ABSTRACT
BACKGROUND: Prevention of the vertical transmission of the hepatitis C virus (HCV) presents an obstetric challenge. There are no approved antiviral medications for the treatment or prevention of HCV for pregnant patients. OBJECTIVE: We aimed to create a composite score to accurately identify a population of pregnant patients with HCV who have high potential for vertical transmission. STUDY DESIGN: In a retrospective, multicenter cohort study, we identified pregnant patients with hepatitis C with linked data to their infants who have had HCV RNA or HCV antibody testing. Demographic data, including age and race/ethnicity, as well as clinical and laboratory data, including tobacco/alcohol use, infections, liver function tests, the HCV RNA titer, HCV antibody, HCV genotype, absolute lymphocyte count, and platelet count, were collected. Data were analyzed using logistic regression and receiver operating characteristics (ROCs) and internally validated using the forward selection bootstrap method. RESULTS: We identified 157 pregnant patients and 163 corresponding infants. The median maternal delivery age was 29 (IQR: 25-33) years, and the majority (141, or 89.8%) were White. A high HCV RNA titer, high absolute lymphocyte count, and high platelet count were associated with vertical transmission. A high HCV RNA titer had an AUROC of 0.815 with sensitivity, specificity, a positive predictive value, and a negative predictive value of 100.0%, 59.1%, 17.6%, and 100.0%, respectively. A composite score combining the three risk factors had an AUROC of 0.902 (95% CI = 0.840-0.964) but with a risk of overfitting. CONCLUSIONS: An HCV RNA titer alone or a composite score combining the risk factors for HCV vertical transmission can potentially identify a population of pregnant patients where the rate of vertical transmission is high, allowing for potential interventions during antepartum care.
ABSTRACT
A multi-sample test for equality of mean directions is developed for populations having Langevin-von Mises-Fisher distributions with a common unknown concentration. The proposed test statistic is a monotone transformation of the likelihood ratio. The high-concentration asymptotic null distribution of the test statistic is derived. In contrast to previously suggested high-concentration tests, the high-concentration asymptotic approximation to the null distribution of the proposed test statistic is also valid for large sample sizes with any fixed nonzero concentration parameter. Simulations of size and power show that the proposed test outperforms competing tests. An example with three-dimensional data from an anthropological study illustrates the practical application of the testing procedure.
ABSTRACT
The IOS test of Presnell and Boss (J. Am. Stat. Assoc. 2004; 99(465):216-227) is a general-purpose goodness-of-fit test based on the ratio of in-sample and out-of-sample likelihoods. For large samples, the IOS statistic can be approximated by a multiplicative contrast between two estimates of the information matrix, and in this way the IOS test is connected to White's (Econometrica 1982; 50:1-26) information matrix test, or IM test, which is based directly on the difference of two estimates of the information matrix. In this paper, we compare the performance of IOS to that of the IM test and of other goodness-of-fit tests for binomial and beta-binomial models, in both examples and simulations. Our findings suggest that IOS is strongly competitive, not only against the IM test but also against tests designed for specific binomial and beta-binomial models.
