Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Bayesian networks”

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.

At least 415 records · Page 23Linked to original sources
PubMed2005

A rapid computational filter for cytochrome P450 1A2 inhibition potential of compound libraries.

QSAR models for a diverse set of compounds for cytochrome P450 1A2 inhibition have been produced using 4 statistical approaches; partial least squares (PLS), multiple linear regression (MLR), classification and regression trees (CART), and bayesian neural networks (BNN). The models complement one another and have identified the following descriptors as important features for CYP1A2 inhibition; lipophilicity, aromaticity, charge, and the HOMO/LUMO energies. Furthermore all models are global and have been used to predict a diverse independent set of compounds. For the first time in the field of QSAR, the kappa index of agreement has comprehensively been used to assess the overall accuracy of the model's predictive power. The models are statistically significant and can be used as a rapid computational filter for cytochrome P450 1A2 inhibition potential of compound libraries.

Bayes Theorem↗
PubMed2006

In silico human and rat Vss quantitative structure-activity relationship models.

We present herein a QSAR tool enabling an entirely in silico prediction of human and rat steady-state volume of distribution (Vss), to be made prior to chemical synthesis, preceding detailed allometric or mechanistic assessment of Vss. Three different statistical methodologies, Bayesian neural networks (BNN), classification and regression trees (CART), and partial least squares (PLS) were employed to model human (N=199) and rat (N=2086) data sets. The results in prediction of an independent test set show the human model has an r2 of 0.60 and an rms error in prediction of 0.48. The corresponding rat model has an r2 of 0.53 and an rms error in prediction of 0.37, indicating both models could be very useful in the early stages of the drug discovery process. This is the first reported entirely in silico approach to the prediction of rat and human steady-state volume of distribution.

Animals↗
PubMed1998

Can we learn to distinguish between "drug-like" and "nondrug-like" molecules?

We have used a Bayesian neural network to distinguish between drugs and nondrugs. For this purpose, the CMC acts as a surrogate for drug-like molecules while the ACD is a surrogate for nondrug-like molecules. This task is performed by using two different set of 1D and 2D parameters. The 1D parameters contain information about the entire molecule like the molecular weight and the the 2D parameters contain information about specific functional groups within the molecule. Our best results predict correctly on over 90% of the compounds in the CMC while classifying about 10% of the molecules in the ACD as drug-like. Excellent generalization ability is shown by the models in that roughly 80% of the molecules in the MDDR are classified as drug-like. We propose to use the models to design combinatorial libraries. In a computer experiment on generating a drug-like library of size 100 from a set of 10 000 molecules we obtain at least a 3 or 4 order of magnitude improvement over random methods. The neighborhoods defined by our models are not similar to the ones generated by standard Tanimoto similarity calculations. Therefore, new and different information is being generated by our models, and so it can supplement standard diversity approaches to library design.

Bayes Theorem↗
PubMed2002

Modelling patient duration of stay to facilitate resource management of geriatric hospitals.

A fundamental aspect of health care management is the effective allocation of resources. This is of particular importance in geriatric hospitals where elderly patients tend to have more complex needs. Hospital managers would benefit immensely if they had advance knowledge of patient duration of stay in hospital. Managers could assess the costs of patient care and make allowances for these in their budget. In this paper. we tackle this important problem via a model which predicts the duration of stay distribution of patients in hospital. The approach uses phase-type distributions conditioned on a Bayesian belief network.

Aged↗
PubMed2003

BPROMPT: A consensus server for membrane protein prediction.

Protein structure prediction is a cornerstone of bioinformatics research. Membrane proteins require their own prediction methods due to their intrinsically different composition. A variety of tools exist for topology prediction of membrane proteins, many of them available on the Internet. The server described in this paper, BPROMPT (Bayesian PRediction Of Membrane Protein Topology), uses a Bayesian Belief Network to combine the results of other prediction methods, providing a more accurate consensus prediction. Topology predictions with accuracies of 70% for prokaryotes and 53% for eukaryotes were achieved. BPROMPT can be accessed at http://www.jenner.ac.uk/BPROMPT.

Bayes Theorem↗
PubMed2003

Generating neural circuits that implement probabilistic reasoning.

We extend the hypothesis that neuronal populations represent and process analog variables in terms of probability density functions (PDFs). Aided by an intermediate representation of the probability density based on orthogonal functions spanning an underlying low-dimensional function space, it is shown how neural circuits may be generated from Bayesian belief networks. The ideas and the formalism of this PDF approach are illustrated and tested with several elementary examples, and in particular through a problem in which model-driven top-down information flow influences the processing of bottom-up sensory input.

Action Potentials↗
PubMed2004

Recursive noisy OR--a rule for estimating complex probabilistic interactions.

This paper focuses on approaches that address the intractability of knowledge acquisition of conditional probability tables in causal or Bayesian belief networks. We state a rule that we term the "recursive noisy OR" (RNOR) which allows combinations of dependent causes to be entered and later used for estimating the probability of an effect. In the development of this paper, we investigate the axiomatic correctness and semantic meaning of this rule and show that the recursive noisy OR is a generalization of the well-known noisy OR. We introduce the concept of positive causality and demonstrate its utility in axiomatic correctness of the RNOR. We also introduce concepts describing the ways in which dependent causes can work together as being either "synergistic" or "interfering." We provide a formalization to quantify these concepts and show that they are preserved by the RNOR. Finally, we present a method for the determination of Conditional Probability Tables from this causal theory.

Algorithms↗
PubMed2002

Computerized lesion detection on breast ultrasound.

We investigated the use of a radial gradient index (RGI) filtering technique to automatically detect lesions on breast ultrasound. After initial RGI filtering, a sensitivity of 87% at 0.76 false-positive detections per image was obtained on a database of 400 patients (757 images). Next, lesion candidates were segmented from the background by maximizing an average radial gradient (ARD) index for regions grown from the detected points. At an overlap of 0.4 with a radiologist lesion outline, 75% of the lesions were correctly detected. Subsequently, round robin analysis was used to assess the quality of the classification of lesion candidates into actual lesions and false-positives by a Bayesian neural network. The round robin analysis yielded an Az value of 0.84, and an overall performance by case of 94% sensitivity at 0.48 false-positives per image. Use of computerized analysis of breast sonograms may ultimately facilitate the use of sonography in breast cancer screening programs.

Bayes Theorem↗
PubMed1997

Diagnostic distance of high grade prostatic intraepithelial neoplasia from normal prostate and adenocarcinoma.

OBJECTIVE: To develop a distance measure based methodology to support the morphological evaluation of high grade prostatic intraepithelial neoplasia (PIN), a direct precursor of prostate cancer. METHODS: Eight morphological and cellular features were analysed in 20 cases of high grade PIN found in radical prostatectomy specimens from patients with adenocarcinoma. The diagnostic distance was evaluated to measure the extent to which the feature outcomes of the individual high grade PIN cases differed from the expected outcome profile of normal prostate, low and high grade PIN, and cribriform and large acinar adenocarcinoma. The belief value for high grade PIN was evaluated with a Bayesian belief network (BBN). RESULTS: Complete separation existed between the cumulative absolute diagnostic distances of these 20 cases from the prototype feature outcomes of high grade PIN and normal prostate the values for which were < or = 3 (range 0 to 3) and > or = 9 (range 9 to 15), respectively. The distances from low grade PIN (range 3 to 9), cribriform adenocarcinoma (range 2 to 8), and large acinar adenocarcinoma (range 5 to 10) were intermediate and showed overlap in their distribution. When taking into consideration whether the severity of feature changes was increasing or decreasing in comparison with the category prototype outcomes, the cumulative directional diagnostic distances from high grade PIN ranged from -3 to +3. Positive distance values were seen relative to low grade PIN (range +3 to +9) and relative to normal prostate (range +9 to +15). Negative values were found relative to cribriform adenocarcinoma (range -8 to +2). The distance values from large acinar adenocarcinoma ranged from -2 to +4 and partly overlapped with those from the high grade PIN category. A bivariate scattergram derived from both diagnostic distance measures showed excellent separation between the groups' distances. BBN analysis confirmed the morphology based diagnosis. The distance evaluation resulted in 18 cases whose belief value for high grade PIN ranged from 0.60 to 0.87. In the remaining two cases the results of the BBN analysis showed a belief value of 0.50 and 0.57 for low grade PIN and of 0.49 and 0.38 for high grade PIN, respectively. CONCLUSIONS: Distance measure based methodology represents a useful diagnostic decision support tool for the accurate evaluation of high grade PIN.

Adenocarcinoma↗
PubMed2006

Constructing molecular classifiers for the accurate prognosis of lung adenocarcinoma.

PURPOSE: Individualized therapy of lung adenocarcinoma depends on the accurate classification of patients into subgroups of poor and good prognosis, which reflects a different probability of disease recurrence and survival following therapy. However, it is currently impossible to reliably identify specific high-risk patients. Here, we propose a computational model system which accurately predicts the clinical outcome of individual patients based on their gene expression profiles. EXPERIMENTAL DESIGN: Gene signatures were selected using feature selection algorithms random forests, correlation-based feature selection, and gain ratio attribute selection. Prediction models were built using random committee and Bayesian belief networks. The prognostic power of the survival predictors was also evaluated using hierarchical cluster analysis and Kaplan-Meier analysis. RESULTS: The predictive accuracy of an identified 37-gene survival signature is 0.96 as measured by the area under the time-dependent receiver operating curves. The cluster analysis, using the 37-gene signature, aggregates the patient samples into three groups with distinct prognoses (Kaplan-Meier analysis, P < 0.0005, log-rank test). All patients in cluster 1 were in stage I, with N0 lymph node status (no metastasis) and smaller tumor size (T1 or T2). Additionally, a 12-gene signature correctly predicts the stage of 94.2% of patients. CONCLUSIONS: Our results show that the prediction models based on the expression levels of a small number of marker genes could accurately predict patient outcome for individualized therapy of lung adenocarcinoma. Such an individualized treatment may significantly increase survival due to the optimization of treatment procedures and improve lung cancer survival every year through the 5-year checkpoint.

Adenocarcinoma↗
PubMed1999

Subtle morphological and molecular changes in normal-looking epithelium in prostates with prostatic intraepithelial neoplasia or cancer.

BACKGROUND: Prostate cancer develops over an extended period of time. Until recently, the events initiating the process and the developments concomitant with the evolution towards invasive disease were largely unknown. METHODS: Analytical and quantitative methods are applied to provide insights into certain individual molecular events and their effects on the complex multiple feedback system of cellular metabolism and regulation in prostate neoplasia. RESULTS: Prostatic intraepithelial neoplasia (PIN) and prostate cancer (PCa) are associated with or possibly preceded by changes in the chromatin of secretory cell nuclei. The changes are detectable with a Bayesian belief network and quantifiable by computer image analysis in prostatic tissue that still appears histologically normal. In addition, normal-looking prostate epithelium shows some molecular changes similar to those present in the associated preneoplastic and neoplastic lesions. Such changes are also occasionally present in normal prostate glands without PIN and cancer. CONCLUSIONS: The subtle morphological and molecular changes of normal-looking epithelium might be seen as the onset of the development of prostatic neoplasia.

Adenocarcinoma↗
PubMedDate not supplied

Computer-based testing in family practice certification and recertification.

BACKGROUND: The member boards of the American Board of Medical Specialties have agreed to expand the scope of certification to include assessment of medical knowledge, practice-based learning and improvement, patient care, interpersonal and communication skills, systems-based practice, and professionalism. Multiple-choice examinations provide limited ability to assess these dimensions. METHODS: The American Board of Family Practice (ABFP) has developed a computer simulation system to facilitate more comprehensive candidate evaluation. The system consists of a knowledge base, a simulation program to create patient scenarios, an interface for presenting simulations to users, and an administrative database to track candidate performance and interactions with the system. The system uses population distributions for disease states to produce cases and evolves patients in response to candidate interventions, such as pharmacological and nonpharmacological therapies. We use Bayesian belief networks to model patient characteristics and comorbid condition interactions. RESULTS: Simulations have been created for 7 disease states; ultimately simulations will be available for 25 to 30 disease states. Initial testing will take place in regional examination centers but will ultimately use the Internet for convenient access for certification and recertification candidates. CONCLUSION: The ABFP will begin field-testing the system in early 2003 and will include simulations in the certification and recertification examination process in 2004.

Bayes Theorem↗
PubMed1999

Evaluating variable selection methods for diagnosis of myocardial infarction.

This paper evaluates the variable selection performed by several machine-learning techniques on a myocardial infarction data set. The focus of this work is to determine which of 43 input variables are considered relevant for prediction of myocardial infarction. The algorithms investigated were logistic regression (with stepwise, forward, and backward selection), backpropagation for multilayer perceptrons (input relevance determination), Bayesian neural networks (automatic relevance determination), and rough sets. An independent method (self-organizing maps) was then used to evaluate and visualize the different subsets of predictor variables. Results show good agreement on some predictors, but also variability among different methods; only one variable was selected by all models.

Algorithms↗
PubMed1999

Changes in the normal-looking epithelium in prostates with PIN or cancer.

BACKGROUND: In prostatic neoplasia, the time from tumour initiation and progression to invasive carcinoma often begins in men in the fourth and fifth decades of life and extends across decades. Until recently, the events initiating the process and the developments concomitant with the evolution towards invasive disease were largely unknown. METHODS: Quantitative and analytical methods are applied to provide insights into certain individual molecular events and their effects on the complex multiple feedback system of cellular metabolism and regulation in prostate neoplasia. RESULTS: Prostatic intraepithelial neoplasia (PIN) and prostate cancer (PCa) are associated with or possibly preceded by changes in the chromatin of secretory cell nuclei. The changes are detectable with a Bayesian belief network and quantifiable by computer image analysis in prostatic tissue that still appears histologically normal. In addition, normal looking prostate epithelium shows some molecular changes similar to those present in the associated preneoplastic and neoplastic lesions. Such changes are also occasionally present in normal prostate glands without PIN and cancer. CONCLUSIONS: The subtle morphological and molecular changes of normal looking epithelium might be seen as the onset of the development of prostatic neoplasia.

Adenocarcinoma↗
PubMed2003

The effect of sample size and MLP architecture on Bayesian learning for cancer prognosis--a case study.

In this paper we investigate the independent effects of training sample size and multilayer perceptron (MLP) architecture on Bayesian learning to build prognostic models for metastatic breast cancer. We trained two types of Bayesian neural networks on a data set of 1477 metastatic breast cancer patients followed at the Institut Curie using disjoint training sets of sizes k = 50, 100, 200, 300, and 450. The learning performance as measured by an expected loss appeared independent of the two architectures modelling the log hazard function under either proportional or non proportional hazard assumptions, thus indicating that no other sources of nonlinearity besides interactions are present. We found a performance breakdown at k = 50, and no sample size effect for k > or = 100.

Bayes Theorem↗
PubMed1992

Graph-grammar productions for the modeling of medical dilemmas.

We introduce graph-grammar production rules, which can guide physicians to construct models for normative decision making. A physician describes a medical decision problem using standard terminology, and the graph-grammar system matches a graph-manipulation rule to each of the standard terms. With minimal help from the physician, these graph-manipulation rules can construct an appropriate Bayesian probabilistic network. The physician can then assess the necessary probabilities and utilities to arrive at a rational decision. The grammar relies on prototypical forms that we have observed in models of medical dilemmas. We have found graph grammars to be a concise and expressive formalism for describing prototypical forms, and we believe such grammars can greatly facilitate the modeling of medical dilemmas and medical plans.

Bayes Theorem↗
PubMed1992

An evaluation of explanations of probabilistic inference.

Providing explanations of the conclusions of decision-support systems can be viewed as presenting inference results in a manner that enhances the user's insight into how these results were obtained. The ability to explain inferences has been demonstrated to be an important factor in making medical decision-support systems acceptable for clinical use. Although many researchers in artificial intelligence have explored the automatic generation of explanations for decision-support systems based on symbolic reasoning, research in automated explanation of probabilistic results has been limited. We present the results of an an evaluation study of INSITE, a program that explains the reasoning of decision-support systems based on Bayesian belief networks. In the domain of anesthesia, we compared subjects who had access to a belief network with explanations of the inference results, to control subjects who used the same belief network without explanations. We show that, compared to control subjects, the explanation subjects demonstrated greater diagnostic accuracy, were more confident about their conclusions, were more critical of the belief network, and found the presentation of the inference results more clear.

Anesthesia↗
PubMed1993

Automated linkage of free-text descriptions of patients with a practice guideline.

The process of applying a practice guideline to a patient requires a great deal of clinical data. AAPT (Appropriateness-Assessment Processing from Text) is an experimental computer program that can assess the appropriateness of coronary-artery bypass grafting surgery (CABG) in patients with coronary-artery disease (CAD) and chronic stable angina from the admission summaries of those patients. The AAPT architecture combines natural-language processing (NLP) and probabilistic inference. The NLP module identifies single clinical concepts of interest in the free-text document. The probabilistic inference module, a Bayesian belief network, estimates values for variables not specifically mentioned. AAPT produces a patient's summary of CAD that is similar to a manually generated clinical summary. Work is ongoing to improve AAPT and evaluate it as a tool to assist in the dissemination of guidelines and as a tool to encourage adherence to practice guidelines.

Angina Pectoris↗