on the content of separate components in the system and cosurfactant nature.
METHOD: Eight pseudoternary phase triangles, containing ethyl oleate as the oil component and a mixture of two nonionic surfactants and n-alcohol or 1,2-alkanediol as a cosurfactant, were constructed and used for training, testing, and validation purposes. A total of 21 molecular descriptors were calculated for each cosurfactant. A genetic algorithm was used to select important molecular descriptors, and a supervised artificial neural network with two hidden layers was used to correlate selected descriptors and the weight ratio of components in the system with the observed phase behavior.
RESULTS: The results proved the dominant role of the chemical composition, hydrophile-lipophile balance, length of hydrocarbon chain, molecular volume, and hydrocarbon volume of cosurfactant. The best GNN model, with 14 inputs and two hidden layers with 14 and 9 neurons, predicted the phase behavior for a new set of cosurfactants with 82.2% accuracy for ME, 87.5% for LC, 83.3% for the O/W EM, and 91.5% for the W/O EM region.
CONCLUSIONS: This type of methodology can be applied in the evaluation of the cosurfactants for pharmaceutical formulations to minimize experimental effort.

Matched MeSH terms: Neural Networks (Computer)*
ANN modeling of the penetration across a polydimethylsiloxane membrane from theoretically derived molecular descriptors

Agatonovic-Kustrin S, Beresford R, Yusof AP

J Pharm Biomed Anal, 2001 Sep;26(2):241-54.
PMID: 11470201

A quantitative structure-permeability relationship was developed using Artificial Neural Network (ANN) modeling to study penetration across a polydimethylsiloxane membrane. A set of 254 compounds and their experimentally derived maximum steady state flux values used in this study was gathered from the literature. A total of 42 molecular descriptors were calculated for each compound. A genetic algorithm was used to select important molecular descriptors and supervised ANN was used to correlate selected descriptors with the experimentally derived maximum steady-state flux through the polydimethylsiloxane membrane (log J). Calculated molecular descriptors were used as the ANN's inputs and log J as the output. Developed model indicates that molecular shape and size, inter-molecular interactions, hydrogen-bonding capacity of drugs, and conformational stability could be used to predict drug absorption through skin. A 12-descriptor nonlinear computational neural network model has been developed for the estimation of log J values for a data set of 254 drugs. Described model does not require experimental parameters and could potentially provide useful prediction of membrane penetration of new drugs and reduce the need for actual compound synthesis and flux measurements.

Matched MeSH terms: Neural Networks (Computer)*
Application of the artificial neural network in quantitative structure-gradient elution retention relationship of phenylthiocarbamyl amino acids derivatives

Tham SY, Agatonovic-Kustrin S

J Pharm Biomed Anal, 2002 May 15;28(3-4):581-90.
PMID: 12008137

Quantitative structure-retention relationship(QSRR) method was used to model reversed-phase high-performance liquid chromatography (RP-HPLC) separation of 18 selected amino acids. Retention data for phenylthiocarbamyl (PTC) amino acids derivatives were obtained using gradient elution on ODS column with mobile phase of varying acetonitrile, acetate buffer and containing 0.5 ml/l of triethylamine (TEA). Molecular structure of each amino acid was encoded with 36 calculated molecular descriptors. The correlation between the molecular descriptors and the retention time of the compounds in the calibration set was established using the genetic neural network method. A genetic algorithm (GA) was used to select important molecular descriptors and supervised artificial neural network (ANN) was used to correlate mobile phase composition and selected descriptors with the experimentally derived retention times. Retention time values were used as the network's output and calculated molecular descriptors and mobile phase composition as the inputs. The best model with five input descriptors was chosen, and the significance of the selected descriptors for amino acid separation was examined. Results confirmed the dominant role of the organic modifier in such chromatographic systems in addition to lipophilicity (log P) and molecular size and shape (topological indices) of investigated solutes.
NETASA: neural network based prediction of solvent accessibility

Ahmad S, Gromiha MM

Bioinformatics, 2002 Jun;18(6):819-24.
PMID: 12075017

MOTIVATION: Prediction of the tertiary structure of a protein from its amino acid sequence is one of the most important problems in molecular biology. The successful prediction of solvent accessibility will be very helpful to achieve this goal. In the present work, we have implemented a server, NETASA for predicting solvent accessibility of amino acids using our newly optimized neural network algorithm. Several new features in the neural network architecture and training method have been introduced, and the network learns faster to provide accuracy values, which are comparable or better than other methods of ASA prediction.
RESULTS: Prediction in two and three state classification systems with several thresholds are provided. Our prediction method achieved the accuracy level upto 90% for training and 88% for test data sets. Three state prediction results provide a maximum 65% accuracy for training and 63% for the test data. Applicability of neural networks for ASA prediction has been confirmed with a larger data set and wider range of state thresholds. Salient differences between a linear and exponential network for ASA prediction have been analysed.
AVAILABILITY: Online predictions are freely available at: http://www.netasa.org. Linux ix86 binaries of the program written for this work may be obtained by email from the corresponding author.

Matched MeSH terms: Neural Networks (Computer)*
A new brain-computer interface design using fuzzy ARTMAP

Palaniappan R, Paramesran R, Nishida S, Saiwaki N

IEEE Trans Neural Syst Rehabil Eng, 2002 Sep;10(3):140-8.
PMID: 12503778

This paper proposes a new brain-computer interface (BCI) design using fuzzy ARTMAP (FA) neural network, as well as an application of the design. The objective of this BCI-FA design is to classify the best three of the five available mental tasks for each subject using power spectral density (PSD) values of electroencephalogram (EEG) signals. These PSD values are extracted using the Wiener-Khinchine and autoregressive methods. Ten experiments employing different triplets of mental tasks are studied for each subject. The findings show that the average BCI-FA outputs for four subjects gave less than 6% of error using the best triplets of mental tasks identified from the classification performances of FA. This implies that the BCI-FA can be successfully used with a tri-state switching device. As an application, a proposed tri-state Morse code scheme could be utilized to translate the outputs of this BCI-FA design into English letters. In this scheme, the three BCI-FA outputs correspond to a dot and a dash, which are the two basic Morse code alphabets and a space to denote the end (or beginning) of a dot or a dash. The construction of English letters using this tri-state Morse code scheme is determined only by the sequence of mental tasks and is independent of the time duration of each mental task. This is especially useful for constructing letters that are represented as multiple dots or dashes. This combination of BCI-FA design and the tri-state Morse code scheme could be developed as a communication system for paralyzed patients.

Matched MeSH terms: Neural Networks (Computer)*
Fractal characterization of bpn weights evolution

Gunasekaran S, Venkatesh B, Sagar BS

Int J Neural Syst, 2004 Apr;14(2):139-45.
PMID: 15112371

Training methodology of the Back Propagation Network (BPN) is well documented. One aspect of BPN that requires investigation is whether or not the BPN would get trained for a given training data set and architecture. In this paper the behavior of the BPN is analyzed during its training phase considering convergent and divergent training data sets. Evolution of the weights during the training phase was monitored for the purpose of analysis. The evolution of weights was plotted as return map and was characterized by means of fractal dimension. This fractal dimensional analysis of the weight evolution trajectories is used to provide a new insight to understand the behavior of BPN and dynamics in the evolution of weights.

Matched MeSH terms: Neural Networks (Computer)*
Neural network classification of autoregressive features from electroencephalogram signals for brain-computer interface design

Huan NJ, Palaniappan R

J Neural Eng, 2004 Sep;1(3):142-50.
PMID: 15876633

In this paper, we have designed a two-state brain-computer interface (BCI) using neural network (NN) classification of autoregressive (AR) features from electroencephalogram (EEG) signals extracted during mental tasks. The main purpose of the study is to use Keirn and Aunon's data to investigate the performance of different mental task combinations and different AR features for BCI design for individual subjects. In the experimental study, EEG signals from five mental tasks were recorded from four subjects. Different combinations of two mental tasks were studied for each subject. Six different feature extraction methods were used to extract the features from the EEG signals: AR coefficients computed with Burg's algorithm, AR coefficients computed with a least-squares (LS) algorithm and adaptive autoregressive (AAR) coefficients computed with a least-mean-square (LMS) algorithm. All the methods used order six applied to 125 data points and these three methods were repeated with the same data but with segmentation into five segments in increments of 25 data points. The multilayer perceptron NN trained by the back-propagation algorithm (MLP-BP) and linear discriminant analysis (LDA) were used to classify the computed features into different categories that represent the mental tasks. We compared the classification performances among the six different feature extraction methods. The results showed that sixth-order AR coefficients with the LS algorithm without segmentation gave the best performance (93.10%) using MLP-BP and (97.00%) using LDA. The results also showed that the segmentation and AAR methods are not suitable for this set of EEG signals. We conclude that, for different subjects, the best mental task combinations are different and proper selection of mental tasks and feature extraction methods are essential for the BCI design.

Matched MeSH terms: Neural Networks (Computer)*
Novel direct and self-regulating approaches to determine optimum growing multi-experts network structure

Loo CK, Rajeswari M, Rao MV

IEEE Trans Neural Netw, 2004 Nov;15(6):1378-95.
PMID: 15565767

This paper presents two novel approaches to determine optimum growing multi-experts network (GMN) structure. The first method called direct method deals with expertise domain and levels in connection with local experts. The growing neural gas (GNG) algorithm is used to cluster the local experts. The concept of error distribution is used to apportion error among the local experts. After reaching the specified size of the network, redundant experts removal algorithm is invoked to prune the size of the network based on the ranking of the experts. However, GMN is not ergonomic due to too many network control parameters. Therefore, a self-regulating GMN (SGMN) algorithm is proposed. SGMN adopts self-adaptive learning rates for gradient-descent learning rules. In addition, SGMN adopts a more rigorous clustering method called fully self-organized simplified adaptive resonance theory in a modified form. Experimental results show SGMN obtains comparative or even better performance than GMN in four benchmark examples, with reduced sensitivity to learning parameters setting. Moreover, both GMN and SGMN outperform the other neural networks and statistical models. The efficacy of SGMN is further justified in three industrial applications and a control problem. It provides consistent results besides holding out a profound potential and promise for building a novel type of nonlinear model consisting of several local linear models.

Matched MeSH terms: Neural Networks (Computer)*
A hybrid neural network system for pattern classification tasks with missing features

Lim CP, Leong JH, Kuan MM

IEEE Trans Pattern Anal Mach Intell, 2005 Apr;27(4):648-53.
PMID: 15794170

A hybrid neural network comprising Fuzzy ARTMAP and Fuzzy C-Means Clustering is proposed for pattern classification with incomplete training and test data. Two benchmark problems and a real medical pattern classification task are employed to evaluate the effectiveness of the hybrid network. The results are analyzed and compared with those from other methods.

Matched MeSH terms: Neural Networks (Computer)*
A novel dengue fever (DF) and dengue haemorrhagic fever (DHF) analysis using artificial neural network (ANN)

Ibrahim F, Taib MN, Abas WA, Guan CC, Sulaiman S

Comput Methods Programs Biomed, 2005 Sep;79(3):273-81.
PMID: 15925426

Dengue fever (DF) is an acute febrile viral disease frequently presented with headache, bone or joint and muscular pains, and rash. A significant percentage of DF patients develop a more severe form of disease, known as dengue haemorrhagic fever (DHF). DHF is the complication of DF. The main pathophysiology of DHF is the development of plasma leakage from the capillary, resulting in haemoconcentration, ascites, and pleural effusion that may lead to shock following defervescence of fever. Therefore, accurate prediction of the day of defervescence of fever is critical for clinician to decide on patient management strategy. To date, no known literature describes of any attempt to predict the day of defervescence of fever in DF patients. This paper describes a non-invasive prediction system for predicting the day of defervescence of fever in dengue patients using artificial neural network. The developed system bases its prediction solely on the clinical symptoms and signs and uses the multilayer feed-forward neural networks (MFNN). The results show that the proposed system is able to predict the day of defervescence in dengue patients with 90% prediction accuracy.

Matched MeSH terms: Neural Networks (Computer)*
Artificial neural network based epileptic detection using time-domain and frequency-domain features

Srinivasan V, Eswaran C, Sriraam N

J Med Syst, 2005 Dec;29(6):647-60.
PMID: 16235818

Electroencephalogram (EEG) signal plays an important role in the diagnosis of epilepsy. The long-term EEG recordings of an epileptic patient obtained from the ambulatory recording systems contain a large volume of EEG data. Detection of the epileptic activity requires a time consuming analysis of the entire length of the EEG data by an expert. The traditional methods of analysis being tedious, many automated diagnostic systems for epilepsy have emerged in recent years. This paper discusses an automated diagnostic method for epileptic detection using a special type of recurrent neural network known as Elman network. The experiments are carried out by using time-domain as well as frequency-domain features of the EEG signal. Experimental results show that Elman network yields epileptic detection accuracy rates as high as 99.6% with a single input feature which is better than the results obtained by using other types of neural networks with two and more input features.

Matched MeSH terms: Neural Networks (Computer)*
Optimizing the specific surface area of fly ash-based sorbents for flue gas desulfurization

Lee KT, Bhatia S, Mohamed AR, Chu KH

Chemosphere, 2006 Jan;62(1):89-96.
PMID: 15996711

High performance sorbents for flue gas desulfurization can be synthesized by hydration of coal fly ash, calcium sulfate, and calcium oxide. In general, higher desulfurization activity correlates with higher sorbent surface area. Consequently, a major aim in sorbent synthesis is to maximize the sorbent surface area by optimizing the hydration conditions. This work presents an integrated modeling and optimization approach to sorbent synthesis based on statistical experimental design and two artificial intelligence techniques: neural network and genetic algorithm. In the first step of the approach, the main and interactive effects of three hydration variables on sorbent surface area were evaluated using a full factorial design. The hydration variables of interest to this study were hydration time, amount of coal fly ash, and amount of calcium sulfate and the levels investigated were 4-32 h, 5-15 g, and 0-12 g, respectively. In the second step, a neural network was used to model the relationship between the three hydration variables and the sorbent surface area. A genetic algorithm was used in the last step to optimize the input space of the resulting neural network model. According to this integrated modeling and optimization approach, an optimum sorbent surface area of 62.2m(2)g(-1) could be obtained by mixing 13.1g of coal fly ash and 5.5 g of calcium sulfate in a hydration process containing 100ml of water and 5 g of calcium oxide for a fixed hydration time of 10 h.
Neural networks aided stone detection in thick slab MRCP images

Logeswaran R

Med Biol Eng Comput, 2006 Aug;44(8):711-9.
PMID: 16937213

This paper proposes a detection scheme for identifying stones in the biliary tract of the body, which is examined using magnetic resonance cholangiopancreatography (MRCP), a sequence of magnetic resonance imaging targeted at the pancreatobiliary region of the abdomen. The scheme enhances the raw 2D thick slab MRCP images and extracts the biliary structure in the images using a segment-based region-growing approach. Detection of stones is scoped within this extracted structure, by highlighting possible stones. A trained feedforward artificial neural network uses selected features of size and average segment intensity as its input to detect possible stones in MRCP images and eliminate false stone-like objects. The proposed scheme achieved satisfactory results in tests of clinical MRCP thick slab images, indicating potential for implementation in computer-aided diagnosis systems for the liver.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Using neural networks and just nine patient-reportable factors of screen for AMI

Bulgiba AM, Fisher MH

Health Informatics J, 2006 Sep;12(3):213-25.
PMID: 17023409 DOI: 10.1177/1460458206066665

The study investigated the effect of different input selections on the performance of artificial neural networks in screening for acute myocardial infarction (AMI) in Malaysian patients complaining of chest pain. We used hospital data to create neural networks with four input selections and used these to diagnose AMI. A 10-fold cross-validation and committee approach was used. All the neural networks using various input selections outperformed a multiple logistic regression model, although the difference was not statistically significant. The neural networks achieved an area under the ROC curve of 0.792 using nine inputs, whereas multiple logistic regression achieved 0.739 using 64 inputs. Sensitivity levels of over 90 per cent were achieved using low output threshold levels. Specificity levels of over 90 per cent were achieved using threshold levels of 0.4-0.5. Thus neural networks can perform as well as multiple logistic regression models even when using far fewer inputs.

Matched MeSH terms: Neural Networks (Computer)*
Context based error modeling for lossless compression of EEG signals using neural networks

Sriraam N, Eswaran C

J Med Syst, 2006 Dec;30(6):439-48.
PMID: 17233156

Two-stage lossless data compression methods involving predictors and encoders are well known. This paper discusses the application of context based error modeling techniques for neural network predictors used for the compression of EEG signals. Error modeling improves the performance of a compression algorithm by removing the statistical redundancy that exists among the error signals after the prediction stage. In this paper experiments are carried out by using human EEG signals recorded under various physiological conditions to evaluate the effect of context based error modeling in the EEG compression. It is found that the compression efficiency of the neural network based predictive techniques is significantly improved by using the error modeling schemes. It is shown that the bits per sample required for EEG compression with error modeling and entropy coding lie in the range of 2.92 to 6.62 which indicates a saving of 0.3 to 0.7 bits compared to the compression scheme without error modeling.

Matched MeSH terms: Neural Networks (Computer)*
Neural network modeling of the kinetics of SO2 removal by fly ash-based sorbent

Raymond-Ooi EH, Lee KT, Mohamed AR, Chu KH

J Environ Sci Health A Tox Hazard Subst Environ Eng, 2006;41(2):195-210.
PMID: 16423725

The mechanistic modeling of the sulfation reaction between fly ash-based sorbent and SO2 is a challenging task due to a variety reasons including the complexity of the reaction itself and the inability to measure some of the key parameters of the reaction. In this work, the possibility of modeling the sulfation reaction kinetics using a purely data-driven neural network was investigated. Experiments on SO2 removal by a sorbent prepared from coal fly ash/CaO/CaSO4 were conducted using a fixed bed reactor to generate a database to train and validate the neural network model. Extensive SO2 removal data points were obtained by varying three process variables, namely, SO2 inlet concentration (500-2000 mg/L), reaction temperature (60-80 degreesC), and relative humidity (50-70%), as a function of reaction time (0-60 min). Modeling results show that the neural network can provide excellent fits to the SO2 removal data after considerable training and can be successfully used to predict the extent of SO2 removal as a function of time even when the process variables are outside the training domain. From a modeling standpoint, the suitably trained and validated neural network with excellent interpolation and extrapolation properties could have immediate practical benefits in the absence of a theoretical model.
Fulltext Diagnosing angina using a simple neural network architecture

Bulgiba, A.M.

JUMMEC, 2006;9(1):39-43.
MyJurnal

The aim of the study was to research the use of a simple neural network in diagnosing angina in patients complaining of chest pain. A total of 887 records were extracted from the electronic medical record system (EMR) in Selayang Hospital, Malaysia. Simple neural networks (simple perceptrons) were built and trained using a subset of 470 records with and without pre-processing using principal components analysis (PCA). These were subsequently tested on another subset of 417 records. Average sensitivity of 80.75% (95% CI 79.54%, 81.96%), specificity of 41.64% (95% CI 40.13%, 43.15%), PPV of 46.73% (95% CI 45.20%, 48.26%) and NPV of 77.39% (95% CI 76.11%, 78.67%) were achieved with the simple perceptron. When PCA pre-processing was used, the perceptrons had a sensitivity of 1.43% (95% CI 1.06%, 1.80%), specificity of 98.32% (95% CI 97.92%, 98.72%), PPV of 32.95% (95% CI 31.51%, 34.39%) and NPV of 61.33% (95% CI 59.84%, 62.82%). These results show that it is possible for a simple neural network to have respectable sensitivity and specificity levels for angina.

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links