How to develop and use a Bayesian Belief Network.

Montironi, Rodolfo; Whimster, W. F.; Collan, Yrjö; Hamilton, Peter; Thompson, Deborah; Ph, Bartels

doi:10.1136/jcp.49.3.194

Cited by 30 publications

(23 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the network analysis also indicated that network pharmacology approaches could be used to forecast and discover unknown or new effects and channel tropisms of TCM slices. Additionally, Zhang et al [58] reconstructed three Bayesian belief networks [59] for bitter, sweet, and pungent flavors, which was based on the modern pharmacology of TCM slices and clinical data. The results suggested that the Bayesian belief network could be used to predict the flavors of Chinese medicinal components and perform further studies of drug properties and drug compatibility.…”

Section: Application Of Network Pharmacology In Chm Researchmentioning

confidence: 99%

Network Pharmacology: A New Approach for Chinese Herbal Medicine Research

Zhang

Chen

et al. 2013

Evidence-Based Complementary and Alternative Medicine

196

185

View full text Add to dashboard Cite

The dominant paradigm of “one gene, one target, one disease” has influenced many aspects of drug discovery strategy. However, in recent years, it has been appreciated that many effective drugs act on multiple targets rather than a single one. As an integrated multidisciplinary concept, network pharmacology, which is based on system biology and polypharmacology, affords a novel network mode of “multiple targets, multiple effects, complex diseases” and replaces the “magic bullets” by “magic shotguns.” Chinese herbal medicine (CHM) has been recognized as one of the most important strategies in complementary and alternative medicine. Though CHM has been practiced for a very long time, its effectiveness and beneficial contribution to public health has not been fully recognized. Also, the knowledge on the mechanisms of CHM formulas is scarce. In the present review, the concept and significance of network pharmacology is briefly introduced. The application and potential role of network pharmacology in the CHM fields is also discussed, such as data collection, target prediction, network visualization, multicomponent interaction, and network toxicology. Furthermore, the developing tendency of network pharmacology is also summarized, and its role in CHM research is discussed.

show abstract

Section: Application Of Network Pharmacology In Chm Researchmentioning

confidence: 99%

Network Pharmacology: A New Approach for Chinese Herbal Medicine Research

Zhang

Chen

et al. 2013

Evidence-Based Complementary and Alternative Medicine

196

185

View full text Add to dashboard Cite

show abstract

“…Beginning in 1987, approximately 1,200 publications could now be found in the Medline database using the key words, ‘Bayesian network', for query. Clinical applications include histopathologic classification [19,20], diagnosis [21] or gene expression network simulation [22]. …”

Section: Discussionmentioning

confidence: 99%

Two-Center Observational Study of the Accuracy of a Bayes Network for Short-Term Outcome Prediction in Cholecystectomy Patients

Udelnow

Schmidt²,

Muche

et al. 2013

Dig Surg

View full text Add to dashboard Cite

Background: A Bayes Network was developed for individual risk prediction after cholecystectomy. Validity and robustness were compared with logistic regression analysis (LR). Methods: Clinical databases were created at the Ulm University and St. Franziskus Flensburg hospitals between 2001 and 2010 were comprised of hospitalized cholecystolithiasis patients serving as model and test cohorts, respectively. The probabilities of in-hospital death, prolonged hospitalization (>7 days), relaparotomy and erythrocyte transfusions were predicted based solely on admission data by BN and LR. ROC curves were calculated. Results: The Ulm and Flensburg cohorts consisted of 1,029 and 1,842 patients, respectively. The areas under the ROC curves for predicting death were 94% (p = 0.8) for both BN and LR, 70 vs. 76% (p < 0.001) for prolonged hospitalization, 69 vs. 68% (p = 0.8) for relaparotomy, and 84 vs. 78% (p = 0.1) for ET. Predictability declined for both methods when explanatory values were changed randomly. In contrast to LR, the BN revealed a good robustness to missing values. Conclusion: Both BN and MR predicted the death risk quite accurately. The advantage of BN consists of its robustness to missing values. Moreover, its graphical representation may be helpful for clinical decision making.

show abstract

“…Such models are representations of the real world and can describe objects, concepts, or methods. Bayesian belief networks, 14 for instance, statistically correlate the presence or absence of findings with the most likely corresponding diagnosis or diagnoses. Structured collections of terms and concepts such as MeSH are often referred to as taxonomies or ontologies.…”

Section: Informatics: a Research And An Applied Disciplinementioning

confidence: 99%

Dental Informatics: An Emerging Biomedical Informatics Discipline

Schleyer

2003

Adv Dent Res.

View full text Add to dashboard Cite

Biomedical informatics is a maturing discipline. During the last forty years, it has developed into a research discipline of significant scale and scope. One of its subdisciplines, dental informatics, is beginning to emerge as its own entity. While there is a growing cadre of trained dental informaticians, dental faculty and administrators in general are not very familiar with dental informatics as an area of scientific inquiry. Many confuse informatics with information technology (IT), are unaware of its scientific methods and principles, and cannot relate dental informatics to biomedical informatics as a whole. This article delineates informatics from information technology and explains the types of scientific questions that dental and other informaticians typically explore. Scientific investigation in informatics centers primarily on model formulation, system development, system implementation, and the study of effects. Informatics draws its scientific methods mainly from information science, computer science, cognitive science, and telecommunications. Dental informatics shares many types of research questions and methods with its parent discipline, biomedical informatics. However, there are indications that certain research questions in dental informatics require novel solutions that have not yet been developed in other informatics fields.

show abstract

How to develop and use a Bayesian Belief Network.

Cited by 30 publications

References 4 publications

Network Pharmacology: A New Approach for Chinese Herbal Medicine Research

Network Pharmacology: A New Approach for Chinese Herbal Medicine Research

Two-Center Observational Study of the Accuracy of a Bayes Network for Short-Term Outcome Prediction in Cholecystectomy Patients

Dental Informatics: An Emerging Biomedical Informatics Discipline

Contact Info

Product

Resources

About