Detecting Plasma Leakage in Patients with DHF

Detecting Plasma Leakage in Patients with DHFCHAPTER 1 foundingDengue disease is one of the most rapidly spreading mosquito-borne viral disease in tropical and sub-tropical regions around the world.Dengue has become a study international public health concern. The incidence of dengue has swelled dramatically around the world in recent decades. Over 2.5 gazillion people over 40% of the worlds population ar now at risk from dengue. WHO currently estimates there whitethorn be 50 blow million dengue infections worldwide e very(prenominal) year.Dengue is transmitted to world by the bite of Aedes mosquitoes. According to WHO (2014), Dengue causes a unsafe flu-like illness, and sometimes a potentially lethal complication called dengue haemorrhagic febricity. About 2.5% of those that ar infected by dengue break-dance since dengue has neither preaching nor vaccination.Plasma leakage is the major cause of deathrate and morbidity in patients with dengue hemorrhagic febrility. So t hat too soon cognition of plasm leakage and prompt initiation of appropriate treatment atomic human activity 18 vital. There atomic tot up 18 only few researches which are done for germ plasm leakage sensing in patients with DHF.Dengue virus infections may be asymptomatic or may lead to undifferentiated pyrexia, dengue fever (DF) or Dengue haemorrhagic fever (DHF) with plasma leakage that may lead to Dengue shock syndrome (DSS).DF is generally an acute febrile illness, with unvoiced headache, myalgia, arthralgia and rashes. Leucopenia and thrombocytopenia may also be observed. Although DF may be benign, it could be an incapacitating disease with severe headache, muscle and joint and bone pains. at times unusual haemorrhage such as gastroin tasteinal bleeding, hypermenorrhea and great epistaxis may occur.Undifferentiated fever and classical dengue fever elicit be managed as any other viral fever with symptomatic treatment. However, often it is difficult to differentiate DF from DHF in the early level (febrile variety) of the illness.DHF is characterized by the acute onset of high fever and is associated with signs and symptoms similar to DF in the early febrile phase. Plasma leakage is the hallmark of DHF which occurs soon afterwards the end of the febrile phase. There is a tendency to develop DSS cod to plasma leakage. Therefore suspected DF and DHF patients should be closely monitored to identify patients with DHF.The point and the rate of plasma leakage in DHF lav vary. It can be minimal in some patients while in others it can be very significant. The leak usually starts slowly, improvers gradually, slows down and then ceases altogether at the end of leakage phase (usually within 48 hours from the onset).(Ministry of Health, 2012)1.1 Description of the explore count onThe main purpose of this research study was to design a remains to detect the plasma leakage in patients with DHF by analyzing patients aesculapian checkup records .Fur ther, by exploitation this system doctors can intervene early treatment of shock.In recent years machine instruction methods direct been widely use in health check diagnosis. Medical diagnosis is one of major paradox in medical application. Several research groups are workings world wide on the development of flighty intercommunicates in medical diagnosis. anxious electronic communicates are use to increase the accuracy and objectivity of medical diagnosis.Detecting plasma leakage is considered as a non-linear problem that turn ins the complex causative relationship between the variables. However, an artificial neural engagement that is suitable for problems of extreme complexity non addressable with ceremonious technologies, either by the conventional computer programming or statistical method.In this research project multilayer feed preliminary neural interlock was used to train and runnel medical records of patients with DHF and DF. The trained network used to test more records of DHF patients to probe the network performance and in order to make system concrete to use in a real time hospital setting. The diagnostic performance of the proposed network is validated with Receiver Operating Characteristics (ROC) analysis to assess the sensitivity and specificity.1.2 Literature Survey1.2.1 Current methods for plasma leakage detection1.2.1.1 HemoconcentrationCurrently, clinical identification of plasma leakage is difficult until DHF develops. The most park method of monitoring leakage relies on identification of haemo-concentration, determined by tracking changes in HCT measurements, with a rise of more than 20% from baseline considered evidence of significant leakage. However, this method can be rather insensitive, especially if the patient is receiving parenteral fluid therapy, and it is also limited by the detail that an individuals baseline value is rarely known.(Ministry of Health, 2012)1.2.1.2 UltrasonographyStudies using ultra sound have demonstrated that pleural effusions, ascites and gall bladder debate oedema are common during the critical phase, and correlate with disease severity. In addition, serial ultrasound studies indicate that subclinical plasma leakage can be detected as days 2 to 3 of fever, and is give away at predicting likely disease progression than other marker of plasma leakage such as HCT measurements. Gallbladder wall oedema appears to infix the development of ascites and effusions, and may therefore be a helpful early predictor of outcome. Thus ultrasonography is a useful monitoring tool, and where available, should be considered in the overall assessment during the febrile phase. However, there are plastered limitations, particularly the lack of defined normal ranges for the parameters of interest, the variability in measurements obtained by different operators, and the lack of specificity of the findings.(Srikiatkhachorn, Krautrachue, Ratanaprakarn, al, 2007)1.2.1.3 white mea t X-RayChest X-ray is recommended to increase the sensitivity of detecting pleural effution. Pleural effusion detected clinically may not be obvious in a Chest X Ray (CXR)-PA, but may be seen only in a CXR chastise lateral decubitus film. (Ministry of Health, 2012)1.2.2 Expert SystemsAn expert system can be divide into two sub-systems the inference engine and the association base. The knowledge base represends facts and rules. The inference engine applies the rules to the known facts to deduce new facts. illation engines can also include explanation and debugging capabilitiesCHAPTER 2 BACKGROUND AND conjecture2.1 Vital Parameters2.1.1 PulseThe pulse is how many times a delicate that our arteries expand and contract in response to the heart. This rate is exactly check to the heartbeat.2.1.2 Pulse Pressure2.2 Neural network2.2.1 Artificial Neural network vs Biological Neural networkAn artificial neural network is a mathematical model or computational model based on biological n eural network. In other words, it is an emulation of biological neural system. An ANN is a network of highly interconnecting processing elements ( nerve cells) operating in parallel. inbred neurons receive signals through synapses located on the dendrites or membrane of the neuron. When the signals authoritative are strong enough (surpass a certain thresh superannuated), the neuron is initiate and emits a signal though the axon. This signal might be sent to another synapse, and might activate other neurons.(Gershenson,2003)2.2.2 Model of Neural cyberspaceArtificial neuron is a highly abstracted model of the indwelling neuron. Inputs of artificial neuron behave like synapse of a biological neuron which are multiplied by weights (strength of the respective signals), and then computed by a mathematical cash in ones chips which is called Transfer function (also known as energizing function) in order to determine the activation of the neuron. The model of a neuron also includes an e xternally applied bias (threshold) that has the effect of lowering or increasing the net input of the activation function.2.2.3 Multilayer Feed forward (MLF) Neural NetworkA MLF neural network consists of neurons that are ordered into layers. The archetypal layer is called the input layer, the last layer is called the return layer, and the layers between are hidden layers. A neural network that has no hidden units is called a Perceptron. However, a perceptron can only represent linear functions, so it isnt powerful enough for the kinds of applications. A multilayer feed forward neural network can represent a very broad set of nonlinear functions. Therefore, it is very useful in practice.2.2.4 Transfer functionThe behaviour of an ANN depends on twain the weights and transfer function that is specified for the units. There are third transfer functions most commonly used for multilayer networks.2.2.5 oversee LearningSupervised learning is an approach to find the input- turnout rela tionship based from the training using a set of information. Fig. 2.6 represents the block diagram of manage learning. Learning system is fed with the input data and generates product, which is then compared with the target to compute the fracture signal by arbitrator. The error is sent to the learning system for come along training until the minimum value of error is generated. (Muhammad Akmal Sapon, 2011)2.2.6 Backpropagation AlgorithmThe backpropagation algorithm is used in feed-forward ANNs. Artificial neurons are organized in layers and send their signals forward, and then the errors are propagated backwards. The network receives inputs by neurons in the input layer, and the output of the network is given by the neurons in the output layer. There may be one or more intermediate hidden layers. The backpropagation algorithm used for supervised learning. The network computes the error that is the difference between output and desired target and the backpropagation algorithm calculate how the error depends on the input, output and weights. The backpropagation technique reduces this error, until the ANN learns the training data.2.2.7 Training the networkCHAPTER 3 METHODOLOGY AND carrying outIn this research project Microsoft Excel 2010 was used to analysis the stash away data and MATLAB R2013a (8.1.0.604), 64-bit(win64) software was used as a tool to run through and to train the Neural Network.3.1 Data CollectionThe records of 10patients with DHF and 6 patients with DF from September 2013 to April 2014which are obtained from centre for clinical Management of Dengue and Dengue Hemorrhagic fever government hospital in Negombo. The data consists of total 1081 instances which 164 instances belonged to the leaking phase and 139 instances belonged to the non-leaking phase. apiece data consists of 10 variables such as heart rate, systolic and diastolic blood pressures, PCV, Temperature and all are coded as numeric values. The patients are both male and fema le between 18 to 60 years old and who have over 50kg weight. These measurements are taken at equally separated time points (hourly) since the patient was admitted to the hospital.3.2 Data PreparationOne of the most in-chief(postnominal) parts in data preparation is to determine the best variables that set up to the decision-making. The data selection step requires some detailed knowledge of the problem domain and the underlying data. Therefore, the selections of the variables are based on the advice of the doctors and also the go off of the literatures. Even though there are quite a number of variables entered into the Observation Chart, only five variables are identified as the authorised variables that contribute to the detection of plasma leakage. They are as follows,3.3 Neural Network TrainingThe training method was supervised training. Input vector contained 490 data for leakage phase and 591for non-leakage phase. The respective target for each was2-element class vector w ith a 1 in the position of the associated leaking or non-leaking. A two-layer feed-forward network with 20 sigmoid hidden neurons was created. The tansig(Tan-Sigmoid) is chosen as the transfer function for both hidden and output layers. The input vectors and target vectors are willy-nilly divided into training, governing body and test sets. From input vector 70% are used for training set,15% are used to validate that the network is generalizing and to pinch training before overfitting, and the last 15% are used as a completely independent test of network generalization. The network was retrained until the network performance approach a satisfactory level (beyond 85%) of supervised training by using different training algorithms and increasing number of hidden neurons.3.4 TestingThe trained neural network saved and it was used to test the new dataset. The new dataset consist of 50 leakage phase and 50 non-leakage phase data. Correct classifications and misclassifications were reco rded.CHAPTER 4 DATA AND ANALYSIS AND RESULTS4.1 military operationPerformance is measured in terms of mean squared error, and shown in log scale below figure 5.1. It rapidly decreased as the network was trained. Performance is shown for each of the training, validation and test sets. The version of the network that did best on the validation set is was after training.This figure does not indicate any major problems with the training. The validation and test thin outs are very similar.If the test curve had increased significantly before the validation curve increased, then it is possible that some over fitting might have occurred.4.2 Confusion MatrixConfusion matrix contains information about effective and predicted classifications done by a classification system for supervised learning system.In confusion matrix, diagonal cells (in green cells) show the number of cases that were decently classified, and the off-diagonal cells (in red cells) show the misclassified cases. The blue cell in the bottom right shows the total percent of correctly classified cases (in green) and the total percent of misclassified cases (in red). In this study, as shown in above figure 5.2, accuracy of training, testing and validation process are 90.9%, 80.9% and 79.0% respectively. Overall accuracy for correct classification is 87.6% and misclassification is 12.4%.Therefore the results show fair good recognition.4.3 Receiver Operating Characteristic (ROC) curvesThe coloured lines (green and blue) in each axis represent the ROC curves for training, testing and validation. The ROC curve is another visualization of quality of the network. It is a plot of the true positive rate (sensitivity) versus the fabricated positive rate (1-specificity) as the threshold is varied. A perfect test shows points in the upper-left corner, with 100% sensitivity and 100% specificity. In this study, the network performs fairly good.