Showing 4 results for Neural Network
M.a Afshar Kazemi , N Bigdeli , J Manoochehri , Y Jenab ,
Volume 12, Issue 4 (3-2014)
Abstract
Background: Emergency department (ED) is the first place for providing diagnostic and therapeutic services to emergency patients. Due to importance of speed and accuracy in providing services the proper allocation of resources, the department must consider this matter in a particular way. Planning Emergency resources implements regardless of patient overcrowding which occurs at different times. In conclusion the emergency department may faces lack of resources and it results in delay of providing services, a whole mess in functions and decreasing in quality of services. This study is aimed to overcome these problems by suggesting a model for predicting the number of arrival patients at ED.
Materials and Methods: The number of arrival patients is predicted based on the data colleted by counting arrival patients and using the data mining technique and neural network model (Multi-layer Perceptron).
Results: The number of arrival patients during whole days of a week and 24 hours a day were calculated by sorting out 1, 2 and 3 priorities . The highest number of arrival patients counted was for Saturdays and the lowest for Fridays. Holidays and non-holidays` number of arrival patients differ . The number of arrival patients on formal holidays was similar to Fridays. The highest number of arrivals was between 9 am and 11 and also between 20 pm and 23 pm and the lowest arrivals was between 2 am and 7 am.
Conclusion: prediction the number of ED arrival patients can be used for estimating required sources and distributing them appropriately and improving quality of services.
, ,
Volume 14, Issue 2 (8-2015)
Abstract
Background: In the telemedicine process, using digital techniques in disease diagnosis caused to have felt needs of archiving and storing patient information and high bandwidth in data transfer.
Methods: This study aimed at introducing an efficient way of multi-stage compression of mammographic image data based LM algorithm and artificial neural networks. At First, data derived from mammographic images given to multi-layer neural network has achieved the possibility of forming with minimum damage and high degree of compaction in the first layer.
Results: The compression process of the mammography images was implemented using images of 128 women aged 46.41±6.55 yrs with BMI 36.78 ±5.5 from three specialized clinics in Sabzevar. The analysis yielded a mean square error (MSE) of 4.24 with the highest difference ratio of 33.46 and compression ratio of 8: 1in the output of the algorithm. The system performance based on the accurate design of the software was acceptable therefore; it demonstrated high efficiency in practice.
Conclusion: The diagnosis in the discovery stage is highly consistent with the diagnosis in real based on reliability of software output in the compression and release, and considering the fact of mammographic images are not completely degraded during compression; therefore, this system has the capacity to be implemented achieving mammography images in hospitals and justify its application.
Fariba Salahi, Nastaran Farajpour,
Volume 20, Issue 2 (9-2021)
Abstract
Background and Aim: Today we are witnessing tremendous advances in medical data mining. The data, by analyzing and discovering the relationships between them, can lead to algorithms that help us prevent or treat many diseases. Meanwhile, genetic diseases have attracted a large part of the attention of the medical world because the birth of children with genetic disorders imposes a great financial, psychological and emotional burden on society. Therefore, the aim of this study is to present an algorithm as a secondary screening test before performing cell and molecular tests.
Material and Methods: In this study, 1000 cases of pregnant women who were in moderate or high risk group after screening tests were studied. Their clinical information was stored, missing data was deleted, and records were integrated. Then, using Clementine software, data mining and data correlation were performed, and finally a suitable algorithm for diagnosing the disease was performed. Genetic mutations were identified.
Results: By applying five algorithms, neural networks, support vector machine, binary decision tree, multiple decision tree and logistic regression on the data, it was found that the neural network algorithm with 97.522% accuracy has the highest success rate in Diagnosis of genetic-chromosomal diseases before birth.
Conclusion: The use of genetic algorithm as a screening test causes less people to be candidates for costly and dangerous cellular and molecular tests and can be used as a tool to help detect the disease. To be used in the medical world.
Rahele Panjekoobi, Farzad Firouzi Jahantigh,
Volume 20, Issue 4 (12-2021)
Abstract
Background and Aim: As difficulties increase, the level of uncertainty and risk in the supply chain increases. Medicine is a strategic product and is directly related to community health. The aim of this study is to evaluate the risk factors of pharmaceutical supply chain with artificial intelligence methods.
Materials and Methods: By reviewing the texts and interviewed 6 adept experts who had a Master’s degree and Ph.D. and had experience between 7 and 15 years in the field of risk and pharmaceutical supply chain, risk factors were identified. Finally, using multilayered perceptron neural networks and support vector machines with polynomial linear kernel functions and radial base in two low-risk and high-risk classes were classified in Python software.
Results: 22 factors were identified and classified using neural networks in 5 categories: assets, network and transportation, government and market, strategy and supplier. Shift in interest and inflation, Changes in exchange rates, Inflexibility in production and disruption of customer service are the most important risks in the pharmaceutical supply chain, respectively. The results of evaluation criteria showed that the multilayer perceptron model had better performance than the support vector machines with linear, polynomial and radial basis functions.
Conclusion: The results showed that artificial neural networks are able to classify pharmaceutical supply chain risk factors with acceptable accuracy. As a result, classification of risk factors with an accuracy of 97/07% indicates the high ability of multilayer perceptron network in risk assessment of pharmaceutical supply chain.
