SEARCH · Search PubMed
Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
A satisfactory definition of intelligence has never been found, and as a result it means different things to different people. What it is may remain too complex for a succinct definition, but the theory and practice of information handling have clarified what it does for us: it enables us to guess better, and the discovery of unexpected orderliness is the chief means of doing this.
Development of medical knowledge bases is a time-consuming process, and no single medical institution can develop medical knowledge bases covering all areas of medicine. The use of medical knowledge representation standards such as the Arden Syntax is an attempt to enhance the writability and readability of computer-stored knowledge and facilitate transfer and sharing among institutions. A method for the realisation of decision support systems based on knowledge formulated according to the Arden Syntax is presented. An essential tool in this process is a medical logic module (MLM) pre-compiler, translating MLMs into an object-oriented programming language, C++. Advantages of the C++ approach compared with other alternatives are discussed.
The application of artificial intelligence systems is still not widespread in the medical field, however there is an increasing necessity for these to handle the surfeit of information available. One drawback to their implementation is the lack of criteria or guidelines for the evaluation of these systems. This is the primary issue in their acceptability to clinicians, who require them for decision support and therefore need evidence that these systems meet the special safety-critical requirements of the domain. This paper shows evidence that the most prevalent form of intelligent system, neural networks, is generally not being evaluated rigorously regarding classification precision. A taxonomy of the types of evaluation tests that can be carried out, to gauge inherent performance of the outputs of intelligent systems has been assembled, and the results of this presented in a clear and concise form, which should be applicable to all intelligent classifiers for medicine.
Diagnosis of a disease and its treatment are not separate, one-shot activities. Instead they are very often dependent and interleaved over time, mostly due to uncertainty about the underlying disease, uncertainty associated with the response of a patient to the treatment and varying cost of different diagnostic (investigative) and treatment procedures. The framework of Partially observable Markov decision processes (POMDPs) developed and used in operations research, control theory and artificial intelligence communities is particularly suitable for modeling such a complex decision process. In the paper, we show how the POMDP framework could be used to model and solve the problem of the management of patients with ischemic heart disease, and point out modeling advantages of the framework over standard decision formalisms.
Predictive models are often constructed from clinical databases with the goal of eventually helping make better clinical decisions. Evaluating models using decision theory is therefore natural. When constructing a model using statistical and machine learning methods, however, we are often uncertain about precisely how the model will be used. Thus, decision-independent measures of classification performance, such as the area under an ROC curve, are popular. As a complementary method of evaluation, we investigate techniques for deriving the expected utility of a model under uncertainty about the model's utilities. We demonstrate an example of the application of this approach to the evaluation of two models that diagnose coronary artery disease.
Causal probabilistic networks (CPNs) offer new methods by which you can build medical expert systems that can handle all types of medical reasoning within a uniform conceptual framework. Based on the experience from a commercially available system and a couple of large prototype systems, it appears that CPNs are now an attractive alternative to other methods. A CPN is an intensional model of a domain, and it is therefore conceptually much closer to qualitative reasoning systems and to simulation systems than to rule-based or logic-based systems. Recent progress in Bayesian inference in networks has yielded computationally efficient methods. The inference method used follows the fundamental axioms of probability theory, and gives a sound framework for causal and diagnostic (deductive and abductive) reasoning under uncertainty. Experience with the prototypes indicates that it may be possible to use decision theory as a rational approach to test planning and therapy planning. The way in which knowledge is acquired and represented in CPNs makes it easy to express 'deep knowledge' for example in the form of physiological models, and the facilities for learning make it possible to make a smooth transition from expert opinion to statistics based on empirical data.
Outcomes-Based Education (OBE) brought about a significant paradigm shift in the education and training of learners in South Africa. OBE requires a shift from focusing on the teacher input (instruction offerings or syllabuses expressed in terms of content), to focusing on learner outcomes. OBE is moving away from 'transmission' models to constructivistic, learner-centered models that put emphasis on learning as an active process (Nieburh, 1996:30). Teachers act as facilitators and mediators of learning (Norms and Standards, Government Gazette vol 415, no 20844 of 2000). Facilitators are responsible to create the environment that is conducive for learners to construct their own knowledge, skills and values through interaction (Peters, 2000). The first critical cross-field outcome accepted by the South African Qualification Framework (SAQA) is that learners should be able to identify and solve problems by using critical and creative thinking skills. This paper seeks to explore some higher order thinking skills competencies required by OBE from learners such as critical thinking, reflective thinking, creative thinking, dialogic / dialectic thinking, decision making, problem solving and emotional intelligence and their implications in facilitating teaching and learning from the theoretical perspective. The philosophical underpinning of these higher order thinking skills is described to give direction to the study. It is recommended that a study focusing on the assessment of these intellectual concepts be made. The study may be qualitative, quantitative or mixed methods in nature (Creswell 2005).
We present the first evaluation results of a knowledge management and decision support system for Type I diabetes patients' care. Such system, meant to help physicians in therapy revision, relies on the integration of Rule Based Reasoning and Case Based Reasoning, and exploits both explicit and implicit knowledge. Reliability was positively judged by a group of expert diabetologists; an increase in its performances is foreseen as new knowledge will be acquired, through the system usage in clinical practice.
Hycones II is a tool that facilitates the construction of hybrid connectionist expert systems to solve problems in classification. Hycones II provides a hybrid system that integrates frames with three types of neural network: the "combinatorial" neural model (CNM), the "Fuzzy ARTMAP" model, and the "Semantic ART" (SMART) model, a combination of the CNM and Fuzzy ART-MAP. We will compare the ability of these three models to solve diagnostic problems in two medical domains.
There is much interest in rule extraction from neural networks and a plethora of different methods have been proposed for this purpose. We discuss the merits of pedagogical and decompositional approaches to rule extraction from trained neural networks, and show that some currently used methods for binary data comply with a theoretical formalism for extraction of Boolean rules from continuously valued logic. This formalism is extended into a generic methodology for rule extraction from smooth decision surfaces fitted to discrete or quantized continuous variables independently of the analytical structure of the underlying model, and in a manner that is efficient even for high input dimensions. This methodology is then tested with Monks' data, for which exact rules are obtained and to Wisconsin's breast cancer data, where a small number of high-order rules are identified whose discriminatory performance can be directly visualized.
MOTIVATION: Modern mass spectrometry allows the determination of proteomic fingerprints of body fluids like serum, saliva or urine. These measurements can be used in many medical applications in order to diagnose the current state or predict the evolution of a disease. Recent developments in machine learning allow one to exploit such datasets, characterized by small numbers of very high-dimensional samples. RESULTS: We propose a systematic approach based on decision tree ensemble methods, which is used to automatically determine proteomic biomarkers and predictive models. The approach is validated on two datasets of surface-enhanced laser desorption/ionization time of flight measurements, for the diagnosis of rheumatoid arthritis and inflammatory bowel diseases. The results suggest that the methodology can handle a broad class of similar problems.
Red teaming is the process of studying a problem by anticipating adversary behaviors. When done in simulations, the behavior space is divided into two groups; one controlled by the red team which represents the set of adversary behaviors or bad guys, while the other is controlled by the blue team which represents the set of defenders or good guys. Through red teaming, analysts can learn about the future by forward prediction of scenarios. More recently, defense has been looking at evolutionary computation methods in red teaming. The fitness function in these systems is highly stochastic, where a single configuration can result in multiple different outcomes. Operational, tactical and strategic decisions can be made based on the findings of the evolutionary method in use. Therefore, there is an urgent need for understanding the nature of these problems and the role of the stochastic fitness to gain insight into the possible performance of different methods. This paper presents a first attempt at characterizing the search space difficulties in red teaming to shed light on the expected performance of the evolutionary method in stochastic environments.
This paper presents an AI-based approach to automatic sleep stage scoring. The system TBNN (Tree-Based Neural Network) uses a decision-tree generator to provide knowledge that defines the architecture of a backpropagation neural network, including feature selection and initialisation of the weights. The case study reports a successful application to the data from polygraphic all-night sleep of 8 babies aged 6 months. The teaching input was provided by a medical expert in accordance with the rules of Guilleminault and Souquet. The performance of TBNN is compared with 5 other methods and the results are discussed.
Blood transfusion is a medical domain where decision support systems (DSSs) could be very helpful to the physicians but must easily and continuously be maintained. We have developed a knowledge acquisition tool that allows the construction and the maintenance of such a system by the domain expert. The methodology used could be applied to another highly evolutive medical domain. In this paper, we detail our knowledge acquisition tool, its use and the final DSS obtained, which is fully integrated into our hospital information network.
The various grading systems proposed for renal cell carcinomas all suffer from problems related to inter-observer variability. Some of these grading systems are based, either partially or wholly, on morphonuclear criteria, such as nuclear size and shape, anisonucleosis, and chromatin pattern. These criteria can be quantitatively (and thus objectively) evaluated by means of the computer-assisted microscopic analysis of Feulgen-stained nuclei. In the present work, 39 quantitative variables, including two morphometric, 28 chromatin pattern-related, and nine DNA ploidy level-related, were computed for 65 renal cell carcinomas. The actual diagnostic information contributed by each variable was determined by means of multifactorial statistical analysis (discriminant analysis) and two artificial intelligence-related methods of data classification (the decision tree and production rule methods). The results show that quantitative information, as provided by the computer-assisted microscopy of Feulgen-stained nuclei and analysed by means of artificial intelligence-related methods of data classification, contributes significant diagnostic information for the grading of renal cell carcinoma, thus reducing the problem of inter-observer reproducibility.
Top-down induction of decision trees is a simple and powerful method of pattern classification. In a decision tree, each node partitions the available patterns into two or more sets. New nodes are created to handle each of the resulting partitions and the process continues. A node is considered terminal if it satisfies some stopping criteria (for example, purity, i.e., all patterns at the node are from a single class). Decision trees may be univariate, linear multivariate, or nonlinear multivariate depending on whether a single attribute, a linear function of all the attributes, or a nonlinear function of all the attributes is used for the partitioning at each node of the decision tree. Though nonlinear multivariate decision trees are the most powerful, they are more susceptible to the risks of overfitting. In this paper, we propose to perform model selection at each decision node to build omnivariate decision trees. The model selection is done using a novel classifiability measure that captures the possible sources of misclassification with relative ease and is able to accurately reflect the complexity of the subproblem at each node. The proposed approach is fast and does not suffer from as high a computational burden as that incurred by typical model selection algorithms. Empirical results over 26 data sets indicate that our approach is faster and achieves better classification accuracy compared to statistical model select algorithms.
We address the problem of filtering medical news articles for targeted audiences. The approach is based on terms and one of the difficulties is extracting a feature set appropriate for the domain. This paper addresses the medical news-filtering problem using a machine learning approach. We describe the application of two supervised machine learning techniques, Decision Trees and Naïve Bayes, to automatically construct classifiers on the basis of a training set, in which news articles have been pre-classified by a medical expert and four other human readers. The goal is to classify the news articles into three groups: non-medical, medical intended for experts, and medical intended for other readers. While the general accuracy of the machine learning approach is around 78%, the accuracy of distinguishing non-medical articles from medical ones is shown to be 92%.
People use arguments to justify their claims. Computer systems use explanations to justify their conclusions. We are developing WOZ, an explanation framework that justifies the conclusions of a clinical decision-support system. WOZ's central component is the explanation strategy that decides what information justifies a claim. The strategy uses Toulmin's argument structure to define pieces of information and to orchestrate their presentation. WOZ uses explicit models that abstract the core aspects of the framework such as the explanation strategy. In this paper, we present the use of arguments, the modeling of explanations, and the explanation process used in WOZ. WOZ exploits the wealth of naturally occurring arguments, and thus can generate convincing medical explanations.