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 397 records · Page 22Linked to original sources
PubMed1999

Inference network-based analyses of the histopathological effects of androgen deprivation on prostate cancer.

The evaluation of prostate cancer histology following hormonal therapy often represents a diagnostic problem for the pathologist. Previous studies have shown that an inference or Bayesian belief network (BBN) offers a descriptive classifier useful for the accurate analysis of morphological changes in individual cases of prostate neoplasia. Three different BBNs were evaluated in 94 cancer foci present in 20 radical prostatectomy (RP) specimens and in the matching biopsies in which the initial diagnosis of prostatic adenocarcinoma was made. Ten RP specimens were from patients treated with total androgen ablation or combination endocrine therapy (CET) before surgery. The first and second BBN allowed the identification with high certainty of the cancer foci present in the biopsies and RP specimens, as well as their Gleason grade, the belief value often being close to 1.0. The results of the second BBN showed a good correspondence between the Gleason grade given in the biopsies and that in the RP specimens, except in the surgical material of the treated patients, in which upgrading was always present. The third BBN showed the existence of three subgroups in treated RP specimens, one with morphological effect, another with poor effect, and the third with the histology of untreated (i.e. unaffected) cancer. In conclusion, an inference network-based analysis allows the characterization of treated prostate cancers according to the degree of histopathological change.

Adenocarcinoma↗
PubMed2005

Prediction of siRNA knockdown efficiency using artificial neural network models.

Selective knockdown of gene expression by short interference RNAs (siRNAs) has allowed rapid validation of gene functions and made possible a high throughput, genome scale approach to interrogate gene function. However, randomly designed siRNAs display different knockdown efficiencies of target genes. Hence, various prediction algorithms based on siRNA functionality have recently been constructed to increase the likelihood of selecting effective siRNAs, thereby reducing the experimental cost. Toward this end, we have trained three Back-propagation and Bayesian neural network models, previously not used in this context, to predict the knockdown efficiencies of 180 experimentally verified siRNAs on their corresponding target genes. Using our input coding based primarily on RNA structure thermodynamic parameters and cross-validation method, we showed that our neural network models outperformed most other methods and are comparable to the best predicting algorithm thus far published. Furthermore, our neural network models correctly classified 74% of all siRNAs into different efficiency categories; with a correlation coefficient of 0.43 and receiver operating characteristic curve score of 0.78, thus highlighting the potential utility of this method to complement other existing siRNA classification and prediction schemes.

Algorithms↗
PubMed2005

Tumour matrilysin expression predicts metastatic potential of stage I (pT1) colon and rectal cancers.

BACKGROUND AND AIMS: Nodal metastases are indisputable determinants of prognosis for colon and rectal cancer. Using classical histological criteria, many attempts to predict nodal metastasis have failed, preventing the adequate management of stage I (pT1) cancer. We investigated the role of tumour matrilysin in predicting metastatic potential, and discuss its potential use in individualising treatment of pT1 colon and rectal cancer. METHODS: The gene signature associated with nodal metastasis was investigated by cDNA array in 24 colon and rectal cancers. We studied 494 colon and rectal cancer patients to identify risk factors for nodal metastasis and evaluated the potential to predict nodal metastasis by either the logistic regression model or the Bayesian neural network model with built-in matrilysin. We then inferred possible causality of nodal metastasis from structural equation modelling. RESULTS: cDNA array revealed that matrilysin was maximally upregulated in the metastasis signature identified. Tumour matrilysin expression emerged as a stage independent risk factor for nodal metastasis, resulting in a similar predictive performance in receiver operating characteristic curve analysis in the two models. A Bayesian approach called automatic relevance determination identified matrilysin as one of the most relevant predictors examined. Structural equation modelling suggested possible direct causality between matrilysin and nodal metastasis. CONCLUSIONS: We have provided evidence that tumour matrilysin expression is a promising biomarker predicting nodal metastasis of colon and rectal cancer. Analysis of tumour matrilysin expression would help clinicians achieve the goal of individualised cancer treatment based on the metastatic potential of pT1 colon and rectal cancer.

Adenocarcinoma↗
PubMedDate not supplied

Symbolic, neural, and Bayesian machine learning models for predicting carcinogenicity of chemical compounds.

Experimental programs have been underway for several years to determine the environmental effects of chemical compounds, mixtures, and the like. Among these programs is the National Toxicology Program (NTP) on rodent carcinogenicity. Because these experiments are costly and time-consuming, the rate at which test articles (i.e., chemicals) can be tested is limited. The ability to predict the outcome of the analysis at various points in the process would facilitate informed decisions about the allocation of testing resources. To assist human experts in organizing an empirical testing regime, and to try to shed light on mechanisms of toxicity, we constructed toxicity models using various machine learning and data mining methods, both existing and those of our own devising. These models took the form of decision trees, rule sets, neural networks, rules extracted from trained neural networks, and Bayesian classifiers. As a training set, we used recent results from rodent carcinogenicity bioassays conducted by the NTP on 226 test articles. We performed 10-way cross-validation on each of our models to approximate their expected error rates on unseen data. The data set consists of physical-chemical parameters of test articles, alerting chemical substructures, salmonella mutagenicity assay results, subchronic histopathology data, and information on route, strain, and sex/species for 744 individual experiments. These results contribute to the ongoing process of evaluating and interpreting the data collected from chemical toxicity studies.

Animals↗
PubMed2006

Massive-training artificial neural network (MTANN) for reduction of false positives in computer-aided detection of polyps: Suppression of rectal tubes.

One of the limitations of the current computer-aided detection (CAD) of polyps in CT colonography (CTC) is a relatively large number of false-positive (FP) detections. Rectal tubes (RTs) are one of the typical sources of FPs because a portion of a RT, especially a portion of a bulbous tip, often exhibits a cap-like shape that closely mimics the appearance of a small polyp. Radiologists can easily recognize and dismiss RT-induced FPs; thus, they may lose their confidence in CAD as an effective tool if the CAD scheme generates such "obvious" FPs due to RTs consistently. In addition, RT-induced FPs may distract radiologists from less common true positives in the rectum. Therefore, removal RT-induced FPs as well as other types of FPs is desirable while maintaining a high sensitivity in the detection of polyps. We developed a three-dimensional (3D) massive-training artificial neural network (MTANN) for distinction between polyps and RTs in 3D CTC volumetric data. The 3D MTANN is a supervised volume-processing technique which is trained with input CTC volumes and the corresponding "teaching" volumes. The teaching volume for a polyp contains a 3D Gaussian distribution, and that for a RT contains zeros for enhancement of polyps and suppression of RTs, respectively. For distinction between polyps and nonpolyps including RTs, a 3D scoring method based on a 3D Gaussian weighting function is applied to the output of the trained 3D MTANN. Our database consisted of CTC examinations of 73 patients, scanned in both supine and prone positions (146 CTC data sets in total), with optical colonoscopy as a reference standard for the presence of polyps. Fifteen patients had 28 polyps, 15 of which were 5-9 mm and 13 were 10-25 mm in size. These CTC cases were subjected to our previously reported CAD scheme that included centerline-based segmentation of the colon, shape-based detection of polyps, and reduction of FPs by use of a Bayesian neural network based on geometric and texture features. Application of this CAD scheme yielded 96.4% (27/28) by-polyp sensitivity with 3.1 (224/73) FPs per patient, among which 20 FPs were caused by RTs. To eliminate the FPs due to RTs and possibly other normal structures, we trained a 3D MTANN with ten representative polyps and ten RTs, and applied the trained 3D MTANN to the above CAD true- and false-positive detections. In the output volumes of the 3D MTANN, polyps were represented by distributions of bright voxels, whereas RTs and other normal structures partly similar to RTs appeared as darker voxels, indicating the ability of the 3D MTANN to suppress RTs as well as other normal structures effectively. Application of the 3D MTANN to the CAD detections showed that the 3D MTANN eliminated all RT-induced 20 FPs, as well as 53 FPs due to other causes, without removal of any true positives. Overall, the 3D MTANN was able to reduce the FP rate of the CAD scheme from 3.1 to 2.1 FPs per patient (33% reduction), while the original by-polyp sensitivity of 96.4% was maintained.

Algorithms↗
PubMed1999

An empirical evaluation of Bayesian sampling with hybrid Monte Carlo for training neural network classifiers.

This article gives a concise overview of Bayesian sampling for neural networks, and then presents an extensive evaluation on a set of various benchmark classification problems. The main objective is to study the sensitivity of this scheme to changes in the prior distribution of the parameters and hyperparameters, and to evaluate the efficiency of the so-called automatic relevance determination (ARD) method. The article concludes with a comparison of the achieved classification results with those obtained with (i) the evidence scheme and (ii) with non-Bayesian methods.

Journal Article↗
PubMed2004

Algorithms based on prostate-specific antigen (PSA), free PSA, digital rectal examination and prostate volume reduce false-positive PSA results in prostate cancer screening.

Our objective was to determine whether multivariate algorithms based on serum total PSA, the free proportion of PSA, age, digital rectal examination and prostate volume can reduce the rate of false-positive PSA results in prostate cancer screening more effectively than the proportion of free PSA alone at 95% sensitivity. A total of 1,775 consecutive 55- to 67-year-old men with a serum PSA of 4-10 microg/l in the European Randomized Study of Screening for Prostate Cancer were included. To predict the presence of cancer, multivariate algorithms were constructed using logistic regression (LR) and a multilayer perceptron neural network with Bayesian regularization (BR-MLP). A prospective setting was simulated by dividing the data set chronologically into one set for training and validation (67%, n = 1,183) and one test set (33%, n = 592). The diagnostic models were calibrated using the training set to obtain 95% sensitivity. When applied to the test set, the LR model, the BR-MLP model and the proportion of free PSA reached 92%, 87% and 94% sensitivity and reduced 29%, 36% and 22% of the false-positive PSA results, respectively. At a fixed sensitivity of 95% in the test set, the LR model eliminated more false-positive PSA results (22%) than the proportion of free PSA alone (17%) (p < 0.001), whereas the BR-MLP model did not (19%) (p = 0.178). The area under the ROC curve was larger for the LR model (0.764, p = 0.030) and the BR-MLP model (0.760, p = 0.049) than for the proportion of free PSA (0.718). A multivariate algorithm can be used to reduce unnecessary prostate biopsies in screening more effectively than the proportion of free PSA alone, but the algorithms will require updating when clinical practice develops with time.

Aged↗
PubMed2002

A computer-based training system for breast fine needle aspiration cytology.

Fine-needle aspiration (FNA) cytology is a rapid and inexpensive technique used extensively in the diagnosis of breast disease. To remove diagnostic subjectivity, a diagnostic decision support system (DDSS) called CytoInform has been developed, based on a Bayesian belief network (BBN) for the diagnosis of breast FNAs. In addition to acting as a DDSS, the system implements a computer-based training (CBT) system, providing a novel approach to breast cytology training. The system guides the trainee cytopathologist through the diagnostic process, allowing the user to grade each diagnostic feature using a set of on-screen reference images as visual clues. The trainee positions a slider on a spectrum relative to these images, reflecting the similarity between the reference image and the microscope image. From this, an evidence vector is generated, allowing the current diagnostic probability to be updated by the BBN. As the trainee assesses each clue, the evidence entered is compared with that of the expert through the use of a defined teaching file. This file records the relative severity of each clue and a tolerance band within which the trainee must position the slider. When all clues in the teaching case have been completed, the system informs the user of inaccuracies and offers the ability to reassess problematic features. In trials with two pathologists of different experience and a series of ten cases, the system provided an effective tool in conveying diagnostic evidence and protocols to trainees. This is evident from the fact that each pathologist only misinterpreted one case and a total of 86%/88% (experienced/inexperienced) of all clues assessed were interpreted correctly. Significantly, in all cases that produced the correct final diagnostic probability, the route taken to that solution was consistent with the expert's solution.

Bayes Theorem↗
PubMed1993

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 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.

Bayes Theorem↗
PubMed1996

Temporal reasoning for diagnosis in a causal probabilistic knowledge base.

We have added temporal reasoning to the Heart Disease Program (HDP) to take advantage of the temporal constraints inherent in cardiovascular reasoning. Some processes take place over minutes while others take place over months or years and a strictly probabilistic formalism can generate hypotheses that are impossible given the temporal relationships involved. The HDP has temporal constraints on the causal relations specified in the knowledge base and temporal properties on the patient input provided by the user. These are used in two ways. First, they are used to constrain the generation of the pre-computed causal pathways through the model that speed the generation of hypotheses. Second, they are used to generate time intervals for the instantiated nodes in the hypotheses, which are matched and adjusted as nodes are added to each evolving hypothesis. This domain offers a number of challenges for temporal reasoning. Since the nature of diagnostic reasoning is inferring a causal explanation from the evidence, many of the temporal intervals have few constraints and the reasoning has to make maximum use of those that exist. Thus, the HDP uses a temporal interval representation that includes the earliest and latest beginning and ending specified by the constraints. Some of the disease states can be corrected but some of the manifestations may remain. For example, a valve disease such as aortic stenosis produces hypertrophy that remains long after the valve has been replaced. This requires multiple time intervals to account for the existing findings. This paper discusses the issues and solutions that have been developed for temporal reasoning integrated with a pseudo-Bayesian probabilistic network in this challenging domain for diagnosis.

Artificial Intelligence↗
PubMed2005

Multimodality computerized diagnosis of breast lesions using mammography and sonography.

RATIONALE AND OBJECTIVES: The purpose of this study is to investigate the use of computer-extracted features of lesions imaged by means of two modalities, mammography and breast ultrasound, in the computerized classification of breast lesions. MATERIAL AND METHODS: We performed computerized analysis on a database of 97 patients with a total of 100 lesions (40 malignant, 40 benign solid, and 20 cystic lesions). Mammograms and ultrasound images were available for these breast lesions. There was an average of three mammographic images and two ultrasound images per lesion. Based on seed points indicated by a radiologist, the computer automatically segmented lesions from the parenchymal background and automatically extracted a set of characteristic features for each lesion. For each feature, its value averaged over all images pertaining to a given lesion was input to a Bayesian neural network for classification. We also investigated different approaches to combine image-based features into this by-lesion analysis. In that analysis, mean, maximum, and minimum feature values were considered for all images representing a lesion. We considered performance by using a leave-one-lesion-out approach, based on image features from mammography alone (two to five features), ultrasound alone (three to four features), and a combination of features from both modalities (three to five features total). RESULTS: For the classification task of distinguishing cancer from other abnormalities in a lesion-based analysis by using a single modality, areas under the receiver operating characteristic curves (A(z) values) increased significantly when the computer selected the manner (mean, minimum, or maximum) in which image-based features were combined into lesion-based features. The highest performance was found for lesion-based analysis and automated feature selection from mean, maximum, and minimum values of features from both modalities (resulting in a total of four features being used). That A(z) value for the task of distinguishing cancer was 0.92, showing a statistically significant increase over that achieved with features from either mammography or ultrasound alone. CONCLUSION: Computerized classification of cancer significantly improved when lesion features from both modalities were combined. Classification performance depended on specific methods for combining features from multiple images per lesion. These results are encouraging and warrant further exploration of computerized methods for multimodality imaging.

Breast Neoplasms↗
PubMed2004

Probabilistic representation of the exposure of consumers to Clostridium botulinum neurotoxin in a minimally processed potato product.

We have examined the potential of a well-specified, minimally processed potato product as a vehicle for the exposure of consumers to Clostridium botulinum neurotoxin. The product is a relatively simple combination of raw potato flakes, flour, starch and other minor ingredients and has an extended lifetime under refrigeration conditions. A combination of information and data, from a variety of sources that includes the manufacturer, has shown that the product is particularly safe with respect to non-proteolytic C. botulinum hazards. The model concentrates on a simple end point, the toxicity of an individual retail unit of the product at the point of consumer preparation, which is related to an individual risk. The probabilistic analysis was built using Bayesian Belief Network (BBN) techniques.

Bayes Theorem↗
PubMed2004

Investigation of new complete denture quality and patients' satisfaction with and use of dentures after two years.

OBJECTIVES: To investigate if clinical quality of new complete dentures predicts patient satisfaction with and usage of those dentures two years after insertion in the same way that it did initially and three months after insertion. METHODS: Four hundred and seventeen patients recruited to a denture outcome study two years previously were surveyed. In each case aspects of denture quality had previously been rated according to a validated method at the first post-insertion visit and patients had completed a postal questionnaire three months after denture insertion. When the dentures were two years old, patients were sent another postal questionnaire to assess denture usage and satisfaction with the dentures. RESULTS: The response rate to the postal survey was 87%. Data were analysed using structural equation modelling and Bayesian belief networks. No significant associations were found between aspects of new denture quality and patient satisfaction with and use of complete dentures after two years. These results contrast with the three month returns from the same patients that demonstrated significant associations between new denture quality and satisfaction with and use of new complete dentures. CONCLUSIONS: The authors conclude that initial clinical quality of new complete dentures is not a significant factor in determining patients' satisfaction with and use of these complete dentures two years after insertion.

Aged↗
PubMed2003

Computerized diagnostic decision support system for the classification of preinvasive cervical squamous lesions.

Previous studies have revealed considerable interobserver and intraobserver variation in the histological classification of preinvasive cervical squamous lesions. The aim of the present study was to develop a decision support system (DSS) for the histological interpretation of these lesions. Knowledge and uncertainty were represented in the form of a Bayesian belief network that permitted the storage of diagnostic knowledge and, for a given case, the collection of evidence in a cumulative manner that provided a final probability for the possible diagnostic outcomes. The network comprised 8 diagnostic histological features (evidence nodes) that were each independently linked to the diagnosis (decision node) by a conditional probability matrix. Diagnostic outcomes comprised normal; koilocytosis; and cervical intraepithelial neoplasia (CIN) I, CIN II, and CIN III. For each evidence feature, a set of images was recorded that represented the full spectrum of change for that feature. The system was designed to be interactive in that the histopathologist was prompted to enter evidence into the network via a specifically designed graphical user interface (i-Path Diagnostics, Belfast, Northern Ireland). Membership functions were used to derive the relative likelihoods for the alternative feature outcomes, the likelihood vector was entered into the network, and the updated diagnostic belief was computed for the diagnostic outcomes and displayed. A cumulative probability graph was generated throughout the diagnostic process and presented on screen. The network was tested on 50 cervical colposcopic biopsy specimens, comprising 10 cases each of normal, koilocytosis, CIN I, CIN II, and CIN III. These had been preselected by a consultant gynecological pathologist. Using conventional morphological assessment, the cases were classified on 2 separate occasions by 2 consultant and 2 junior pathologists. The cases were also then classified using the DSS on 2 occasions by the 4 pathologists and by 2 medical students with no experience in cervical histology. Interobserver and intraobserver agreement using morphology and using the DSS was calculated with kappa statistics. Intraobserver reproducibility using conventional unaided diagnosis was reasonably good (kappa range, 0.688 to 0.861), but interobserver agreement was poor (kappa range, 0.347 to 0.747). Using the DSS improved overall reproducibility between individuals. Using the DSS, however, did not enhance the diagnostic performance of junior pathologists when comparing their DSS-based diagnosis against an experienced consultant. However, the generation of a cumulative probability graph also allowed a comparison of individual performance, how individual features were assessed in the same case, and how this contributed to diagnostic disagreement between individuals. Diagnostic features such as nuclear pleomorphism were shown to be particularly problematic and poorly reproducible. DSSs such as this therefore not only have a role to play in enhancing decision making but also in the study of diagnostic protocol, education, self-assessment, and quality control.

Bayes Theorem↗
PubMed2000

Research on factors allowing a risk assessment of spore-forming pathogenic bacteria in cooked chilled foods containing vegetables: a FAIR collaborative project.

Vegetables are frequent ingredients of cooked chilled foods and are frequently contaminated with spore-forming bacteria (SFB). Therefore, risk assessment studies have been carried out, including the following: hazard identification and characterisation--from an extensive literature review and expertise of the participants, B. cereus and C. botulinum were identified as the main hazards; exposure assessment--consisting of determination of the prevalence of hazardous SFB in cooked chilled foods containing vegetables and in unprocessed vegetables, and identification of SFB representative of the bacterial community in cooked chilled foods containing vegetables, determination of heat-resistance parameters and factors affecting heat resistance of SFB, determination of the growth kinetics of SFB in vegetable substrate and of the influence of controlling factors, validation of previous work in complex food systems and by challenge testing and information about process and storage conditions of cooked chilled foods containing vegetables. The paper illustrates some original results obtained in the course of the project. The results and information collected from scientific literature or from the expertise of the participants are integrated into the microbial risk assessment, using both a Bayesian belief network approach and a process risk model approach, previously applied to other foodborne hazards.

Bacillus cereus↗
PubMed1992

Construction of the knowledge file for an image understanding system.

To enable an image understanding system to provide an automated interpretation of diagnostic imagery it must have access to all of the concepts, procedures and methods used by human experts. The paper describes information elicitation from experts of different domains and the construction of a knowledge file. Uncertainty management is based on Bayesian belief network methods.

Bayes Theorem↗
PubMed1999

Feature selection for computerized mass detection in digitized mammograms by using a genetic algorithm.

RATIONALE AND OBJECTIVES: To investigate optimization of feature selection for computerized mass detection in digitized mammograms, and to compare the effectiveness of a genetic algorithm (GA) in such optimization with that of an "exhaustive" search of all feature permutations. MATERIALS AND METHODS: A Bayesian belief network (BBN) was used to classify positive and negative regions for masses depicted in digitized mammograms; 20 features were computed for each of 592 positive and 3,790 negative regions in two databases. Conditional probabilities for the BBN were computed by using a "training" database of 288 positive and 2,204 negative regions. Performance was measured by the area under the receiver operating characteristic curve (A) by using the remainder database (304 positive and 1,586 negative regions). The optimal set was first found by using an "exhaustive" (complete permutation) searching method. A GA-based search for the optimal set then was applied, and the results of the two approaches were compared. RESULTS: As the number of features in the classifier increased, the A value increased until it reached a maximum performance for 11 features of 0.876 +/- 0.008. The A value then decreased monotonically as the number of features increased from 11 to 20. Using 100 random chromosomes (seeds) in the first generation, the GA identified the same optimal set of features but reduced the total computation time by a factor of 65. CONCLUSION: A GA-based search might be an efficient and effective approach to selecting an optimal feature set.

Algorithms↗
PubMedDate not supplied

Statistical modelling in specific case analysis.

In spite of the problems associated with the development of a statistical approach in specific case analysis, the potential of two statistical methods, logistic regression and Bayesian belief networks, has been investigated and found encouraging in the context of a database relating to child murders with a sexual connotation. Continual collaboration between statisticians and detectives would be needed in the collection of the data, the choice and construction of the models, and the interpretation of the results.

Adult↗