Bayesian Latent Class Models in Malaria Diagnosis

Abstract

Aims The 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 ( 3317) collected in São Tomé and Príncipe. Methods Bayesian 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 years old) and fever status (febrile, afebrile). Results In 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. Conclusions The 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.

Multiplex 5′ Nuclease Quantitative Real-Time PCR for Clinical Diagnosis of Malaria and Species-Level Identification and Epidemiologic Evaluation of Malaria-Causing Parasites, Including Plasmodium knowlesi

“…We also obtained and tested a large number of blood samples from patients with clinically suspected and clinical microbiology laboratory-confirmed microscopic malaria, and we enriched our specimen repository with additional samples from patients with rare P. ovale, P. malariae, and P. knowlesi infections. We compared qPCR to the existing standard of microscopy as our primary analysis but we also completed extensive additional testing to adjudicate discordant qPCR and microscopy results, since microscopy can be insensitive, relative to other methods (3), and identification to the species level is not always possible.…”

“…Microscopy has been the historic diagnostic standard but depends on the skill of the microscopist. Further, Bayesian latent-class models suggest that microscopy can be insensitive (with likely sensitivity ranges of 50 to 90%) for low-level parasitemia (3). Under optimal conditions, the analytical sensitivity of thick-film microscopy is 10 to 30 parasites per l of blood (4).…”

Parkinson’s Brain Disease Prediction Using Big Data Analytics

“…4. As specificity increases, sensitivity decreases and this kind of inverse linear relationship is clearly depicted from this ROC curve [24]. From this, one can clearly understand that as true positive rate increases, the false negative rate decreases automatically.…”

Measuring obesity in the absence of a gold standard

“…However, by treating the true unknown disease status as a latent variable, it is possible to use latent class analysis to estimate the true underlying prevalence of the disease along with measures of the sensitivity and specificity of each of the tests (see for example Walter and Irwig 1988, Biemer and Wiesen 2002and Biemer 2011. 1 This approach has been used elsewhere in biostatistics, for example when comparing alternative skin tests for the presence of tuberculosis (Hiu and Walter 1980), comparing diagnosis of myocardial infarction (Rindskopf and Rindskopf 1986), evaluating diagnostic tests of autism (Szatmari et al 1995) and malaria (Gonçalves 2012 The estimated true racial gap in obesity for women is similar to that based on BMI, both of which in turn are significantly higher than that gap suggested by the BIA method. In contrast however, the BMI approach suggests no difference in the obesity rate between black and white men, while our estimated true rates imply a significantly lower obesity rate for black men, which is in keeping with the findings from the BIA analysis.…”