Search

Your search keyword '"Lewis, Fraser Iain"' showing total 9 results
Start Over Author "Lewis, Fraser Iain"
9 results on '"Lewis, Fraser Iain"'

1. Additive Bayesian Network Modelling with the R Package abn

Author

Kratzer, Gilles, Lewis, Fraser Iain, Comin, Arianna, Pittavino, Marta, and Furrer, Reinhard

Subjects
Statistics - Machine Learning, Computer Science - Machine Learning, Statistics - Methodology
Abstract

The R package abn is designed to fit additive Bayesian models to observational datasets. It contains routines to score Bayesian networks based on Bayesian or information theoretic formulations of generalized linear models. It is equipped with exact search and greedy search algorithms to select the best network. It supports a possible blend of continuous, discrete and count data and input of prior knowledge at a structural level. The Bayesian implementation supports random effects to control for one-layer clustering. In this paper, we give an overview of the methodology and illustrate the package's functionalities using a veterinary dataset about respiratory diseases in commercial swine production., Comment: 37 pages, 14 figures and 2 tables

Published
2019

2. Assessing the impact of variable infectivity on the transmission of HIV among intravenous drug users

Author

Lewis, Fraser Iain

Subjects
614, Drug abuse
Abstract

The spread of HIV and AIDS is a serious and increasing global problem with the sharing of contaminated injection equipment a primary cause of HIV infection in the developed world. Mathematical models of disease transmission allow us to assess the impact of different epidemiological and behavioural assumptions on the long term behaviour of disease. Initially a simple deterministic model is examined which allows intravenous drug users to progress through three different infectious stages after initial infection with HIV and prior to the development of AIDS. This model is then developed to also allow contaminated injection equipment to exist in three different states of infectivity. The resulting model contains a number of parameters, which while potentially important, are extremely difficult to estimate. In response to this, several special cases are examined which represent intuitive upper and lower bounds for the spread of disease. In each case an equilibrium and stability analysis is presented. Later these special cases, together with a generalisation of them, are compared with a well established single stage infectivity model to ascertain whether the inclusion of variable infectivity increases the predicted spread of disease. We find that the impact of variable infectivity depends on a number of factors and can lead to either an increase or decrease in the prevalence of disease. Testing drug users for the presence of HIV has been proposed as a method of reducing the incidence of HIV. Using the previously discussed upper and lower bound variable infectivity models, we examine the effect of testing addicts for HIV using a number of different infectivity assumptions. We find that under certain conditions HIV testing can be an effective control strategy against the future spread of HIV. This is followed by a short discussion of sensitivity analysis of these models. While predominantly discussing deterministic models we conclude with a brief discussion of stochastic models and demonstrate the behaviour of these models using simulation.

Published
2000
Full Text
View/download PDF

3. Estimating diagnostic test accuracies for brachyspira hyodysenteriae accounting for the complexities of population structure in food animals

Author

Hartnack, Sonja, Nathues, Christina, Nathues, Heiko, Grosse Beilage, Elisabeth, Lewis, Fraser Iain, Lin, Baochuan, and University of Zurich

Subjects
Veterinary medicine, Swine, Veterinary Microbiology, lcsh:Medicine, Polymerase Chain Reaction, Feces, Statistics, Medicine and Health Sciences, lcsh:Science, Animal Management, Swine Diseases, Multidisciplinary, 630 Agriculture, Sampling (statistics), Contrast (statistics), Agriculture, Veterinary Bacteriology, Random effects model, Test (assessment), Veterinary Diseases, Molecular Diagnostic Techniques, Veterinary Informatics, Physical Sciences, Statistics (Mathematics), Research Article, Veterinary Medicine, Animal Types, Bayesian probability, 610 Medicine & health, 1100 General Agricultural and Biological Sciences, Large Animals, Biostatistics, Biology, Animal Welfare, Sensitivity and Specificity, Veterinary Epidemiology, Dysentery, Diagnostic Medicine, 1300 General Biochemistry, Genetics and Molecular Biology, Animals, Statistical Methods, 10599 Chair in Veterinary Epidemiology, Models, Statistical, lcsh:R, Biology and Life Sciences, Gold standard (test), Brachyspira hyodysenteriae, Herd, 570 Life sciences, biology, Veterinary Science, lcsh:Q, Mathematics
Abstract

For swine dysentery, which is caused by Brachyspira hyodysenteriae infection and is an economically important disease in intensive pig production systems worldwide, a perfect or error-free diagnostic test ("gold standard") is not available. In the absence of a gold standard, Bayesian latent class modelling is a well-established methodology for robust diagnostic test evaluation. In contrast to risk factor studies in food animals, where adjustment for within group correlations is both usual and required for good statistical practice, diagnostic test evaluation studies rarely take such clustering aspects into account, which can result in misleading results. The aim of the present study was to estimate test accuracies of a PCR originally designed for use as a confirmatory test, displaying a high diagnostic specificity, and cultural examination for B. hyodysenteriae. This estimation was conducted based on results of 239 samples from 103 herds originating from routine diagnostic sampling. Using Bayesian latent class modelling comprising of a hierarchical beta-binomial approach (which allowed prevalence across individual herds to vary as herd level random effect), robust estimates for the sensitivities of PCR and culture, as well as for the specificity of PCR, were obtained. The estimated diagnostic sensitivity of PCR (95% CI) and culture were 73.2% (62.3; 82.9) and 88.6% (74.9; 99.3), respectively. The estimated specificity of the PCR was 96.2% (90.9; 99.8). For test evaluation studies, a Bayesian latent class approach is well suited for addressing the considerable complexities of population structure in food animals.

Published
2014
Full Text
View/download PDF

5. Estimating diagnostic test accuracies for brachyspira hyodysenteriae accounting for the complexities of population structure in food animals

Author

Hartnack, Sonja; https://orcid.org/0000-0002-5757-5708, Nathues, Christina, Nathues, Heiko, Grosse Beilage, Elisabeth, Lewis, Fraser Iain, Hartnack, Sonja; https://orcid.org/0000-0002-5757-5708, Nathues, Christina, Nathues, Heiko, Grosse Beilage, Elisabeth, and Lewis, Fraser Iain

Abstract

For swine dysentery, which is caused by Brachyspira hyodysenteriae infection and is an economically important disease in intensive pig production systems worldwide, a perfect or error-free diagnostic test (‘‘gold standard’’) is not available. In the absence of a gold standard, Bayesian latent class modelling is a well-established methodology for robust diagnostic test evaluation. In contrast to risk factor studies in food animals, where adjustment for within group correlations is both usual and required for good statistical practice, diagnostic test evaluation studies rarely take such clustering aspects into account, which can result in misleading results. The aim of the present study was to estimate test accuracies of a PCR originally designed for use as a confirmatory test, displaying a high diagnostic specificity, and cultural examination for B. hyodysenteriae. This estimation was conducted based on results of 239 samples from 103 herds originating from routine diagnostic sampling. Using Bayesian latent class modelling comprising of a hierarchical beta-binomial approach (which allowed prevalence across individual herds to vary as herd level random effect), robust estimates for the sensitivities of PCR and culture, as well as for the specificity of PCR, were obtained. The estimated diagnostic sensitivity of PCR (95% CI) and culture were 73.2% (62.3; 82.9) and 88.6% (74.9; 99.3), respectively. The estimated specificity of the PCR was 96.2% (90.9; 99.8). For test evaluation studies, a Bayesian latent class approach is well suited for addressing the considerable complexities of population structure in food animals.

Published
2014

9. Estimating Diagnostic Test Accuracies for Brachyspira hyodysenteriae Accounting for the Complexities of Population Structure in Food Animals.

Author

Hartnack, Sonja, Nathues, Christina, Nathues, Heiko, Grosse Beilage, Elisabeth, and Lewis, Fraser Iain

Subjects
SWINE dysentery, TREPONEMA hyodysenteriae, FOOD animals, BAYESIAN analysis, ROBUST control, ESTIMATION theory, DIAGNOSIS
Abstract

For swine dysentery, which is caused by Brachyspira hyodysenteriae infection and is an economically important disease in intensive pig production systems worldwide, a perfect or error-free diagnostic test (“gold standard”) is not available. In the absence of a gold standard, Bayesian latent class modelling is a well-established methodology for robust diagnostic test evaluation. In contrast to risk factor studies in food animals, where adjustment for within group correlations is both usual and required for good statistical practice, diagnostic test evaluation studies rarely take such clustering aspects into account, which can result in misleading results. The aim of the present study was to estimate test accuracies of a PCR originally designed for use as a confirmatory test, displaying a high diagnostic specificity, and cultural examination for B. hyodysenteriae. This estimation was conducted based on results of 239 samples from 103 herds originating from routine diagnostic sampling. Using Bayesian latent class modelling comprising of a hierarchical beta-binomial approach (which allowed prevalence across individual herds to vary as herd level random effect), robust estimates for the sensitivities of PCR and culture, as well as for the specificity of PCR, were obtained. The estimated diagnostic sensitivity of PCR (95% CI) and culture were 73.2% (62.3; 82.9) and 88.6% (74.9; 99.3), respectively. The estimated specificity of the PCR was 96.2% (90.9; 99.8). For test evaluation studies, a Bayesian latent class approach is well suited for addressing the considerable complexities of population structure in food animals. [ABSTRACT FROM AUTHOR]

Published
2014
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results