جستجوی مقالات مرتبط با کلیدواژه "شبکه ی عصبی مصنوعی" در نشریات گروه "پزشکی"

Wastewater treatment plants are systems that can contribute to the health of the industry and the environment provided that they function properly. Mathematical and statistical simulators coupled with various models can be used to alleviate the costs of monitoring and managing wastewater treatment systems.

This is a retrospective descriptive- analytical study. Considering the complexity of biological processes along with the advances in data processing methods, algorithms (ANN) and M5 model tree were used in this study in order to make a modelto estimate the effluent COD in the sanitary wastewater treatment plant of one of the country's refineries. ANN and M5 were developed through learning and testing stages based on daily data of five consecutive years (2015-2020). Various statistical indicators such as MSE and R were used to evaluate the models. Ethical considerations were observed in all stages of the study.

In the ANN model with 100 hidden layers, through the training step, the amount of MSE and R respectively decreased and increased, compared to the two modes of 10 and 30 hidden layers. This is why 100 layers were chosen for this model. Also, in the M5 tree model, R-SqOptimal = 0.6147 was calculated by selecting independent data as input, which is significant at the 0.05 level. In other words, with 95% confidence, the developed model is considered sufficiently logical for predicting CODout. The results showed that the ANN model outperformed M5 model tree for predicting effluent COD with a coefficient of determination equal to 0.90 and 0.61, respectively.

Both models have high robustness, reliability and generalizability. Therefore, ANN and M5 model tree data mining techniques can be successfully used for environmental decision-making and estimation of lost data in wastewater treatment plants.

Most heart diseases show symptoms on ECG, but diagnosing heart disease with ECG requires the knowledge and experience of medical specialized. Because these specialists may not always be available, it is necessary to design tools to diagnose heart disease in these situations.

In this paper, a two-stage approach based on artificial neural networks is designed to diagnose heart disease using ECG information.

To design the proposed approach, first ECG information for 861 refers to a number of medical centers in Arak city is collected and and data consulted is proccesed by specialists. Then 154 features from ECG as input variables in proposed approach has been specified. In the first stage of approach, an artificial neural network is designed to detect the status of the ECG in two situation as usable and unusable. Then, in the second stage, using the usable ECG information, an artificial neural network is designed to diagnose the presence or absence of heart disease. Finally, the performance of the two-stage approach is evaluated and its accuracy and precision in determining the status of the ECG as well as the disease status is determined.

Results:

 In the proposed approach, the neural network for the determining of ECG status has an precision of 97.1% and an accuracy of 97.3%, and also the neural network for the diagnosis of heart disease has an precision of 95.8% and an accuracy of 95.4%.

Considering the high effeciency of the proposed approach in the determining of ECG status and also diagnosing heart disease, it is possible to use this approach as a reliable assistant to assist the treatment staff.

Air pollution is one of the most significant environmental problems that has a remarkable impact on the incidence of cardiovascular disease and associated mortality. It is essential to comprehend air pollution effects and the ways of emission and predict the number of patients with acute respiratory problems to eliminate and reduce air pollutants and associated mortality. This study aimed to investigate the relationship between different air pollutants and the number of cardiovascular disease patients in Mashhad.

This study applied a neural network to model and analyze the relationship between CO, NO2, SO2, PM2.5, and PM10 and the number of patients with acute respiratory problems. The inputs were average temperature, humidity, wind direction, and wind speed and the output was the number of people referred per day by gender and age. The data set used included meteorological data from the Iran Meteorological Organization, air pollution data from the Mashhad Meteorological Organization, and the number of daily referrals of heart disease patients to the emergency department of Mashhad.

According to this study, the most effective air pollutants in Mashhad were PM2.5 and PM10, followed by NO2, CO, and SO2, respectively.

Neural networks can be applied in the modeling of the relationship between environmental parameters and cardiovascular disease patients because they have a high ability to model nonlinear phenomena. These models show that the more airborne particles, the more rate of cardiovascular diseases in Mashhad

One of the symptoms of lung cancer, which is one of the deadliest cancers, is the lung nodules. It is very difficult to detect these tiny nodules on CT scans of the lungs with the naked eye. Therefore, intelligent systems or computer-aided detection (CAD) systems can assist a radiologist in detecting, locating, and evaluating the quality of lung nodules. The most important challenge of existing intelligent systems is the balanced improvement of accuracy, sensitivity, specificity, and reduction of false positive rate (FPr), and also the complexity of these systems has reduced the efficiency and speed of execution. Therefore, the purpose of this study was to provide an agile framework and optimize the challenge.

One of the new subfields of artificial intelligence is the deep learning and orientation of CNN networks, which has been widely used in the analysis of medical images in recent years. In this research, an innovative network based on CNN networks of LeNet type is proposed to extract image features as well as image classification. The used dataset is a subset of 7072 image pieces derived from the LIDC-IDRI standard dataset. The size of nodules of these images, which are used to train and validate the network, are 1 to 4 mm.

The training and validation processes of this network were performed with a computer device (configurations 2.4GHz Core i5 processor, 8GB of memory, and Intel Graphics 520) in five hours and eleven minutes and the accuracy, sensitivity, and specificity are 91.1%, 85.3% and 92.8%, respectively.

Based on the standard basis of the proposed model and also the use of valid database images to measure the network and compare with previous works, the results establish a good balance between evaluation criteria, and with faster implementation gain the necessary capability for real time applications.

Distribution of air pollutants in industrial units is one of the issues that always affects the environment and ecosystem of adjacent areas. Air pollution is an inevitable part of modern life, and the knowledge of air pollution existed in the past and must be continued to make policies. The cement manufacturing process produces millions of tons of byproducts each year, including dust, toxic gases and heavy metals, which will pose health and respiratory hazards and environmental pollution. Therefore, awareness of pollutant concentrations can be used as key information in pollution control programs. There are still many activities to complete effective control strategies for the prevention, continuous improvement and application of modern technologies to substantially reduce dust in the cement industry. The amount of dust produced can be significantly reduced using modern technologies such as cyclones, bag filters, and electrostatic filters. There are various types of dust in the cement industry including, raw materials such as limestone, marl, clay, iron ore, mixing dust, dryer outlet dust, furnace outlet dust, clinker dust, gypsum dust, and cement dust. In this study, the purpose of dust is the furnace outlet dust. Air pollution is a very complex process that depends on many factors. Therefore, it is very difficult to predict such data with nonlinear dynamics and to determine how the pollutants are to be dispersed and propagated in the atmosphere, which will also be extremely costly. Then, each section can be modeled using this data and solving the equations involving atmospheric processes in the form of data networks. Air quality modeling can be considered as a suitable tool for predicting future air quality and determining emission control strategies. In recent years, one of the best models that has shown good performance in pattern and control modeling is intelligent systems, which include neural networks. Multilayer perceptron neural networks are a model for information processing made by mimicking biological neural networks such as the human brain. The key element of this model is the new structure of its information processing system, consisting of a large number of elements (neurons) with strong internal communications that work together to solve specific problems. Artificial neural networks by empirical data processing transmit knowledge by the law behind the data into the network structure; this is called learning. Ability to learn is essentially the most important feature of an intelligent system. A system that can learn is more flexible and easier to program, so it is better responsive to new problems and equations. Artificial neural networks have been employed for various purposes such as simulation, pattern recognition, classification, prediction, and optimization in engineering sciences. The ability of these networks to map between input and output information with acceptable error has made this method a useful tool for modeling engineering processes. In the basic state, a neural network consists of three layers, input layer, hidden layer, and output layer. Also, each layer contains a number of neurons. In the neural network, neurons are active (on or 1) and inactive (off or 0) and each wing (synapse or communication between nodes) has a weight. Positive-weighted wings trigger or activate the next inactive node, and negative-weighted edges inactivate or inhibit the next inactive node (if it was active). To calculate the output, each of the previous layer inputs is multiplied by the network weights and summed with the corresponding bias. Sabzevar city is located on the west of Khorasan Razavi province in Mashhad-Tehran highway. This city is bounded by Esfarayen in the north, Neyshabur in the east, Kashmar and Bardeskan in the south, Shahroud city in Semnan province in the west. Based on the latest country divisions, Sabzevar has five Bakhsh including, Markazi, Roudab, Khoshab, Davarzan, and Sheshtamad. Sabzevar Cement Factory is one of the sources of dust emission in southwest of Sabzevar in Roudab Bakhsh. The plant started operating on an area of 150 hectares, with a capacity of 3400 tons per day, with Portland cement type 2, 1-325, and 1-425 from October 2007. The plant also uses Bag filter, Bag house, and electrostatic filters for dust, and allocates an area of 50 hectares to build a green belt to protect the environment. The purpose of this research was to predict the amount of dust from the main chimney (baking furnace of Sabzevar cement plant) using a perceptron neural network model.

In this study, first, the amount of dust emitted from the main chimney of Sabzevar cement plant was studied through field surveying in three seasons in 2017-18 by the Experts of Mashhad Environmental Trust Company (Pak Afarinan Avizheh). All sampling and measurement procedures were in accordance with the requirements of the Iranian Environmental Protection Agency. 180 dust samples were collected and then, compared with Iranian Environmental Protection Agency standards and the US Environmental Protection Agency (EPA). The parameters of output gas velocity parameters, temperature, voltage, fuel, and furnace feed were used as perceptron neural network input. Perceptron neural network with 5 neurons as input in the first layer, 10 neurons in the hidden layer, and 1 neurons in the hidden layer. The Levenberg-Marquardt algorithm was used to train the network, which is one of the most used and fastest optimization algorithms. Perceptron neural network is one of the supervised learning methods. To evaluate this method, the data were divided into two training and test groups. The model was trained on the training data. The model error was estimated on the test data. In order to include all data in both training and test groups, k-fold cross-validation method with k = 5 was used. In this way, the data were divided into 5 sections and at each run, 4 groups were considered as training and 1 groups as testing. The network with the least error over the test data was selected. The amount of dust concentration was estimated based on input parameters with the above mentioned neural network (input, hidden and output three layers) and above method. In order to observe the effect of each of the input parameters on the estimation of dust concentration with the perceptron neural network, all possible scenarios should be considered. Since five input parameters are selected, so 25, there are 32 subsets, which results in 31 cases with the removal of the null set. The perceptron neural network was run with 10 neurons in the hidden layer and one neuron in the output layer on each mode (subset). Thus, all subsets of one-member, two-member, three-member, four-member and five-member problem parameters were investigated. In each case, the number of input layer neurons is equal to the number of selected parameters. For each subset of input parameters a neural network was constructed and the amount of dust was estimated. The subset that had the least error in predicting dust concentration was selected as the influencing parameter. For each subset, 5 models were trained, validated each time, and the model with the least error mean squared on the test data was selected. Correlation coefficients and mean squared error were used to evaluate the accuracy of the model in predicting dust concentration. All implementations were performed in MATLAB software.

The results showed that the perceptron model has a good accuracy in predicting the dust concentration of Sabzevar cement plant. Perceptron neural network model was able to Show the correlation coefficient as much as 0.98168 and 0.98249, and Mean square error as much as 0.709 and 280, respectively in two modes of using all parameters (output gas speed, temperature, voltage, fuel, and furnace feed) and the influential parameter (temperature). This indicates a higher correlation and lower error of the perceptron neural network model in using only the temperature parameter than in the prediction of dust concentration in all parameters.

Achieving environmental pollution standards in the cement industry requires proper design and increased efficiency of dust collecting equipment to reduce dust particles. Nowadays, due to the increasing development of cement factories to produce cement needed in the country as well as the growing importance of environmental considerations in various industries, especially the cement industry, the need for better and more efficient technologies to control pollutants and wastes from cement plants has become more and more prevalent. The cement industry is one of the industries that is always referred to as the pollutant of the environment. Although in recent years the industry has tried to meet the environmental standards required by modernizing its equipment and machinery, it is still one of the most important contributors to air pollution. The results of this study showed that the, this model can be a suitable and fast way to better manage industrial dust concentration and ensure quality monitoring results and reduce costs because of the high capability of perceptron neural network in predicting dust concentration.

Facing difficult situations have happened to all of us. One of these difficult situations is being informed about having a specific disease which can be extremely shocking and as a result, may cause mental illnesses. The purpose of this study was to investigate the effect of artificial neural network on the effect of nurses 'empathy, responsiveness and responsibility on the patients' sense of hospitalization in emergency wards.

This descriptive-correlational study was conducted in January 2020. The statistical population included the patients in the emergency wards of Namazi Hospital of Shiraz. The sample size was calculated using 195 Cochran formula. Samples were selected using available random sampling method. The tool used in this study was a standard questionnaire with a confirmed validity and reliability. Also, the artificial neural networks have been used for data analysis.

The mean scores of patients' evaluation of nurses' empathy were 4.42 out of 5, responsibility was 4.48, responsiveness was 4.44 and patients' sense of calm was 4.52. The normalized significance level of the independent variables on the dependent variable according to the ANN spend was calculated as: Empathy 100, Accountability 68.6 and Accountability 59.5.

In the hospital environment, different behaviors of nurses can have a great impact on the morale of frustrated patients. By creating a sense of empathy in patients with proper and timely responsiveness and good accountability (quality of services), respected nurses can develop a sense of comfort in their patients.

Dust modeling can be considered as an appropriate tool for predicting future industrial dust and identifying pollutant emission control strategies. Perceptron (MLP) and radial base (RBF) neural networks were used as a means for predicting the outflow dust from the main cogeneration of Sabzevar cement factory located in Khorasan Razavi Province. the concentration of dust from the main cement chimney in the study area was measured through field measurements. Then, the parameters of the production line (temperature, speed of gas output, voltage, fuel, raw materials, and time of sampling) were used as input data to the nerve networks to predict the concentration of dust. The values obtained from the implementation of the models were compared with the results of field measurements as a superior model selection. The analysis of figures and statistical parameters showed that the mean squared errors for the two MLP and RBF models were as much as 1.787 and 21.263, respectively, and the correlation coefficients were as much as 0.99693 and 0.95811, respectively, which indicates a lower error and greater correlation between the MLP and RBF model in predicting the concentration of dust. Because of the high ability of perceptron nervous networks to predict dust concentration, this model can be a convenient and fast solution to predict the amount of dust in the industry.

Diagnosis of leukemia is very difficult, therefore, it is necessary to use image processing techniques. The main objective of this study was to provide a system based on intelligent models that could improve the accuracy of the diagnostic system for acute leukemia. The images produced in this study were extracted from the University Degli Studi Dimilan database and processed in the MATlab 2014a software. In this research, Fuzzy-Cmeans method was used in fragmentation and neural network and support vector machine in classification networks. Ethical Considerations: In this study, all principles of research ethics were considered. Feature data were extracted using the original image transfer to RGB, HSV, Lab and Enhanced RGB spaces. The data obtained from the previous step were entered into the SVM network, then the network separated normal data from abnormal data. The results of comparing the output of the proposed method with different educational methods showed the highest mean of accuracy equal to 95.7%. The application of the proposed network in this study was that eliminate the weak points of all the networks in addition to presenting the advantages of these network. Combining the networks improved the accuracy of output up to 98% and considerably reduced the time required for calculations.

Contact lenses are transparent, thin plastic disks that cover the surface of the cornea. Appropriate lens prescription should be performed properly by an expert to provide better visual acuity and reduce side effects. The lens administration is a multi-stage, complex and time-consuming process involving many considerations. The purpose of this study was to develop a decision support system in the field of contact lens prescription. In this fundamental study, data were collected from 127 keratoconus patients referred to the contact lens clinic at Farabi Eye Hospital, Tehran, Iran during the period of March 2013 to July 2014. Five parameters in the contact lens prescribing process were investigated. Parameters were collected as follows. “Lens vertical position”, “vertical movement of the lens during blinking” and “width of the rim” in the fluorescein pattern were obtained by recording videos of the patients while wearing the lens. “Fluorescein dye concentration” under the lens was evaluated by the physician and “patient comfort” was obtained by asking the patient to fill a simple scoring system. Approved and disapproved lenses were judged and recorded based on the decision of an expert contact lens practitioner. The decision support system was designed using artificial neural networks with the mentioned variables as inputs. Approved and disapproved lenses are considered as system outputs. Artificial neural network was developed using MATLAB® software, version 8.3 (Mathworks Inc., Natick, MA, USA). Eighty percent of the data was used to train the support vector machine and the rest of the data (20%) to test the system's performance. Accuracy, sensitivity and specificity, calculated using the confusion matrix, were 91.3%, 89.8% and 92.6% respectively. The results indicate that the designed decision support system could assist contact lens prescription with high precision. According to the results, we conclude that hard contact lens fitness could be evaluated properly using an artificial neural network as a decision support system. The proposed system detected approved and disapproved contact lenses with high accuracy.

A main problem in diabetes is its timely and accurate diagnosis. This study aimed at diagnosing diabetes using data mining methods. The present study is an analytical investigation including 768 individuals with 8 attributes. Artificial neural networks and fuzzy neural networks were used to diagnose the diabetes. To achieve a realaccuracy, the Kfold method was used to divide samples into training and test groups. The mean square errors in multilayer perceptron network (MLP), learning vector quantization and Nero fuzzy networks were 98.6%, 98.2% and 99.6%, respectively. According to the results of this study, , data mining method can be effective in diagnosing diabetes. In this regard, both used methods are useful; however, higher precision was obtained following the use of Neuro-Fuzzy approach.

Although severe brain injury can make people susceptible to mental disorders, there is still debate about traumatic brain injury. The purpose of this study was to compare the power of artificial neural network in predicting post-traumatic mental disorder in mild brain injury patients and logistic regression. For this purpose, in a prospective cohort study, 100 trauma patients referred to the trauma center of Shahid Beheshti Hospital of Kashan during 6 months were compared with 100 healthy people. For modeling, the data were randomly divided into two educational groups (100) and experimental (100 people). The Rock's curve and classification accuracy were used to estimate the predictive power of mental disorder. The results showed that there is a significant difference between the two groups of mild traumatic patients and healthy subjects in terms of mental disorders, and artificial neural network models have better efficiency than logistic regression models. This study showed that in order to predict mental disorder, the diagnostic indices of this factor should be considered at the beginning of the traumatic brain injury patients and then, using the artificial neural network model, predict this factor. The necessity of using this technology in demographic screening is useful in treating patients with trauma and preventing possible problems for such patients.

Uncontrolled health status of drivers, can lead to the death of healthy individuals who are living in their best periods of life in terms of performance and wellness and also it can impose huge financial costs on a country. The purpose of this study was to design an intelligent system using Multilayer perceptron (MLP) and radial basis function (RBF) neural networks in order to diagnose drivers’ health status
In this study, we applied the MLP and RBF networks with some changes in the number of middle layers, neurons, as well as learning algorithms such as Momentum (MOM), Conjugate Gradient (CG), and Levenberg Marquardt (LM) in order to diagnose the health status of the drivers.) Then, the best model was introduced according to the area under receiver operating characteristics (ROC) curve, sensitivity, and precision criteria.
In this study, 20 variables were selected as inputs and two variables that include healthy and unhealthy status were determined as output parameters. MLP and RBF neural networks with LM algorithm have the best performance with 66.7% and 29% precision; 97.2% and 100% sensitivity; 91.1% and 86 % accuracy respectively. The area under ROC curve for the nervous system MLP and RBF estimated 91.02 for MLP and 88.1 for RBF.
According to this study, the MLP neural network model with the LM learning algorithm compared to the RBF neural network can have an important role in helping physicians in order to diagnose drivers’ health status. Furthermore, such a model can be used in centers of occupational medicine to enhance the accuracy and the speed of diagnosis and reduce costs.

The aim of this study is proposing an intelligent model for diagnosis and classification of learning disabilities based on machine learning methods and artificial neural network. Learning disabilities are among the most important and the most complex disabilities in the field of exceptional children's education. Exceptional education is an important area to which computer systems have contributed. Perhaps the first step in the education of exceptional children is the identification and classification of problems that these children face. A lot of research has been carried out regarding the use of machine learning techniques and artificial intelligence in the diagnosis and classification of learning disabilities. Reviewing of related works shows that machine learning techniques and expert systems are helpful to teachers and exceptional education’s specialists. Due to complex nature of and large number of learning disabilities, experts find it difficult to diagnose and classify learning disabilities without the help of computers. Insufficient number of experts raises work pressure and diagnosis delaying. Delaying in learning disabilities diagnosis causes various problems in learning disabilities treatment. The diversity and extent of learning disabilities and insufficient number of experts make an expert system necessary for the diagnosis and classification learning disabilities of children.
In this research firstly, the necessity to develop an expert system for classifying learning disabilities is discussed. Then with reviewing related works, strengths and weaknesses of each model is expressed. Digital signal processing, digital image processing and machine learning are the most cited methods used for learning disabilities classification in previous research. A review of the literature shows that models based on digital signal processing and digital image processing could not be used for this purpose because they are costly and require controlled conditions for analysis of digital signals and digital images. However, models based on digital signal processing and image processing are highly accurate. Models based on machine learning and artificial intelligence methods are also highly accurate. In addition, results show models based on artificial intelligence are less costly than models based on digital signal processing and image processing. Therefore, models based on machine learning methods are more appropriate than models based on digital signal processing and image processing for application systems. Artificial neural network could classify learning disabilities with an accuracy of over 85%.
Results show that by using genetic algorithm for feature selection the accuracy of classification can be improved. In addition, by using fuzzy logic system researchers can extract rules of classification.
A hybrid intelligent model based on artificial intelligence and machine-learning methods using the strengths of previous models is proposed. The proposed model uses genetic algorithm for feature selection from among a set of features that have the highest impact in classification extracting. In the proposed model learning disabilities are classified with an artificial neural network. This model uses a fuzzy logic system to extracts rules of classification intelligently. The proposed model is highly accurate in classification and implementation simplicity. Finally, implementation of proposed model is explained.

The service quality is always one of the managerial concerns to supply customer’s satisfaction. Preparing qualified service needs to exact knowledge about the key factors of service quality and their effectiveness in the level of customer’s satisfaction. So implementing the different methods of measuring service quality could make it more explicit the unknown aspects of this factor effectiveness on the satisfaction. So the aim of this study was to evaluating the health care quality methods with artificial neural network approach.
This study was a descriptive-correlation and an applied research. The statistical population of research consists of customers in hospitals of medical sciences Birjand University with an indefinite number. Referring to Cochran sampling formula a number of 385 individuals were selected using in access approach and validated questionnaires of study distributed among them. To measure the service quality it used the 4 approaches of weighted and un-weighted SERVQL and SERVPRF and the effect of service quality dimensions in each 4 approach were evaluated on the satisfaction. In this study to analyze the data is used of Spss software and the results of four methods to measure service quality using artificial neural networks have been studied.
The results showed that the method of measuring the quality of services achieved the lowest level of error for SERVQUAL 0.18 Weighted number That measure the quality of service in terms of weight SERVQUAL model using artificial neural networks have been more accurate in predicting customer satisfaction.
methods of measuring service quality have different performance in predicting customer’s satisfaction under the scale of measuring service quality. Also the artificial neural networks regarding to implement predicting algorithm, may contain weaker forecast rather than classic statistical methods.

Non-Alcoholic Fatty Liver Disease (NAFLD) is one of the most prevalent liver diseases with several levels of severity. Recently, the FibroScan device has been used as a non-invasive method for measurement of elasticity of the liver and consequently its fattiness. The current study aimed at providing a low-cost and simple method for diagnosing of the disease through the clinical symptoms.
A collection of data obtained from 726 patients was used for conducting this study with each patient having a fatty liver disease with different levels of intensity. The severity of the disease for each patient was measured by FibroScan device along with medical tests and ultrasound monitoring. Then, the artificial neural networks were used for determination of the relationship between the data obtained from the patients and the intensity levels. Finally, by the aid of artificial intelligence techniques, a method is employed for extracting rules from artificial neural networks for representing the relationship between the data.
According to the results obtained from FibroScan device, among the 726 patients, 5 were located in F4 class, 23 in F3 class, 132 in F2class, 151 in F1, and 415 in F0 Class (Healthy people). According to the proposed method, the accuracy of diagnosis for various classes is as follows: 100% for F4 class, 99.31% for F3 class, 93.94% for F2 class, and 80.58% for F1 Class. Accordingly, this method can identify the samples in F4 and F3 classes with an ideal accuracy and the samples in F1 and F2 classes with a good accuracy.
Results in this research indicate that the proposed method can be used for diagnosing NAFLD and identifying its intensity levels with a lower costs and easier accessibility. It extracts the required rules for diagnosing the dieses that can be used by the physicians in their diagnosis.

Warfarin is one of the most common oral anticoagulant, which role is to prevent the clots. The dose of this medicine is very important because changes can be dangerous for patients. Diagnosis is difficult for physicians because increase and decrease in use of warfarin is so dangerous for patients. Identifying the clinical and genetic features involved in determining dose could be useful to predict using data mining techniques. The aim of this paper is to provide a convenient way to select the clinical and genetic features to determine the dose of warfarin using artificial neural networks (ANN) and evaluate it in order to predict the dose patients.
This experimental study, was investigate from April to May 2014 on 552 patients in Tehran Heart Center Hospital (THC) candidates for warfarin anticoagulant therapy within the international normalized ratio (INR) therapeutic target. Factors affecting the dose include clinical characteristics and genetic extracted, and different methods of feature selection based on genetic algorithm and particle swarm optimization (PSO) and evaluation function neural networks in MATLAB (MathWorks, MA, USA), were performed.
Between algorithms used, particle swarm optimization algorithm accuracy was more appropriate, for the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) were 0.0262, 0.1621 and 0.1164, respectively.
In this article, the most important characteristics were identified using methods of feature selection and the stable dose had been predicted based on artificial neural networks. The output is acceptable and with less features, it is possible to achieve the prediction warfarin dose accurately. Since the prescribed dose for the patients is important, the output of the obtained model can be used as a decision support system.

About 10-15 percent of Iranian couples are infertile which is due to different causes determining particular diagnostic and treatment methods. In this study، the model presented is based on basic features and simple tests، helping physicians predict the causes of infertility The data were taken from Sarem hospital infertility data bank by using data mining methods. First، K-means clustering was run; then، support vector machine and artificial neural network classification methods were used to predict the type of infertility، and finally، the results of two classification algorithms were compared. In addition، SPSS Clementine 12. 0 was used to analyze the data and implement the algorithm in modeling part. In k-means clustering، the data were divided into five clusters. In each cluster، one or more causes of infertility were observed. Then، by applying SVM and artificial neural network classification algorithms، the SVM algorithm with a polynomial kernel appeared to have the maximum accuracy. The findings of this study، could contribute to the understanding of the factors responsible for infertility and pave the way for future investigations. These findings can be used in future studies to develop a system for applying this model since by diagnosing the causes of infertility prior to secondary stages and before performing heavy tests، a considerable amount of time and cost will be saved، and physical burden on patient will be decreased.

Diabetes and hypertension are from important non-communicable diseases in the world and their prevalence are very important for health authorities. The objective of this study was to compare the predictive precision of joint logistic regression (LR) and artificial neutral network (ANN) in concurrent diagnosis of diabetes and hypertension. This cross-sectional study was performed on 12000 Iranian people in 2013. The study questionnaire included some items on hypertension and diabetes and their risk factors. A perceptron ANN with two hidden layers was applied to data. The variables in the study were diabetes, hypertension, gender, type of cooking oil, physical activity, family history, age, obesity and passive smokers. To build a joint LR model, and ANN, SAS 9.2 and Matlab software were used. The ROC curve was used to find the higher accuracy model for predicting diabetes and hypertension. The variables of gender, type of cooking oil, physical activity, family history, age, passive smokers and obesity entered to the LR model and ANN. The odds ratio of affliction to both diabetes and hypertension is high in females, user of solid oil, people with no physical activity, with positive family history, age of equal to or higher than 55, passive smokers and obesity. The area under ROC curve for LR model and ANN were 0.78 (p=0.039) and 0.86 (p=0.046) respectively. The best model for concurrent affliction to hypertension and diabetes is ANN which has higher accuracy than the joint LR model.

In the past decades, machine learning algorithms have become a useful tool for data mining within huge amounts of health data to create prediction models. Burn is one of the diseases that predicting of its outcome has high importance. The aim of this study was to survey two widely used machine learning algorithms; neural network and decision tree, and compare them with logistic regression method to predict the outcome of burn patients. In this retrospective observational study, following preprocessing of the data and determining the outcome of patient (live or death), two well-known machine learning algorithms (neural network and decision tree) and logistic regression method were used to create prediction models using data from 4804 burn patients hospitalized in Taleghani Burn Center in Ahvaz during the years 2001-2007. The preprocessing of the data was performed using SPSS (Version16.0), and in the modeling phase, Clementine (Version 12.0) software was used. Moreover, 10-fold cross validation technique was used to validate the model and criteria for evaluating the performance of models were measured and compared. The results showed that the neural network algorithm with accuracy of 97% resulted the most accurate model on the studied data. The decision tree model with 95% accuracy was in the second place and the logistic regression model with an accuracy of 90% was the least accurate. Moreover other evaluating criteria such as sensitivity, specificity, PPV, NPV and AUC showed that performance of the neural network model was better than the others. The current study shows that machine learning algorithms compared with statistical methods create more accurate models. In analyzing the current data, the model created by artificial neural network is more accurate than the other machine learning algorithm, decision tree.Keywords: Data Mining; Machine Learning; Forecasting; Decision Tree; Artificial Neural Network; Burns