RESUMO
Many statistical models have been proposed in the literature for the analysis of longitudinal data. One may propose to model two or more correlated longitudinal processes simultaneously, with a goal of understanding their association over time. Joint modeling is then required to carefully study the association structure among the outcomes as well as drawing joint inferences about the different outcomes. In this study, we sought to model the associations among six nutrition outcomes while circumventing the computational challenge posed by their clustered and high-dimensional nature. We analyzed data from a 2 × $\times$ 2 randomized crossover trial conducted in Kenya, to compare the effect of high-dose and low-dose iodine in household salt on systolic blood pressure (SBP) and diastolic blood pressure (DBP) in women of reproductive age and their household matching pair of school-aged children. Two additional outcomes, namely, urinary iodine concentration (UIC) in women and children were measured repeatedly to monitor the amount of iodine excreted through urine. We extended the model proposed by Mwangi et al. (2021, Communications in Statistics: Case Studies, Data Analysis and Applications, 7(3), 413-431) allowing flexible piecewise joint models for six outcomes to depend on separate random effects, which are themselves correlated. This entailed fitting 15 bivariate general linear mixed models and deriving inference for the joint model using pseudo-likelihood theory. We analyzed the outcomes separately and jointly using piecewise linear mixed-effects (PLME) model and further validated the results using current state-of-the-art Jones and Kenward methodology (JKME model) used for analyzing randomized crossover trials. The results indicate that high-dose iodine in salt significantly reduced blood pressure (BP) compared to low-dose iodine in salt. Estimates for the random effects and residual error components showed that SBP and DBP had strong positive correlation, with effect of the random slope indicating that significantly related outcomes are strongly associated in their evolution. There was a moderately strong inverse relationship between evolutions of UIC and BP both in women and children. These findings confirmed the original hypothesis that high-dose iodine salt has significant lowering effect on BP. We further sought to evaluate the performance of our proposed PLME model against the widely used JKME model, within the multivariate joint modeling framework through a simulation study mimicking a 2 × 2 $2\times 2$ crossover design. From our findings, the multivariate joint PLME model performed exceptionally well both in estimation of random-effects matrix (G) and Hessian matrix (H), allowing satisfactory model convergence during estimation. It allowed a more complex fit to the data with both random intercepts and slopes effects compared to the multivariate joint JKME model that allowed for random intercepts only. When a hierarchical viewpoint is adopted, in the sense that outcomes are specified conditionally upon random effects, the variance-covariance matrix of the random effects must be positive definite. In some cases, additional random effects could explain much variability in the data, thus improving precision in estimation of the estimands (effect size) parameters. The key highlight in this evaluation shows that multivariate joint JKME model is a powerful tool especially while fitting mixed models with random intercepts only, in crossover design settings. Addition of random slopes may lead to model complexities in most cases, resulting in unsatisfactory model convergence during estimation. To circumvent convergence pitfalls, extention of JKME model to PLME model allows a more flexible fit to the data (generated from crossover design settings), especially in the multivariate joint modeling framework.
Assuntos
Iodo , Modelos Estatísticos , Criança , Feminino , Humanos , Estudos Cross-Over , Modelos Lineares , Estudos Longitudinais , Adulto , Ensaios Clínicos Controlados Aleatórios como AssuntoRESUMO
Cross-over designs are commonly used in randomized clinical trials to estimate efficacy of a new treatment. They have received a lot of attention, particularly in connection with regulatory requirements for new drugs. The main advantage of using cross-over designs over conventional parallel designs is increased precision, thanks to within-subject comparisons. In the statistical literature, more recent developments are discussed in the analysis of cross-over trials, in particular regarding repeated measures. A piecewise linear model within the framework of mixed effects has been proposed in the analysis of cross-over trials. In this article, we report on a simulation study comparing performance of a piecewise linear mixed-effects (PLME) model against two commonly cited models-Grizzle's mixed-effects (GME) and Jones & Kenward's mixed-effects (JKME) models-used in the analysis of cross-over trials. Our simulation study tried to mirror real-life situation by deriving true underlying parameters from empirical data. The findings from real-life data confirmed the original hypothesis that high-dose iodine salt have significantly lowering effect on diastolic blood pressure (DBP). We further sought to evaluate the performance of PLME model against GME and JKME models, within univariate modeling framework through a simulation study mimicking a 2 × 2 cross-over design. The fixed-effects, random-effects and residual error parameters used in the simulation process were estimated from DBP data, using a PLME model. The initial results with full specification of random intercept and slope(s), showed that the univariate PLME model performed better than the GME and JKME models in estimation of variance-covariance matrix (G) governing the random effects, allowing satisfactory model convergence during estimation. When a hierarchical view-point is adopted, in the sense that outcomes are specified conditionally upon random effects, the variance-covariance matrix of the random effects must be positive-definite. The PLME model is preferred especially in modeling an increased number of random effects, compared to the GME and JKME models that work equally well with random intercepts only. In some cases, additional random effects could explain much variability in the data, thus improving precision in estimation of the estimands (effect size) parameters.
Assuntos
Simulação por Computador , Estudos Cross-Over , Ensaios Clínicos Controlados Aleatórios como Assunto , Humanos , Ensaios Clínicos Controlados Aleatórios como Assunto/métodos , Ensaios Clínicos Controlados Aleatórios como Assunto/estatística & dados numéricos , Modelos Lineares , Projetos de Pesquisa , Modelos Estatísticos , Interpretação Estatística de Dados , Pressão Sanguínea/efeitos dos fármacosRESUMO
BACKGROUND: Malnutrition is a universal problem in cancer patients renowned as an important factor for increased morbidity, decreased quality of life and high mortality. Early diagnosis of malnutrition risk through nutrition screening followed by comprehensive and timely interventions reduces mortality associated with malnutrition. The Scored Patient-Generated Subjective Global Assessment (PGSGA) method has been proved efficient in identifying cancer patients with nutrition challenges and guiding appropriate interventions. However this tool has not been adopted in management of cancer patients in Kenya. The aim of the study was to assess and describe nutrition status of cancer outpatients receiving treatment at Kenyatta National Hospital Hospital (KNH) and Texas Cancer Centre (TCC). METHODS: The study adopted a hospital based descriptive cross sectional study. Cancer outpatients with confirmed stage 1-4 cancers, physically stable, aged 18 years and above and receiving cancer treatment were recruited and assessed using Scored PGSGA tool. Proportions, measures of central tendency and pearsons' chi-square test were used in statistical analysis. RESULTS: Among the 471 participants assessed, 71.8% were female and 28.2% male. Most participants had stage 2, 3 and 4 cancers at 27.2%, 27.2% and 24.3% respectively. Highest proportion of participants had breast (29.7%) and female genital cancers (22.9%). Sixty nine percent of participants were well nourished (SGA-A), 19.7% moderately malnourished (SGA-B) and 11.3% severely malnourished (SGA-C) and this difference was statistically significant. The mean PGSGA score was 6.76 (SD 5.17). Based on the score, 33.8% of participants required critical nutrition care, 34.8% symptoms management, 14.2% constant nutrition education and pharmacological intervention while 17.2% required routine assessments and reassurance. More (m;54.7%, f; 45.3%) males than females were severely malnourished(SGA-C) and this was statistically significant (P < 0.001).Prevalence of severe malnutrition was highest among participants with digestive organ cancers (49.1%) followed by those with lip cancer (17%) and the least prevalence reported in those with Karposi Sarcoma (0%). Most of stage 4 participants were moderately (37.5%) and severely (29.4%) malnourished. CONCLUSIONS: The Scored Patient-Generated Subjective Global Assessment is able to identify cancer patients both at risk of malnutrition and those severely malnourished. It also provides a guideline on the appropriate nutrition intervention hence an important tool in nutrition management of cancer patients.
RESUMO
BACKGROUND: A measure of the proportion of deliveries assisted by skilled attendants is one of the indicators of progress towards achieving Millennium Development Goal (MDG) 5, which aims at improving maternal health. This study aimed at establishing delivery practices and associated factors among mothers seeking child welfare services at selected health facilities in Nyandarua South district, Kenya to determine whether mothers were receiving appropriate delivery care. METHODS: A hospital-based cross-sectional survey among women who had recently delivered while in the study area was carried out between August and October 2009. Binary Logistic regression was used to identify factors that predicted mothers' delivery practice. RESULTS: Among the 409 mothers who participated in the study, 1170 deliveries were reported. Of all the deliveries reported, 51.8% were attended by unskilled birth attendants. Among the deliveries attended by unskilled birth attendants, 38.6% (452/1170) were by neighbors and/or relatives. Traditional Birth Attendants attended 1.5% (17/1170) of the deliveries while in 11.7% (137/1170) of the deliveries were self administered. Mothers who had unskilled birth attendance were more likely to have <3 years of education (Adjusted Odds ratio [AOR] 19.2, 95% confidence interval [CI] 1.7 - 212.8) and with more than three deliveries in a life time (AOR 3.8, 95% CI 2.3 - 6.4). Mothers with perceived similarity in delivery attendance among skilled and unskilled delivery attendants were associated with unsafe delivery practice (AOR 1.9, 95% CI 1.1 - 3.4). Mother's with lower knowledge score on safe delivery (%) were more likely to have unskilled delivery attendance (AOR 36.5, 95% CI 4.3 - 309.3). CONCLUSION: Among the mothers interviewed, utilization of skilled delivery attendance services was still low with a high number of deliveries being attended by unqualified lay persons. There is need to implement cost effective and sustainable measures to improve the quality of maternal health services with an aim of promoting safe delivery and hence reducing maternal mortality.