A Retrospective Five-Year Study of Cardiovascular Risk Assessment and Risk-Based Interventions Among Hypertensive Patients in Nairobi Hospital, Kenya

Introduction Cardiovascular disease (CVD) is a leading cause of global morbidity and mortality. It is projected that the prevalence of CVD will continue to rise in developing countries, largely driven by an increase in the prevalence of potentially modifiable risk factors. Atherosclerotic cardiovascular risk assessment among individuals with risk factors for CVD but without CVD is an inexpensive and viable strategy in CVD risk stratification and prevention. Despite the known benefits of CVD risk assessment, it is not well established whether physicians/ cardiologists in Kenya comply with the guideline-recommended practice of CVD risk stratification as a prerequisite for initiation of primary CVD preventive interventions. Aims and objectives This study was designed to audit the utilization of cardiovascular risk assessment tools in risk stratification of hypertensive individuals and physician provision of risk-based primary CVD prevention interventions. Results A five-year (2017-2022) retrospective study of patients' medical records was conducted in December 2022 at the PrimeCare cardiology clinic in Nairobi Hospital, Kenya. Data were collected from 373 patients' medical records retrospectively. The data were analyzed using IBM SPSS Statistics for Windows, Version 25 (Released 2017; IBM Corp., Armonk, New York, United States). The mean age of the patients was 60 years with the majority being female (54%). The mean BMI was 30.3 kg/m2 while the mean systolic and diastolic pressure was 140mmHg and 80mmHg, respectively. Only 2.1% of participants were current smokers. The national or alternative guideline-recommended CVD risk assessment tool was used in 0.3% and 2.4%, respectively. The 10-year CVD risk score was documented in only 1.3%. The majority of the participants (93%) had low CVD risk. Half of the patients were taking statins for primary prevention while > 60% of them had been offered therapeutic lifestyle advice. Conclusion The study revealed poor compliance with guideline-recommended CVD risk assessment tools and documentation of the CVD risk level. However, there was above-average adherence to documentation of therapeutic lifestyle measures for primary CVD prevention.

Fitting and Testing Log-Linear Subpopulation Models with Known Support

In this paper, the support of the joint probability distribution of categorical variables in the total population is treated as unknown. From a general total population model with unknown support, a general subpopulation model with its support equal to the set of all observed score patterns is derived. In maximum likelihood estimation of the parameters of any such subpopulation model, the evaluation of the log-likelihood function only requires the summation over a number of terms equal to at most the sample size. It is made clear that the parameters of a hypothesized total population model are consistently and asymptotically efficiently estimated by the values that maximize the log-likelihood function of the corresponding subpopulation model. Next, new likelihood ratio goodness-of-fit tests are proposed as alternatives to the Pearson chi-square goodness-of-fit test and the likelihood ratio test against the saturated model. In a simulation study, the asymptotic bias and efficiency of maximum likelihood estimators and the asymptotic performance of the goodness-of-fit tests are investigated.

A unified approach based on multidimensional scaling for calibration estimation in survey sampling with qualitative auxiliary information

Survey calibration is a widely used method to estimate the population mean or total score of a target variable, particularly in medical research. In this procedure, auxiliary information related to the variable of interest is used to recalibrate the estimation weights. However, when the auxiliary information includes qualitative variables, traditional calibration techniques may be not feasible or the optimisation procedure may fail. In this article, we propose the use of linear calibration in conjunction with a multidimensional scaling-based set of continuous, uncorrelated auxiliary variables along with a suitable metric in a distance-based regression framework. The calibration weights are estimated using a projection of the auxiliary information on a low-dimensional Euclidean space. The approach becomes one of the linear calibration with quantitative variables avoiding the usual computational problems in the presence of qualitative auxiliary information. The new variables preserve the underlying assumption in linear calibration of a linear relationship between the auxiliary and target variables, and therefore the optimal properties of the linear calibration method remain true. The behaviour of this approach is examined using a Monte Carlo procedure and its value is illustrated by analysing real data sets and by comparing its performance with that of traditional calibration procedures.

A Novel Information-Theory-Based Genetic Distance That Approximates Phenotypic Differences

Application of genetic distances to measure phenotypic relatedness is a challenging task, reflecting the complex relationship between genotype and phenotype. Accurate assessment of proximity among sequences with different phenotypic traits depends on how strongly the chosen distance is associated with structural and functional properties. In this study, we present a new distance measure Mutual Information and Entropy H (MIH) for categorical data such as nucleotide or amino acid sequences. MIH applies an information matrix (IM), which is calculated from the data and captures heterogeneity of individual positions as measured by Shannon entropy and coordinated substitutions among positions as measured by mutual information. In general, MIH assigns low weights to differences occurring at high entropy positions or at dependent positions. MIH distance was compared with other common distances on two experimental and two simulated data sets. MIH showed the best ability to distinguish cross-immunoreactive sequence pairs from non-cross-immunoreactive pairs of variants of the hepatitis C virus hypervariable region 1 (26,883 pairwise comparisons), and Major Histocompatibility Complex (MHC) binding peptides (n = 181) from non-binding peptides (n = 129). Analysis of 74 simulated RNA secondary structures also showed that the ratio between MIH distance of sequences from the same RNA structure and MIH of sequences from different structures is three orders of magnitude greater than for Hamming distances. These findings indicate that lower MIH between two sequences is associated with greater probability of the sequences to belong to the same phenotype. Examination of rule-based phenotypes generated in silico showed that (1) MIH is strongly associated with phenotypic differences, (2) IM of sequences under selection is very different from IM generated under random scenarios, and (3) IM is robust to sampling. In conclusion, MIH strongly approximates structural/functional distances and should have important applications to a wide range of biological problems, including evolution, artificial selection of biological functions and structures, and measuring phenotypic similarity.

On the correspondence of deviances and maximum-likelihood and interval estimates from log-linear to logistic regression modelling

Consider a set of categorical variables P where at least one, denoted by Y, is binary. The log-linear model that describes the contingency table counts implies a logistic regression model, with outcome Y. Extending results from Christensen (1997, Log-linear models and logistic regression, 2nd edn. New York, NY, Springer), we prove that the maximum-likelihood estimates (MLE) of the logistic regression parameters equals the MLE for the corresponding log-linear model parameters, also considering the case where contingency table factors are not present in the corresponding logistic regression and some of the contingency table cells are collapsed together. We prove that, asymptotically, standard errors are also equal. These results demonstrate the extent to which inferences from the log-linear framework translate to inferences within the logistic regression framework, on the magnitude of main effects and interactions. Finally, we prove that the deviance of the log-linear model is equal to the deviance of the corresponding logistic regression, provided that no cell observations are collapsed together when one or more factors in P ∖ { Y } become obsolete. We illustrate the derived results with the analysis of a real dataset.

[A new method for agreement evaluation based on AC1]

Medical studies use various methods for assessing agreement among different raters or measurement methods. Many of these coefficients have limitations, and among them the paradoxes of kappa are the best known. To achieve a higher accuracy and reliability, we propose an alternative statistic method based on AC1, known as CEA, which adjusts the chance agreement. We explored the influences of the prevalence rate and chance agreement probability on the total agreement and compared the accuracy and stability of kappa, AC1 and CEA coefficient through simulations and real data analysis. The proposed method offers a stable and reliable option for assessing agreement of binary data.

Types of biological variables

Identification and description of variables used in any study is a necessary component in biomedical research. Statistical analyses rely on the type of variables that are involved in the study. In this short article, we introduce the different types of biological variables. A researcher has to be familiar with the type of variable he/she is dealing with in his/her research to decide about appropriate graphs/diagrams, summary measures and statistical analysis.

A variety of variables

In designing studies and developing plans for analyses, we must consider which tests are appropriate for the types of variables we are using. Here I describe the types of variables available to us, and I briefly consider the appropriate tools to use in their analysis.

Urinary arsenic species, toenail arsenic, and arsenic intake estimates in a Michigan population with low levels of arsenic in drinking water

The large disparity between arsenic concentrations in drinking water and urine remains unexplained. This study aims to evaluate predictors of urinary arsenic in a population exposed to low concentrations (≤50 μg/l) of arsenic in drinking water. Urine and drinking water samples were collected from a subsample (n=343) of a population enrolled in a bladder cancer case-control study in southeastern Michigan. Total arsenic in water and arsenic species in urine were determined using ICP-MS: arsenobetaine (AsB), arsenite (As[III]), arsenate (As[V]), methylarsenic acid (MMA[V]), and dimethylarsenic acid (DMA[V]). The sum of As[III], As[V], MMA[V], and DMA[V] was denoted as SumAs. Dietary information was obtained through a self-reported food intake questionnaire. Log(10)-transformed drinking water arsenic concentration at home was a significant (P<0.0001) predictor of SumAs (R(2)=0.18). Associations improved (R(2)=0.29, P<0.0001) when individuals with less than 1 μg/l of arsenic in drinking water were removed and further improved when analyses were applied to individuals who consumed amounts of home drinking water above the median volume (R(2)=0.40, P<0.0001). A separate analysis indicated that AsB and DMA[V] were significantly correlated with fish and shellfish consumption, which may suggest that seafood intake influences DMA[V] excretion. The Spearman correlation between arsenic concentration in toenails and SumAs was 0.36 and between arsenic concentration in toenails and arsenic concentration in water was 0.42. Results show that arsenic exposure from drinking water consumption is an important determinant of urinary arsenic concentrations, even in a population exposed to relatively low levels of arsenic in drinking water, and suggest that seafood intake may influence urinary DMA[V] concentrations.