Antonio Soriano - Academia.edu (original) (raw)
Papers by Antonio Soriano
Proceedings of the First International Conference on Health Informatics, 2008
In this article we evaluate the work out of artificial neural networks as tools for helping and s... more In this article we evaluate the work out of artificial neural networks as tools for helping and support in the medical diagnosis. In particular we compare the usability of one supervised and two unsupervised neural network architectures for medical diagnoses of lower urinary tract dysfunctions. The purpose is to develop a system that aid urologists in obtaining diagnoses, which will yield improved diagnostic accuracy and lower medical treatment costs. The clinical study has been carried out using the medical registers of patients with dysfunctions in the lower urinary tract. The current system is able to distinguish and classify dysfunctions as areflexia, hyperreflexia, obstruction of the lower urinary tract and patients free from dysfunction.
The model defines three basic units: diagnosis, control, and communication. They are characterize... more The model defines three basic units: diagnosis, control, and communication. They are characterized by defining their functionality and their sets of inputs and outputs. It also specifies patients’ clinical specific input data dissemination and the output’s list of diagnoses, built by fusing DUs’ results. DUs are seen as black boxes, abstracting the heterogeneity of their underlying classification algorithms. Cases in which DUs interaction could reflect relations between disorders are considered.
2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, 2010
Currently, the best way to reduce the mortality of cancer is to detect and treat it in its early ... more Currently, the best way to reduce the mortality of cancer is to detect and treat it in its early stages. Automatic decision support systems, such as automatic diagnosis systems, are very helpful in this task but their performance is constrained by the integrity of the clinical input data. This could be a problem since clinical databases, in which these systems are based on, are commonly built up containing dirty data (empty fields, non-standard or normalized values, etc). This article presents a study of the performance of a clinical decision support system, based on an artificial neural networks, using sets of clean and dirty prostate cancer data. The study shows that is possible to obtain an implementation that allow us to avoid the problems associated to the database's lack of integrity and reach a similar performance using either clean or dirty data.
2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, 2005
The modelling of biological neuroregulated systems is usually complex because of their non-struct... more The modelling of biological neuroregulated systems is usually complex because of their non-structured and distributed architecture. Software agents are a very useful tool to use in the modelling of this kind of systems, allowing increasing the model with characteristics which are not present in the biological equivalent. This work proposes a model of a neural regulator incorporating modularity, flexibility and scalability. The main approach has been the modelling of each neural centre as an agent, incorporating the distributed behaviour of the system. On the other hand, the model can solve local dysfunctions in the centres using extra diagnostic information. The neural regulator of the lower urinary tract has been implemented as an example. We have developed several experiments adding artificial dysfunctions to the model and comparing the results with a normal functioning of the model.
2006 1st Bio-Inspired Models of Network, Information and Computing Systems, 2006
In this article we propose the development of a tool for helping in the medical diagnosis using n... more In this article we propose the development of a tool for helping in the medical diagnosis using neural networks, in particular the multilayer perceptron. This new tool is meant to help the urologists in obtaining an automatic diagnosis for complex multi-variable systems, and to avoid painful and costly medical treatments. The clinical study has been carried out using the medical registers of patients with dysfunctions in the lower urinary tract. The system is able to distinguish and classify dysfunctions as arreflexive, hyper-reflexive, and effort incontinence. Moreover, it is able to predict whether there is presence of dysfunction or not. The results of the experiments display a high percentage of certainty of about 85 %.
Kybernetes, 2006
PurposeTo provide a formal framework based on the action and reaction model that allows us to cov... more PurposeTo provide a formal framework based on the action and reaction model that allows us to cover the dynamics of multi‐agent systems (MAS) made up of mobile software agents suitable for scalable networks.Design/methodology/approachThis model is based on the operation of the human nervous centers. In the case of systems based on mobile agents, the main problem is the different vision the agents have of the world and the impossibility of being aware of and synchronizing all the influences brought by the different agents acting on it.FindingsThis proposal has been compared with the conventional MAS by solving an extension of the predator‐prey problem. The results show the advantages of mobility, as the size of the problem grows in a distributed system.Practical implicationsAt the present time, the model is being applied in works related to the control of biological systems and also in those related to the network management.Originality/valueFrom this formulation, a set of refinement...
The Scientific World Journal, 2014
The growing demand for physical rehabilitation processes can result in the rising of costs and wa... more The growing demand for physical rehabilitation processes can result in the rising of costs and waiting lists, becoming a threat to healthcare services’ sustainability. Telerehabilitation solutions can help in this issue by discharging patients from points of care while improving their adherence to treatment. Sensing devices are used to collect data so that the physiotherapists can monitor and evaluate the patients’ activity in the scheduled sessions. This paper presents a software platform that aims to meet the needs of the rehabilitation experts and the patients along a physical rehabilitation plan, allowing its use in outpatient scenarios. It is meant to be low-cost and easy-to-use, improving patients and experts experience. We show the satisfactory results already obtained from its use, in terms of the accuracy evaluating the exercises, and the degree of users’ acceptance. We conclude that this platform is suitable and technically feasible to carry out rehabilitation plans outsid...
Lecture Notes in Computer Science, 2004
... 835840, 2004. © Springer-Verlag Berlin Heidelberg 2004 Fuzzy Logic-Based Modeling of the Bio... more ... 835840, 2004. © Springer-Verlag Berlin Heidelberg 2004 Fuzzy Logic-Based Modeling of the Biological Regulator of Blood Glucose José-Luis Sánchez Romero, Francisco-Javier Ferrández Pastor, Antonio Soriano Payá, and Juan-Manuel García Chamizo ...
2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2007
In this paper we analyze the problems in home healthcare communication and we propose an approach... more In this paper we analyze the problems in home healthcare communication and we propose an approach for communication between different technologies implementing a new protocol. We use XML to define the communication frames, stored data and the accessibility. We also propose the ways to access to the information from anywhere using criteria of security, accessibility and the possibility of defining models of actuation before critical situations.
2006 Pervasive Health Conference and Workshops, 2006
Diagnosis is an important process in patient care. A suitable diagnosis helps a physician determi... more Diagnosis is an important process in patient care. A suitable diagnosis helps a physician determine a precise treatment. Physicians also have a tendency to seek collaboration from other colleagues and expert systems for better confidence in their decision. The sources of knowledge can be both human in the form of medical specialist, and artificial in the form of expert systems connected through Internet, thereby producing a network of distributed medical knowledge. A system that combines availability, cooperation and harmonization of all contributions in a diagnosis process will bring more confidence in healthcare for the physicians.
Lecture Notes in Computer Science, 2011
In this article we want to assess the feasibility of using genetic algorithms as classifiers that... more In this article we want to assess the feasibility of using genetic algorithms as classifiers that could be used in clinical decision support systems, for urological diseases diagnosis in our case. The use of artificial neural networks is more common in this field, and we have ...
Advances in Intelligent and Soft Computing, 2010
Currently, the best way to reduce the mortality of cancer is to detect it and treat it in the ear... more Currently, the best way to reduce the mortality of cancer is to detect it and treat it in the earliest stages. Automatic decision support systems are very helpful in this task but their performance is constrained by different factors and sometimes it is difficult to find a method ...
Expert Systems with Applications, 2011
Melanoma is the most deathful of all skin cancers and the number of cases grows every year. The e... more Melanoma is the most deathful of all skin cancers and the number of cases grows every year. The extirpation in early phases implies a high degree of survival so it is fundamental to diagnose it as soon as possible. In this paper we present a clinical decision support system for melanoma diagnosis using as input an image set of the skin lesion to be diagnosed. The system analyses the image sequence to extract the affected area, determinates the characteristics which indicate the degree of damage and, according to them, it makes a decision. Several methods of classification are proposed: a multilayered perceptron, a Bayesian classifier and the algorithm of the K nearest neighbours. These methods work independently and also in combination making a collaborative decision support system. The classification rates obtained are around 87%.
Proceedings of the First International Conference on Health Informatics, 2008
In this article we evaluate the work out of artificial neural networks as tools for helping and s... more In this article we evaluate the work out of artificial neural networks as tools for helping and support in the medical diagnosis. In particular we compare the usability of one supervised and two unsupervised neural network architectures for medical diagnoses of lower urinary tract dysfunctions. The purpose is to develop a system that aid urologists in obtaining diagnoses, which will yield improved diagnostic accuracy and lower medical treatment costs. The clinical study has been carried out using the medical registers of patients with dysfunctions in the lower urinary tract. The current system is able to distinguish and classify dysfunctions as areflexia, hyperreflexia, obstruction of the lower urinary tract and patients free from dysfunction.
The model defines three basic units: diagnosis, control, and communication. They are characterize... more The model defines three basic units: diagnosis, control, and communication. They are characterized by defining their functionality and their sets of inputs and outputs. It also specifies patients’ clinical specific input data dissemination and the output’s list of diagnoses, built by fusing DUs’ results. DUs are seen as black boxes, abstracting the heterogeneity of their underlying classification algorithms. Cases in which DUs interaction could reflect relations between disorders are considered.
2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, 2010
Currently, the best way to reduce the mortality of cancer is to detect and treat it in its early ... more Currently, the best way to reduce the mortality of cancer is to detect and treat it in its early stages. Automatic decision support systems, such as automatic diagnosis systems, are very helpful in this task but their performance is constrained by the integrity of the clinical input data. This could be a problem since clinical databases, in which these systems are based on, are commonly built up containing dirty data (empty fields, non-standard or normalized values, etc). This article presents a study of the performance of a clinical decision support system, based on an artificial neural networks, using sets of clean and dirty prostate cancer data. The study shows that is possible to obtain an implementation that allow us to avoid the problems associated to the database's lack of integrity and reach a similar performance using either clean or dirty data.
2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, 2005
The modelling of biological neuroregulated systems is usually complex because of their non-struct... more The modelling of biological neuroregulated systems is usually complex because of their non-structured and distributed architecture. Software agents are a very useful tool to use in the modelling of this kind of systems, allowing increasing the model with characteristics which are not present in the biological equivalent. This work proposes a model of a neural regulator incorporating modularity, flexibility and scalability. The main approach has been the modelling of each neural centre as an agent, incorporating the distributed behaviour of the system. On the other hand, the model can solve local dysfunctions in the centres using extra diagnostic information. The neural regulator of the lower urinary tract has been implemented as an example. We have developed several experiments adding artificial dysfunctions to the model and comparing the results with a normal functioning of the model.
2006 1st Bio-Inspired Models of Network, Information and Computing Systems, 2006
In this article we propose the development of a tool for helping in the medical diagnosis using n... more In this article we propose the development of a tool for helping in the medical diagnosis using neural networks, in particular the multilayer perceptron. This new tool is meant to help the urologists in obtaining an automatic diagnosis for complex multi-variable systems, and to avoid painful and costly medical treatments. The clinical study has been carried out using the medical registers of patients with dysfunctions in the lower urinary tract. The system is able to distinguish and classify dysfunctions as arreflexive, hyper-reflexive, and effort incontinence. Moreover, it is able to predict whether there is presence of dysfunction or not. The results of the experiments display a high percentage of certainty of about 85 %.
Kybernetes, 2006
PurposeTo provide a formal framework based on the action and reaction model that allows us to cov... more PurposeTo provide a formal framework based on the action and reaction model that allows us to cover the dynamics of multi‐agent systems (MAS) made up of mobile software agents suitable for scalable networks.Design/methodology/approachThis model is based on the operation of the human nervous centers. In the case of systems based on mobile agents, the main problem is the different vision the agents have of the world and the impossibility of being aware of and synchronizing all the influences brought by the different agents acting on it.FindingsThis proposal has been compared with the conventional MAS by solving an extension of the predator‐prey problem. The results show the advantages of mobility, as the size of the problem grows in a distributed system.Practical implicationsAt the present time, the model is being applied in works related to the control of biological systems and also in those related to the network management.Originality/valueFrom this formulation, a set of refinement...
The Scientific World Journal, 2014
The growing demand for physical rehabilitation processes can result in the rising of costs and wa... more The growing demand for physical rehabilitation processes can result in the rising of costs and waiting lists, becoming a threat to healthcare services’ sustainability. Telerehabilitation solutions can help in this issue by discharging patients from points of care while improving their adherence to treatment. Sensing devices are used to collect data so that the physiotherapists can monitor and evaluate the patients’ activity in the scheduled sessions. This paper presents a software platform that aims to meet the needs of the rehabilitation experts and the patients along a physical rehabilitation plan, allowing its use in outpatient scenarios. It is meant to be low-cost and easy-to-use, improving patients and experts experience. We show the satisfactory results already obtained from its use, in terms of the accuracy evaluating the exercises, and the degree of users’ acceptance. We conclude that this platform is suitable and technically feasible to carry out rehabilitation plans outsid...
Lecture Notes in Computer Science, 2004
... 835840, 2004. © Springer-Verlag Berlin Heidelberg 2004 Fuzzy Logic-Based Modeling of the Bio... more ... 835840, 2004. © Springer-Verlag Berlin Heidelberg 2004 Fuzzy Logic-Based Modeling of the Biological Regulator of Blood Glucose José-Luis Sánchez Romero, Francisco-Javier Ferrández Pastor, Antonio Soriano Payá, and Juan-Manuel García Chamizo ...
2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2007
In this paper we analyze the problems in home healthcare communication and we propose an approach... more In this paper we analyze the problems in home healthcare communication and we propose an approach for communication between different technologies implementing a new protocol. We use XML to define the communication frames, stored data and the accessibility. We also propose the ways to access to the information from anywhere using criteria of security, accessibility and the possibility of defining models of actuation before critical situations.
2006 Pervasive Health Conference and Workshops, 2006
Diagnosis is an important process in patient care. A suitable diagnosis helps a physician determi... more Diagnosis is an important process in patient care. A suitable diagnosis helps a physician determine a precise treatment. Physicians also have a tendency to seek collaboration from other colleagues and expert systems for better confidence in their decision. The sources of knowledge can be both human in the form of medical specialist, and artificial in the form of expert systems connected through Internet, thereby producing a network of distributed medical knowledge. A system that combines availability, cooperation and harmonization of all contributions in a diagnosis process will bring more confidence in healthcare for the physicians.
Lecture Notes in Computer Science, 2011
In this article we want to assess the feasibility of using genetic algorithms as classifiers that... more In this article we want to assess the feasibility of using genetic algorithms as classifiers that could be used in clinical decision support systems, for urological diseases diagnosis in our case. The use of artificial neural networks is more common in this field, and we have ...
Advances in Intelligent and Soft Computing, 2010
Currently, the best way to reduce the mortality of cancer is to detect it and treat it in the ear... more Currently, the best way to reduce the mortality of cancer is to detect it and treat it in the earliest stages. Automatic decision support systems are very helpful in this task but their performance is constrained by different factors and sometimes it is difficult to find a method ...
Expert Systems with Applications, 2011
Melanoma is the most deathful of all skin cancers and the number of cases grows every year. The e... more Melanoma is the most deathful of all skin cancers and the number of cases grows every year. The extirpation in early phases implies a high degree of survival so it is fundamental to diagnose it as soon as possible. In this paper we present a clinical decision support system for melanoma diagnosis using as input an image set of the skin lesion to be diagnosed. The system analyses the image sequence to extract the affected area, determinates the characteristics which indicate the degree of damage and, according to them, it makes a decision. Several methods of classification are proposed: a multilayered perceptron, a Bayesian classifier and the algorithm of the K nearest neighbours. These methods work independently and also in combination making a collaborative decision support system. The classification rates obtained are around 87%.