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 181 records · Page 10Linked to original sources
PubMedDate not supplied

Expert system support using Bayesian belief networks in the prognosis of head-injured patients of the ICU.

The present study concerns the construction and operation of a Bayesian analytical system, namely a Bayesian belief network (BBN) for the prognosis at 24 h of head-injured patients of the intensive care unit. The construction of a BBN incorporates the maintenance of a large database including all the critical variables corresponding to the specific clinical domain. This database is processed to provide the necessary libraries of conditional probability values. BBNs permit the combination of prognostic evidence in a cumulative manner and provide a quantitative measure of certainty in the final decision. The user views the changes at each step, thus being capable of deciding upon the necessary pieces of information in order to reach a certain belief threshold. The system produces results that are compatible with the opinions of medical experts regarding the prognosis of patients exhibiting certain patterns of clinical or laboratory data.

Adult↗
PubMed2004

Using prior knowledge to improve genetic network reconstruction from microarray data.

The use of Bayesian Network methods to recover transcriptional regulatory networks from static microarray data is an active area of bioinformatics research. However, early work in this area lacked realistic analysis of the effects of data set size on learning performance and ignored the potentially immense benefits of using prior biological knowledge. More recent work which has utilized such information has tended to focus on qualitative descriptions of the results. In this paper, we construct a detailed, realistic model for glucose homeostasis and use this model to generate static, synthetic gene expression data. We then use a Bayesian Network method to reconstruct this genetic network from the synthetic microarray data utilizing various amounts and types of prior knowledge. By quantitatively analyzing the effects of data set size and the incorporation of different types of prior biological knowledge on our ability to reconstruct the original network, we show that characteristic portions of genetic networks can be reconstructed from microarray data. Incorporating prior knowledge into the learning scheme greatly reduces the data required, allowing these reverse engineering techniques to be used to learn regulatory interactions from microarray data sets of realistic size.

Bayes Theorem↗
PubMed2004

An integrative genomics approach to the reconstruction of gene networks in segregating populations.

The reconstruction of genetic networks in mammalian systems is one of the primary goals in biological research, especially as such reconstructions relate to elucidating not only common, polygenic human diseases, but living systems more generally. Here we propose a novel gene network reconstruction algorithm, derived from classic Bayesian network methods, that utilizes naturally occurring genetic variations as a source of perturbations to elucidate the network. This algorithm incorporates relative transcript abundance and genotypic data from segregating populations by employing a generalized scoring function of maximum likelihood commonly used in Bayesian network reconstruction problems. The utility of this novel algorithm is demonstrated via application to liver gene expression data from a segregating mouse population. We demonstrate that the network derived from these data using our novel network reconstruction algorithm is able to capture causal associations between genes that result in increased predictive power, compared to more classically reconstructed networks derived from the same data.

11-beta-Hydroxysteroid Dehydrogenases↗
PubMed2005

Network analysis of mild cognitive impairment.

We present a network analysis of a cross-sectional study of mild cognitive impairment (MCI). Network analysis, as opposed to univariate analysis, accounts for interactions among brain structures in explaining a clinical outcome. In this context, we analyze structural magnetic resonance (MR) data based on a Bayesian network representation of variables in the problem domain. The Bayesian network resulting from this analysis reveals complex, nonlinear multivariate associations among morphological changes in the left hippocampus and in the right thalamus and the presence of mild cognitive impairment. This Bayesian network could be used to predict the presence of mild cognitive impairment from structural MR scans.

Aged↗
PubMed1997

Constructing probabilistic models.

Bayesian networks have become one of the most popular probabilistic techniques in AI, largely due to the development of several efficient inference algorithms. In this paper we describe a heuristic method for constructing Bayesian networks. Our construction method relies on the relationship between Bayesian networks and decomposable models, a special kind of graphical model. We explain this relationship and then show how it can be used to facilitate model construction. Finally, we describe an implemented computer program that illustrates these ideas.

Algorithms↗
PubMed1999

The item generation methodology of an empiric simulation project.

The American Board of Family Practice (ABFP) is developing a computer-based testing system that will create realistic clinical encounters using an adaptation of an item generation process. Simulated patients' entire lives will be stochastically produced from a knowledge base, with constraints applied to prevent implausible simulations. The constraint mechanisms include knowledge acquisition decisions about grouping closely related medical concepts and widespread use of Bayesian networks to manage dependencies between concepts. Bayesian networks and fuzzy definitions provide stochastic variability between simulations produced from the same data. Examinees will interact with these patients using a large and stable set of queries and interventions. Multiple management plans associated with patient simulations provide a framework for scoring performance. All major components, including Health States, history generating "Lead To" objects, and Plans are reusable and often substitutable. Although initial knowledge acquisition demands are enormous, the system has good potential for low cost maintenance of content areas, and economies of scale as simulations and components are reused.

Journal Article↗
PubMed2006

Using a Bayesian belief network model to categorize length of stay for radical prostatectomy patients.

A clinical pathway implements best medical practices and represents sequencing and timing of interventions by clinicians for a particular clinical presentation. We used a Bayesian belief network (BBN) to model a clinical pathway for radical prostatectomy and to categorize patient's length of stay (LOS) as being met or delayed given the patient's outcomes and activities. A BBN model constructed from historical data collected as part of a retrospective chart study represents probabilistic dependencies between specific events from the pathway and identifies events directly affecting LOS. Preliminary evaluation of a BBN model on an independent test sample of patients' data shows that model reliably categorizes LOS for the second and third day after the surgery (with overall accuracy of 82 and 84%, respectively).

Bayes Theorem↗
PubMed1996

Reproducibility of Bayesian belief network assessment of breast fine needle aspirates.

OBJECTIVE: To assess the consistency of diagnosis of fine needle aspiration biopsies of breast lesions by three experienced and five less experienced pathologists using conventional means and applying a Bayesian belief network (BBN) to 10 diagnostic features to support diagnostic decision making. STUDY DESIGN: Forty fine needle aspiration biopsies, previously assessed by one of the experienced pathologists both conventionally and using a BBN, were assessed by two further experienced pathologists and five less experienced pathologists. RESULTS: Using the BBN, the experienced pathologists arrived at diagnoses in agreement with an established consensus at a slightly lower rate than by conventional means. The less experienced pathologists arrived at the correct diagnoses no more frequently with the help of the BBN than conventionally. CONCLUSION: As used in this study, the BBN did not help less experienced pathologists to interpret their observations but did not enable less experienced pathologists to identify how their observations differed and affected their diagnoses. The prototype system used in this study has since been upgraded by providing computer graphic displays of the features to be observed so that a more uniform mental image can be held by the participating pathologists. This will be tested with the same study design.

Biopsy, Needle↗
PubMedDate not supplied

Urothelial papillary lesions. Development of a Bayesian Belief Network for diagnosis and grading.

The diagnosis and grading of urothelial papillary lesions are affected by uncertainties which arise from the fact that the knowledge of histopathology is expressed in descriptive linguistic terms, words and concepts. A Bayesian Belief Network (BBN) was used to reduce the problem of uncertainty in diagnostic clue assessment, while still considering the dependencies between elements in the reasoning sequence. A shallow network was designed and developed with an open-tree topology, consisting of a root node containing four diagnostic alternatives (papilloma, papillary carcinoma grade 1, papillary carcinoma grade 2 and papillary carcinoma grade 3) and eight first-level descendant nodes for the diagnostic features. Six of these nodes were based on cell features and two on the architecture. The results obtained with prototypes of relative likelihood ratios showed that belief in the diagnostic alternatives is very high and that the network can identify papilloma and papillary carcinoma, including their grade, with certainty. In conclusion, a BBN applied to the diagnosis and grading of urothelial papillary lesions is a descriptive classifier which is readily implemented and allows the use of linguistic, fuzzy variables and the accumulation of evidence presented by diagnostic clues.

Bayes Theorem↗
PubMed1995

Prostatic intraepithelial neoplasia (PIN). Performance of Bayesian belief network for diagnosis and grading.

Prostatic intraepithelial neoplasia (PIN) diagnosis and grading are affected by uncertainties which arise from the fact that almost all knowledge of PIN histopathology is expressed in concepts, descriptive linguistic terms, and words. A Bayesian belief network (BBN) was therefore used to reduce the problem of uncertainty in diagnostic clue assessment, while still considering the dependences between elements in the reasoning sequence. A shallow network was used with an open-tree topology, with eight first-level descendant nodes for the diagnostic clues (evidence nodes), each independently linked by a conditional probability matrix to a root node containing the diagnostic alternatives (decision node). One of the evidence nodes was based on the tissue architecture and the others were based on cell features. The system was designed to be interactive, in that the histopathologist entered evidence into the network in the form of likelihood ratios for outcomes at each evidence node. The efficiency of the network was tested on a series of 110 prostate specimens, subdivided as follows: 22 cases of non-neoplastic prostate or benign prostatic tissue (NP), 22 PINs of low grade (PINlow), 22 PINs of high grade (PINhigh), 22 prostatic adenocarcinomas with cribriform pattern (PACcri), and 22 prostatic adenocarcinomas with large acinar pattern (PAClgac). The results obtained in the benign and malignant categories showed that the belief for the diagnostic alternatives is very high, the values being in general more than 0.8 and often close to 1.0. When considering the PIN lesions, the network classified and graded most of the cases with high certainty. However, there were some cases which showed values less than 0.8 (13 cases out of 44), thus indicating that there are situations in which the feature changes are intermediate between contiguous categories or grades. Discrepancy between morphological grading and the BBN results was observed in four out of 44 PIN cases: one PINlow was classified as PINhigh and three PINhigh were classified as PINlow. In conclusion, the network can grade PIN lesions and differentiate them from other prostate lesions with certainty. In particular, it offers a descriptive classifier which is readily implemented and which allows the use of linguistic, fuzzy variables.

Adenocarcinoma↗
PubMed2005

Decision support for diagnosis of lyme disease.

This paper describes the development of a Bayesian model for diagnosis of patients suspected of Lyme disease, and the integration of such a model into a medical information system. A Bayesian network incorporating the clinical history and laboratory results has been constructed. Because many of the symptoms are not exclusive to Lyme disease and they develop over time, the clinical history is important for making the correct diagnosis. The model is based on time slices, where each time slice contains the observed pathological picture from one consultation with for example, the general practitioner. Since the time intervals between consultations typically are not equivalent, we have developed a novel method that can handle non-equivalent time intervals between the time slices in the network. The method is based on a description of the general development pattern of Lyme disease, which is implemented in a model that states the conditional probabilities of experiencing a certain pathological picture given time since infection. The model has been integrated into a web-based medical information system, called Borrelia Systems, which has enabled us to evaluate the model during a progressive diagnostic process. The integration has been accomplished through the development of a Bayesian Application Framework. This framework specifies a communication data structure in XML providing a graphical user interface and database components, which can be used when developing systems that are based on Bayesian networks. The framework generalizes the integration of Bayesian networks so that it is possible to switch network without manually having to update or change the system.

Bayes Theorem↗
PubMed1994

Expert system support using Bayesian belief networks in the diagnosis of fine needle aspiration biopsy specimens of the breast.

AIM: To develop an expert system model for the diagnosis of fine needle aspiration cytology (FNAC) of the breast. METHODS: Knowledge and uncertainty were represented in the form of a Bayesian belief network which permitted the combination of diagnostic evidence in a cumulative manner and provided a final probability for the possible diagnostic outcomes. The network comprised 10 cytological features (evidence nodes), each independently linked to the diagnosis (decision node) by a conditional probability matrix. The system was designed to be interactive in that the cytopathologist entered evidence into the network in the form of likelihood ratios for the outcomes at each evidence node. RESULTS: The efficiency of the network was tested on a series of 40 breast FNAC specimens. The highest diagnostic probability provided by the network agreed with the cytopathologists' diagnosis in 100% of cases for the assessment of discrete, benign, and malignant aspirates. Atypical probably benign cases were given probabilities in favour of a benign diagnosis. Suspicious cases tended to have similar probabilities for both diagnostic outcomes and so, correctly, could not be assigned as benign or malignant. A closer examination of cumulative belief graphs for the diagnostic sequence of each case provided insight into the diagnostic process, and quantitative data which improved the identification of suspicious cases. CONCLUSION: The further development of such a system will have three important roles in breast cytodiagnosis: (1) to aid the cytologist in making a more consistent and objective diagnosis; (2) to provide a teaching tool on breast cytological diagnosis for the non-expert; and (3) it is the first stage in the development of a system capable of automated diagnosis through the use of expert system machine vision.

Bayes Theorem↗
PubMed1994

Prostatic intraepithelial neoplasia. Development of a Bayesian belief network for diagnosis and grading.

The diagnosis and grading of prostatic intraepithelial neoplasia (PIN) are affected by uncertainties that arise from the fact that almost all our knowledge of PIN histopathology is not expressed in numeric form but rather in descriptive linguistic terms, words and concepts. A Bayesian belief network (BBN) was used to reduce the problem of uncertainty in diagnostic clue assessment while considering the dependencies between elements in the reasoning sequence. A shallow network was developed with an open-tree topology, with a root node containing the diagnostic alternatives and seven first-level descendant nodes for the diagnostic clues. One of these nodes was based on tissue architecture and the others on cell features. The results obtained with prototypes of relative likelihood ratios showed that beliefs for the diagnostic alternatives are very high. The network can grade and differentiate PIN lesions from other prostate lesions with certainty. A number of diagnostic clues greater than seven did not significantly improve network performance, whereas a reduced number of clues resulted in decreased beliefs. A BBN for PIN diagnosis and grading offers a descriptive classifier that is readily implemented and allows the use of linguistic, fuzzy variables. A BBN allows the accumulation of evidence presented by diagnostic clues, each offering only weak evidence.

Bayes Theorem↗
PubMed2005

A Bayesian Neural Network approach to estimating the Energy Equivalent Speed.

To reduce the number and the gravity of accidents, it is necessary to analyse and reconstruct them. Accident modelling requires the modelling of the impact which in turn requires the estimation of the deformation energy. There are several tools available to evaluate the deformation energy absorbed by a vehicle during an impact. However, there is a growing demand for more precise and more powerful tools. In this work, we express the deformation energy absorbed by a vehicle during a crash as a function of the Energy Equivalent Speed (EES). The latter is a difficult parameter to estimate because the structural response of the vehicle during an impact depends on parameters concerning the vehicle, but also parameters concerning the impact. The objective of our work is to design a model to estimate the EES by using an original approach combining Bayesian and Neural Network approaches. Both of these tools are complementary and offer significant advantages, such as the guarantee of finding the optimal model and the implementation of error bars on the computed output. In this paper, we present the procedure for implementing this Bayesian Neural Network approach and the results obtained for the modelling of the EES: our model is able to estimate the EES of the car with a mean error of 1.34 m s(-1). Furthermore, we built a sensitivity analysis to study the relevance of model's inputs.

Accidents, Traffic↗
PubMed2001

Developing a Bayesian belief network for the management of geriatric hospital care.

Resource management is an essential feature of hospital management. This is especially true for geriatric services, as older people often have complex medical and social needs. Hospital management should benefit from an explanatory model that provides predictions of duration of stay and destination on discharge. We describe how a Bayesian belief network models the behaviour of geriatric patients using predictive variables: personal details, admission reasons and dependency levels. This approach is illustrated using data on 4,722 patients admitted to geriatric medicine at St. George's Hospital, London; distributions of the patient outcome given typical values of the predictive variables are provided.

Aged↗
PubMed1996

Atypical adenomatous hyperplasia (adenosis) of the prostate: development of a Bayesian belief network for its distinction from well-differentiated adenocarcinoma.

The diagnosis of atypical adenomatous hyperplasia (AAH) of the prostate and its distinction from well-differentiated prostatic adenocarcinoma with small acinar pattern (PACsmac; Gleason primary grades 1 or 2) are affected by uncertainties that arise from the fact that the knowledge of AAH histopathology is expressed in descriptive linguistic terms, words, and concepts. A Bayesian belief network (BBN) was used to reduce the problem of uncertainty in diagnostic clue assessment, while still considering the dependencies between elements in the reasoning sequence. A shallow network was designed and developed with an open-tree topology, consisting of a root node containing two diagnostic alternatives (eg, AAH v PACsmac) and 12 first-level descendant nodes for the diagnostic features. Eight of these nodes were based on cell features, three on the type of gland lumen contents and one on the gland shape. The results obtained with prototypes of relative likelihood ratios showed that belief for the diagnostic alternatives is high and that the network can differentiate AAH from PACsmac with certainty. The features that best contributed to the highest belief were those concerning the nucleolar size, frequency, and location. In particular, after the analysis of five nucleolar features (prominent nucleoli, inconspicuous nucleoli, nucleoli with diameter greater than 2.5 micron, nucleolar margination, and nuclei with multiple nucleoli), the belief for AAH was 1.0, being already close to 1.0 when three were evaluated (the value range is 0.0 to 1.0; the closer to 1.0, the greater the belief). The contribution of the three features concerning the gland lumen contents (mucinous material, corpora amylacea, and crystalloids) was such that the final belief did not exceed 0.8. Results with the group of remaining features (eg, basal cell recognition, gland shape variation, cytoplasm appearance, and nuclear size variation) were slightly better. These features allowed a substantial accumulation of belief that was already greater than 0.9 when three were polled. However, the maximum belief value was never obtained. In conclusion, a BBN for AAH diagnosis offers a descriptive classifier that is readily implemented, and allows the use of linguistic, fuzzy variables, and the accumulation of evidence presented by diagnostic clues.

Adenocarcinoma↗
PubMed2002

Expert system support using a Bayesian belief network for the classification of endometrial hyperplasia.

Accurate morphological classification of endometrial hyperplasia is crucial as treatments vary widely between the different categories of hyperplasia and are dependent, in part, on the histological diagnosis. However, previous studies have shown considerable inter-observer variation in the classification of endometrial hyperplasias. The aim of this study was to develop a decision support system (DSS) for the classification of endometrial hyperplasias. The system used a Bayesian belief network to distinguish proliferative endometrium, simple hyperplasia, complex hyperplasia, atypical hyperplasia and grade 1 endometrioid adenocarcinoma. These diagnostic outcomes were held in the decision node. Four morphological features were selected as diagnostic clues used routinely in the discrimination of endometrial hyperplasias. These represented the evidence nodes and were linked to the decision node by conditional probability matrices. The system was designed with a computer user interface (CytoInform) where reference images for a given clue were displayed to assist the pathologist in entering evidence into the network. Reproducibility of diagnostic classification was tested on 50 cases chosen by a gynaecological pathologist. These comprised ten cases each of proliferative endometrium, simple hyperplasia, complex hyperplasia, atypical hyperplasia and grade 1 endometrioid adenocarcinoma. The DSS was tested by two consultant pathologists, two junior pathologists and two medical students. Intra- and inter-observer agreement was calculated following conventional histological examination of the slides on two occasions by the consultants and junior pathologists without the use of the DSS. All six participants then assessed the slides using the expert system on two occasions, enabling inter- and intra-observer agreement to be calculated. Using unaided conventional diagnosis, weighted kappa values for intra-observer agreement ranged from 0.645 to 0.901. Using the DSS, the results for the four pathologists ranged from 0.650 to 0.845. Both consultant pathologists had slightly worse weighted kappa values using the DSS, while both junior pathologists achieved slightly better values using the system. The grading of morphological features and the cumulative probability curve provided a quantitative record of the decision route for each case. This allowed a more precise comparison of individuals and identified why discordant diagnoses were made. Taking the original diagnoses of the consultant gynaecological pathologist as the 'gold standard', there was excellent or moderate to good inter-observer agreement between the 'gold standard' and the results obtained by the four pathologists using the expert system, with weighted kappa values of 0.586-0.872. The two medical students using the expert system achieved weighted kappa values of 0.771 (excellent) and 0.560 (moderate to good) compared to the 'gold standard'. This study illustrates the potential of expert systems in the classification of endometrial hyperplasias.

Bayes Theorem↗
PubMed2001

Combining decision support methodologies to diagnose pneumonia.

OBJECTIVE: To evaluate the performance of a computerized decision support system that combines two different decision support methodologies (a Bayesian network and a natural language understanding system) for the diagnosis of patients with pneumonia. DESIGN: Evaluation study using data from a prospective, clinical study. PATIENTS: All patients 18 years and older who presented to the emergency department of a tertiary care setting and whose chest x-ray report was available during the encounter. METHODS: The computerized decision support system calculated a probability of pneumonia using information provided by the two systems. Outcome measures were the area under the receiver operating characteristic curve, sensitivity, specificity, predictive values, likelihood ratios, and test effectiveness. RESULTS: During the 3-month study period there were 742 patients (45 with pneumonia). The area under the receiver operating characteristic curve was 0.881 (95% CI: 0.822, 0.925) for the Bayesian network alone and 0.916 (95% CI: 0.869, 0.949) for the Bayesian network combined with the natural language understanding system (p=0.01). CONCLUSION: Combining decision support methodologies that process information stored in different data formats can increase the performance of a computerized decision support system.

Adult↗