Dataset Information

Partially latent class models for case-control studies of childhood pneumonia aetiology.

ABSTRACT: In population studies on the aetiology of disease, one goal is the estimation of the fraction of cases that are attributable to each of several causes. For example, pneumonia is a clinical diagnosis of lung infection that may be caused by viral, bacterial, fungal or other pathogens. The study of pneumonia aetiology is challenging because directly sampling from the lung to identify the aetiologic pathogen is not standard clinical practice in most settings. Instead, measurements from multiple peripheral specimens are made. The paper introduces the statistical methodology designed for estimating the population aetiology distribution and the individual aetiology probabilities in the Pneumonia Etiology Research for Child Health study of 9500 children for seven sites around the world. We formulate the scientific problem in statistical terms as estimating the mixing weights and latent class indicators under a partially latent class model (PLCM) that combines heterogeneous measurements with different error rates obtained from a case-control study. We introduce the PLCM as an extension of the latent class model. We also introduce graphical displays of the population data and inferred latent class frequencies. The methods are tested with simulated data, and then applied to Pneumonia Etiology Research for Child Health data. The paper closes with a brief description of extensions of the PLCM to the regression setting and to the case where conditional independence between the measures is relaxed.

SUBMITTER: Wu Z

PROVIDER: S-EPMC7169268 | biostudies-literature | 2016 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Partially latent class models for case-control studies of childhood pneumonia aetiology.

Wu Zhenke Z Deloria-Knoll Maria M Hammitt Laura L LL Zeger Scott L SL

Journal of the Royal Statistical Society. Series C, Applied statistics 20150326 1

In population studies on the aetiology of disease, one goal is the estimation of the fraction of cases that are attributable to each of several causes. For example, pneumonia is a clinical diagnosis of lung infection that may be caused by viral, bacterial, fungal or other pathogens. The study of pneumonia aetiology is challenging because directly sampling from the lung to identify the aetiologic pathogen is not standard clinical practice in most settings. Instead, measurements from multiple peri ...[more]

PMID: 32327815

Similar Datasets

Project description:BackgroundPneumonia is a leading cause of mortality and morbidity in children globally. The cause of pneumonia after introduction of the 13-valent pneumococcal conjugate vaccine (PCV13) has not been well studied in low-income and middle-income countries, and most data are from cross-sectional studies of children admitted to hospital. We aimed to longitudinally investigate the incidence and causes of childhood pneumonia in a South African birth cohort.MethodsWe did a nested case-control study of children in the Drakenstein Child Health Study who developed pneumonia from May 29, 2012, to Dec 1, 2014. Children received immunisations including acellular pertussis vaccine and PCV13. A nested subgroup had nasopharyngeal swabs collected every 2 weeks throughout infancy. We identified pneumonia episodes and collected blood, nasopharyngeal swabs, and induced sputum specimens. We used multiplex real-time PCR to detect pathogens in nasopharyngeal swabs and induced sputum of pneumonia cases and in nasopharyngeal swabs of age-matched and site-matched controls. To show associations between organisms and pneumonia we used conditional logistic regression; results are presented as odds ratios (ORs) with 95% CIs.Findings314 pneumonia cases occurred (incidence of 0·27 episodes per child-year, 95% CI 0·24-0·31; median age 5 months [IQR 3-9]) in 967 children during 1145 child-years of follow-up. 60 (21%) cases of pneumonia were severe (incidence 0·05 episodes per child-year [95% CI 0·04-0·07]) with a case fatality ratio of 1% (three deaths). A median of five organisms (IQR 4-6) were detected in cases and controls with nasopharyngeal swabs, and a median of six organisms (4-7) recorded in induced sputum (p=0·48 compared with nasopharyngeal swabs). Bordetella pertussis (OR 11·08, 95% CI 1·33-92·54), respiratory syncytial virus (8·05, 4·21-15·38), or influenza virus (4·13, 2·06-8·26) were most strongly associated with pneumonia; bocavirus, adenovirus, parainfluenza virus, Haemophilus influenzae, and cytomegalovirus were also associated with pneumonia. In cases, testing of induced sputum in addition to nasopharyngeal swabs provided incremental yield for detection of B pertussis and several viruses.InterpretationPneumonia remains common in this highly vaccinated population. Respiratory syncytial virus was the most frequently detected pathogen associated with pneumonia; influenza virus and B pertussis were also strongly associated with pneumonia. Testing of induced sputum increases the yield for detection of several organisms. New vaccines and strategies are needed to address the burden of childhood pneumonia.FundingBill & Melinda Gates Foundation, Medical Research Council South Africa, National Research Foundation South Africa, National Institute of Health, and H3Africa.

Project description:AimsThe main focus of this study is to illustrate the importance of the statistical analysis in the evaluation of the accuracy of malaria diagnostic tests, without admitting a reference test, exploring a dataset (n=3317) collected in São Tomé and Príncipe.MethodsBayesian Latent Class Models (without and with constraints) are used to estimate the malaria infection prevalence, together with sensitivities, specificities, and predictive values of three diagnostic tests (RDT, Microscopy and PCR), in four subpopulations simultaneously based on a stratified analysis by age groups (< 5, ? 5 years old) and fever status (febrile, afebrile).ResultsIn the afebrile individuals with at least five years old, the posterior mean of the malaria infection prevalence is 3.2% with a highest posterior density interval of [2.3-4.1]. The other three subpopulations (febrile ? 5 years, afebrile or febrile children less than 5 years) present a higher prevalence around 10.3% [8.8-11.7]. In afebrile children under-five years old, the sensitivity of microscopy is 50.5% [37.7-63.2]. In children under-five, the estimated sensitivities/specificities of RDT are 95.4% [90.3-99.5]/93.8% [91.6-96.0]--afebrile--and 94.1% [87.5-99.4]/97.5% [95.5-99.3]--febrile. In individuals with at least five years old are 96.0% [91.5-99.7]/98.7% [98.1-99.2]--afebrile--and 97.9% [95.3-99.8]/97.7% [96.6-98.6]--febrile. The PCR yields the most reliable results in four subpopulations.ConclusionsThe utility of this RDT in the field seems to be relevant. However, in all subpopulations, data provide enough evidence to suggest caution with the positive predictive values of the RDT. Microscopy has poor sensitivity compared to the other tests, particularly, in the afebrile children less than 5 years. This type of findings reveals the danger of statistical analysis based on microscopy as a reference test. Bayesian Latent Class Models provide a powerful tool to evaluate malaria diagnostic tests, taking into account different groups of interest.

Dataset Information

Partially latent class models for case-control studies of childhood pneumonia aetiology.

Publications

Partially latent class models for case-control studies of childhood pneumonia aetiology.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets