Francisco J. Díez

Francisco J. Díez
National University of Distance Education | UNED · Department of Artificial Intelligence

Doctor of Physics

About

72
Publications
15,202
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,431
Citations
Additional affiliations
January 1989 - April 2016
National University of Distance Education
Position
  • Managing Director
January 1989 - April 2016
National University of Distance Education
Position
  • Managing Director

Publications

Publications (72)
Article
Full-text available
Background Breast thermography originated in the 1950s but was later abandoned due to the contradictory results obtained in the following decades. However, advances in infrared technology and image processing algorithms in the twenty-first century led to a renewed interest in thermography. This work aims to provide an updated and objective picture...
Article
Full-text available
Breast cancer is the most common cancer in women. Ultrasound is one of the most used techniques for diagnosis, but an expert in the field is necessary to interpret the test. Computer-aided diagnosis (CAD) systems aim to help physicians during this process. Experts use the Breast Imaging-Reporting and Data System (BI-RADS) to describe tumors accordi...
Article
Full-text available
Cost-effectiveness analysis (CEA) is used increasingly in medicine to determine whether the health benefit of an intervention is worth the economic cost. Discrete event simulation (DES) is playing an increasing role in CEA thanks to several advantages, such as the possibility of modeling time and heterogeneous populations. It is usually implemented...
Article
Full-text available
Personality disorders are psychological ailments with a major negative impact on patients, their families, and society in general, especially those of the dramatic and emotional type. Despite all the research, there is still no consensus on the best way to assess and treat them. Traditional assessment of personality disorders has focused on a limit...
Article
Full-text available
OpenMarkov is an open-source software tool for probabilistic graphical models. It has been developed especially for medicine, but has also been used to build applications in other fields and for tuition, in more than 30 countries. In this paper we explain how to use it as a pedagogical tool to teach the main concepts of Bayesian networks and influe...
Article
Full-text available
Introduction Cost-effectiveness analysis (CEA) is used increasingly in medicine to determine whether the health benefit of an intervention is worth the economic cost. Decision trees, the standard decision modeling technique for non-temporal domains, can only perform CEAs for very small problems. Influence diagrams can model much larger problems, bu...
Article
Full-text available
A sum-product network (SPN) is a probabilistic model, based on a rooted acyclic directed graph, in which terminal nodes represent probability distributions and non-terminal nodes represent convex sums (weighted averages) and products of probability functions. They are closely related to probabilistic graphical models, in particular to Bayesian netw...
Preprint
Full-text available
A sum-product network (SPN) is a probabilistic model, based on a rooted acyclic directed graph, in which terminal nodes represent univariate probability distributions and non-terminal nodes represent convex combinations (weighted sums) and products of probability functions. They are closely related to probabilistic graphical models, in particular t...
Conference Paper
Full-text available
OpenMarkov is a Java open-source tool for creating and evaluating probabilistic graphical models, including Bayesian networks, influence diagrams, and some Markov models. With more than 100,000 lines of code, it offers some features for interactive learning, explanation of reasoning, and cost-effectiveness analysis, which are not available in any o...
Article
Full-text available
Background. Several methods, such as the half-cycle correction and the life-table method, were developed to attenuate the error introduced in Markov models by the discretization of time. Elbasha and Chhatwal have proposed alternative “corrections” based on numerical integration techniques. They present an example whose results suggest that the trap...
Conference Paper
Full-text available
OpenMarkov is an open-source software tool for probabilistic graphical models. It has been de-veloped especially for medicine, but it has also been used for building applications in other fields,in a total of more than 30 countries. In this paper we explain how to use it as a pedagogical toolto teach the main concepts of Bayesian networks, such as...
Article
This paper presents decision analysis networks (DANs) as a new type of probabilistic graphical model. Like influence diagrams (IDs), DANs are much more compact and easier to build than decision trees and can represent conditional independencies. In fact, for every ID there is an equivalent symmetric DAN, but DANs can also represent asymmetric probl...
Conference Paper
Full-text available
Influence diagrams (IDs) are a powerful tool for representing and solving decision problems under uncertainty. The objective of evaluating an ID is to compute the expected utility and an optimal strategy, which consists of a policy for each decision. Every policy is usually represented as a table containing a column for each decision scenario , i.e...
Article
Objectives/hypothesis: To determine the incremental cost-effectiveness of bilateral versus unilateral cochlear implantation for 1-year-old children suffering from bilateral sensorineural severe to profound hearing loss from the perspective of the Spanish public health system. Study design: Cost-utility analysis. Methods: We conducted a general...
Conference Paper
In spite the important advantages of influence diagrams over decision trees, including the possibility of solving much more complex problems, the medical literature still contains around 10 decision trees for each influence diagram. In this paper we analyse the reasons for the low acceptance of influence diagrams in health decision analysis, in con...
Article
Markov influence diagrams (MIDs) are a new type of probabilistic graphical model that extends influence diagrams in the same way that Markov decision trees extend decision trees. They have been designed to build state-transition models, mainly in medicine, and perform cost-effectiveness analyses. Using a causal graph that may contain several variab...
Article
Markov influence diagrams (MIDs) are a new type of probabilistic graphical model that extends influence diagrams in the same way that Markov decision trees extend decision trees. They have been designed to build state-transition models, mainly in medicine, and perform cost-effectiveness analyses. Using a causal graph that may contain several variab...
Article
Full-text available
Background Non-small cell lung cancer (NSCLC) is the most prevalent type of lung cancer and the most difficult to predict. When there are no distant metastases, the optimal therapy depends mainly on whether there are malignant lymph nodes in the mediastinum. Given the vigorous debate among specialists about which tests should be used, our goal was...
Article
Cost-effectiveness analysis (CEA) is used increasingly in medicine to determine whether the health benefit of an intervention is worth the economic cost. Decision trees, the standard decision modeling technique for non-temporal domains, can only perform CEA for very small problems. To develop a method for CEA in problems involving several dozen var...
Article
IntroductionCost-effectiveness analysis (CEA) is increasingly used to inform health policies. Decision trees are the standard method for decision analysis in non-temporal domains. A decision node that is not the root of the tree is said to be embedded.All books on medical decision analysis discuss both CEA and decision trees [1–11], but few explain...
Conference Paper
Severe and profound hearing losses can be treated with cochlear implants (CI). Given that a CI may have up to 150 tunable parameters, adjusting them is a highly complex task. For this reason, we decided to build a decision support system based on a new type of probabilistic graphical model (PGM) that we call tuning networks. Given the results of a...
Article
Full-text available
Spiegelhalter and Lauritzen [15] studied sequential learning in Bayesian networks and proposed three models for the representation of conditional probabilities. A forth model, shown here, assumes that the parameter distribution is given by a product of Gaussian functions and updates them from the _ and _r messages of evidence propagation. We also g...
Conference Paper
In this paper we introduce a new type of probabilistic graphical model, called decision analysis networks (DANs). Like influence diagrams (IDs), DANs are much more compact and easier to build than decision trees, and are able to represent conditional independencies. However, IDs are unable to represent many real-world problems, as they require a to...
Article
Full-text available
ProbModelXML is an XML format for encoding probabilistic graphical models. The main advantages of this format are that it can represent several kinds of models, such as Bayesian networks, Markov networks, influence diagrams, LIMIDs, decision analysis networks, as well as temporal models: dynamic Bayesian networks, MDPs, POMDPs, Markov processes wit...
Article
Algorithms for learning Bayesian networks (BNs) behave as a black box that takes a database as an input and returns a network as the output. In contrast, OpenMarkov, our tool for probabilistic graphical models, includes the option to run the algorithms in a step-by-step fashion, presenting a ranked list of operations (such as adding, removing, or i...
Article
DLIMIDs, which can represent decision problems with partial observability and large horizons, constitute an alternative to POMDPs, or rather, they can be viewed as almost the same type of model with two different types of policies and, consequently, two paradigms of evaluation. In this paper, we describe a Markovian model for carcinoid tumors and d...
Article
One of the objectives of artificial intelligence is to build decision-support models for systems that evolve over time and include several types of uncertainty. Dynamic limited-memory influence diagrams (DLIMIDs) are a new type of model proposed recently for this kind of problems. DLIMIDs are similar to other models in assuming a multi-stage proces...
Article
In the original formulation of influence diagrams (IDs), each model contained exactly one utility node. In 1990, Tatman and Shachtar introduced the possibility of having super value nodes that represent a combination of their parents’ utility functions. They also proposed an arc-reversal algorithm for IDs with super value nodes. In this paper we pr...
Conference Paper
Full-text available
Lung cancer is a very frequent tumor in the developed world and the leading cause of cancer death, with non-small cell lung cancer being the most prevalent type and with most difficult prognosis. In this paper we present a decision support system built for finding the optimal selection of tests and therapy for each patient. The system basically con...
Conference Paper
Full-text available
In this paper we address the problem of explaining the recommendations returned by a Markov decision process (MDP) that is part of an intelligent assistant for operator training. When analyzing the explanations provided by human experts, we observed that they concentrated on the "most relevant variable", i.e., the variable that in the current state...
Article
A potential is a function that maps each configuration of a set of variables onto a real number. In the context of probabilistic graphical models, every family of probability distributions and every utility function is a potential, and the process of inference gives rise to new potentials. In principle, potentials defined on discrete variables migh...
Article
Full-text available
Bayesian networks (BNs) and influence diagrams (IDs) are probabilistic graphical models that are widely used for building diagnosis- and decision-support expert systems. Explanation of both the model and the reasoning is important for debugging these models, alleviating users' reluctance to accept their advice, and using them as tutoring systems. T...
Article
The development of dynamic limited-memory influence diagrams as a framework for representing factorized infinite-horizon partially observable Markov decision processes (POMDPs), the introduction of algorithms for their (approximate) solution, and the application to a dynamic decision problem in clinical oncology. A dynamic limited-memory influence...
Article
Full-text available
The hardest task in knowledge engineering for probabilistic graphical models, such as Bayesian networks and influence diagrams, is obtaining their numerical parameters. Models based on acyclic directed graphs and composed of discrete variables, currently most common in practice, require for every variable a number of parameters that is exponential...
Article
Full-text available
Díez's algorithm for the noisy MAX is very efficient for polytrees, but when the net-work has loops it has to be combined with local conditioning, a suboptimal propagation algorithm. Other algorithms, based on several factorizations of the conditional probability of the noisy MAX, are not as efficient for polytrees, but can be combined with general...
Article
Full-text available
Temporal Nodes Bayesian Networks (TNBNs) and Networks of Probabilistic Events in Discrete Time (NPEDTs) are two different types of Event Bayesian Networks (EBNs). Both are based on the representation of uncertain events, alternatively to Dynamic Bayesian Networks, which deal with real-world dynamic properties. In a previous work, Arroyo-Figueroa an...
Article
Bayesian networks originated as a framework for distributed reasoning. In singly connected networks, there exists an elegant inference algorithm that can be implemented in parallel having a processor for every node. It can be extended to take advantage of the OR-gate, a model of interaction among causes that simplifies knowledge acquisition and evi...
Article
Debugging an expert system is virtually unfeasible without explanation facilities, especially in the case of probabilistic expert systems, whose way of reasoning is completely different from that of human experts. Unfortunately, almost currently available tools for building probabilistic graphical models offer no explanation facility. This paper sh...
Chapter
Most artificial intelligence applications, especially expert systems, have to reason and make decisions based on uncertain data and uncertain models. For this reason, several methods have been proposed for reasoning with different kinds of uncertainty.
Conference Paper
Full-text available
Explanation of reasoning in expert systems is necessary for debugging the knowledge base, for facilitating their acceptance by human users, and for using them as tutoring systems. In∞uence diagrams have proved to be efiective tools for building decision-support systems, but explanation of their reasoning is di-cult, because inference in probabilist...
Conference Paper
Full-text available
In previous work we have introduced dynamic limited-memory influence diagrams (DLIM- IDs) as an extension of LIMIDs aimed at representing infinite-horizon decision processes. If a DLIMID respects the first-order Markov assumption then it can be represented by 2TLIMIDS. Given that the treatment selection algorithm for LIMIDs, called single policy up...
Article
Dynamic limited-memory influence diagrams (DLIMIDs) have been developed as a framework for decision-making under uncertainty over time. We show that DLIMIDs constructed from two- stage temporal LIMIDs can represent infinite- horizon decision processes. Given a treatment strategy supplied by the physician, DLIMIDs may be used as prognostic models. T...
Article
Full-text available
When trying to solve two medical decision prob-lems we have encountered several difficulties: how to represent and operate with decomposable utility functions, how to calibrate our human ex-perts and explain them the "reasoning" of our in-fluence diagrams, and how to deal with partially ordered decisions. This paper describes these dif-ficulties an...
Article
Full-text available
This paper briefly describes the main features of the UNED (Spanish National University for Distance Education) and the course on Probability and Statistics in Medicine. Then it introduces Bayesian networks and influence diagrams, two of the methods taught in this course. Finally, it explains how Elvira, a software package, can help the students to...
Article
Full-text available
Explanation of reasoning is one of the most important abilities an expert system should provide in order to be widely accepted. In fact, since MYCIN, many expert systems have tried to include some explanation capability. This paper reviews the methods developed to date for explanation in heuristic expert systems.
Conference Paper
Full-text available
Temporal Nodes Bayesian Networks (TNBNs) and Networks of Probabilistic Events in Discrete Time (NPEDTs) are two difierent types of Bayesian networks (BNs) for temporal reasoning. Arroyo-Figueroa and Sucar applied TNBNs to an industrial domain: the diagnosis and prediction of the temporal faults that may,occur in the steam generator of a fossil powe...
Conference Paper
The manual development of a Bayesian Network (BN) is considered more an art than a technique, which mostly depends on the interaction between knowledge engineers and human experts. As a consequence, an explanation facility constitutes a very useful tool. The current paper focuses on the process of building Prostanet, a BN designed to help to diagno...
Article
Full-text available
Building probabilistic and decision-theoretic models requires a considerable knowledge engineering effort in which the most daunting task is obtaining the numerical parameters. Authors of Bayesian networks usually combine various sources of information, such as textbooks, statistical reports, databases, and expert judgement. In this paper, we demon...
Article
D¶‡ez's algorithm for the noisy MAX is very e-cient for polytrees, but when the network has loops it has to be combined with local conditioning, a suboptimal propa- gation algorithm. Other algorithms, based on several factorizations of the conditional probability of the noisy MAX, are not as e-cient for polytrees, but can be combined with general p...
Article
Full-text available
Building probabilistic and decision-theoretic models requires a considerable knowledge engineering effort in which the most daunting task is obtaining the numerical parameters. Authors of Bayesian networks usually combine various sources of information, such as textbooks, statistical reports, databases, and expert judgement. In this paper, we demon...
Conference Paper
This paper describes the object oriented (OO) analysis patterns applied in the construction of Carmen, a development environment for graphical probabilistic models (GPMs). Taking inspiration from research carried out in the design pattern specification field, these OO patterns are defined by means of structural and behavioural “meta-level” constra...
Article
The usual methods of applying Bayesian networks to the modeling of temporal processes, such as Dean and Kanazawa’s dynamic Bayesian networks (DBNs), consist in discretizing time and creating an instance of each random variable for each point in time. We present a new approach called network of probabilistic events in discrete time (NPEDT), for temp...
Article
The spread of cancer is a non-deterministic dynamic process. As a consequence, the design of an assistant system for the diagnosis and prognosis of the extent of a cancer should be based on a representation method that deals with both uncertainty and time. The ultimate goal is to know the stage of development of a cancer in a patient before selecti...
Conference Paper
Full-text available
Cancer spread is a non-deterministic dynamic process. As a c onse- quence, the design of an assistant system for the diagnosis and prognosis of the extent of a cancer should be based on a representation method which deals with both un certainty and time. The ultimate goal i s to know the stage of develop- ment reached by a cancer in the patient, pr...
Article
Building probabilistic and decision-analytic models requires a considerable knowledge engineering effort in which obtaining numerical parameters is especially daunting.
Conference Paper
Bayesian networks have proved to be an appropriate tool for medical diagnosis, because uncertain reasoning in this field is based on a combination of causal knowledge and statistical data. However, a condition for the acceptance of a medical expert system is the ability to explain the diagnosis. This is a difficult task, because probabilistic infer...
Article
The usual way of applying Bayesian n etworks to the modelling of temporal processes consists in d iscretizing time a nd creating an instance of each random variable for each point in time. This method leads to large a nd complex networks. We present a new approach called Net of Irreversible Events in Discrete Time (NIEDT), for temporal reasoning in...
Article
Full-text available
La medicina tiene dos propiedades que hacen que los modelos gráficos probabilistas (MGP) encajen en ella como anillo al dedo: el conocimiento causal, correspondiente a los mecanismos patofisiológicos, y las numerosas fuentes de incertidumbre. Por ello, no es de extrañar que la mayor parte de los MGP, desde el principio hasta la actualidad, se hayan...
Article
Full-text available
DIAVAL is an expert system for the diagnosis of heart diseases, including several kinds of data, mainly from echocardiography. The first part of this paper is devoted to the causal probabilistic model which constitutes the knowledge base of the expert system in the form of a Bayesian network, emphasizing the importance of the OR gate. The second pa...
Article
Local conditioning (LC) is an exact algorithm for computing probability in Bayesian networks, developed as an extension of Kim and Pearl's algorithm for singly-connected networks. A list of variables associated to each node guarantees that only the nodes inside a loop are conditioned on the variable which breaks it. The main advantage of this algor...
Article
We propose a knowledge representation architecture organized in three levels—a causal network (containing the domain knowledge), medical strategies and causal reasoning—and expose the fundamentals of a mathematical model for computing probaility through the application of Bayes' theorem in a causal network.
Article
The distinction between canonical and canonoid transformations, introduced by Currie and Saletan (1972), is emphasised through an example, which also shows that the initial condition of their theorem was quite strict. A step forward is taken by reducing the requirement that all quadratic Hamiltonians be canonoid to the requirement that a finite num...
Article
Full-text available
In the last three decades hundreds of Markov mod-els have been built for medical applications, but most of them fall under the paradigm of what we call simple Markov models (SMMs). Markov de-cision processes (MDPs) are much more powerful as a decision analysis tool, but they are ignored in medical decision analysis books and the num-ber of medical...
Article
Full-text available
In this paper we present a new method for performing cost-effectiveness analyses of problems that involve multiple decisions and probabilistic outcomes. This issue has been ignored by most of the literature on medical decision making, and the few proposed solutions are either wrong or unfeasible, except for very small problems. The method proposed...

Network

Cited By