Search

Latent classification model is a class of statistical methods for identifying unobserved class membership among the study samples using some observed data. In this study, we proposed a latent classification model that takes a censored longitudinal binary outcome variable and uses its changing pattern over time to predict individuals' latent class membership. Assuming the time‐dependent outcome variables follow a continuous‐time Markov chain, the proposed method has two primary goals: (1) estimate the distribution of the latent classes and predict individuals' class membership, and (2) estimate the class‐specific transition rates and rate ratios. To assess the model's performance, we conducted a simulation study and verified that our algorithm produces accurate model estimates (ie, small bias) with reasonable confidence intervals (ie, achieving approximately 95% coverage probability). Furthermore, we compared our model to four other existing latent class models and demonstrated that our approach yields higher prediction accuracies for latent classes. We applied our proposed method to analyze the COVID‐19 data in Houston, Texas, US collected between January first 2021 and December 31st 2021. Early reports on the COVID‐19 pandemic showed that the severity of a SARS‐CoV‐2 infection tends to vary greatly by cases. We found that while demographic characteristics explain some of the differences in individuals' experience with COVID‐19, some unaccounted‐for latent variables were associated with the disease. [ABSTRACT FROM AUTHOR]

Recurrent events can occur more than once in the same individual; such events may be of different types, known as multitype recurrent events. They are very common in longitudinal studies. Often there is a terminating event, after which no further events can occur. The risk of any event, including terminating events such as death or cure, is typically affected by prior events. We propose a flexible joint multitype recurrent-events model that explicitly provides estimates of the change in risk for each event due to subject characteristics, including number and type of prior events and the absolute risk for every event type (terminating and nonterminating), and predicts event-free survival probability over a desired time period. The model is fully parametric, and therefore a standard likelihood function and robust standard errors can be constructed. We illustrate the model with applications to the Antihypertensive and Lipid-Lowering Treatment to Prevent Heart Attack Trial (1994–2002) and provide discussion of the results and model features. [ABSTRACT FROM AUTHOR]

Objective: To identify dietary patterns (DP) of children enrolled in the Family Weight Management Study (FWMS) and to examine relationship between the identified DP with demographics. Design: We performed a cross-sectional analysis of baseline data from 332 children (BMI ≥85th percentile for age and sex and 7–12 years old) who were enrolled in the FWMS. The Block Kids Food Frequency Questionnaire was used to assess dietary intake. Principal component analysis was conducted to identify DPs. Setting: Participants were recruited from Jacobi Medical Center, Bronx, NY from July 2009 – December 2011. Results: The mean age of the children was 9.3 (±1.7 SD) years; about half were female and 75% self-identified as Hispanic/Latino. The majority of parents/guardians were born outside of the mainland USA and half had less than a high school education. We identified a "pizza-pasta" DP (high loadings of pizza, pasta, red meat, chicken, fries, sweets, processed meat, and sweet breads) and a "snacks-dessert" DP (high loadings of snacks, desserts, soft drinks, and bread and refined grains) but no healthy patterns with high loadings of fruit, vegetables, nuts, and dairy products. The "pizza-pasta" pattern was associated with parents/guardian being born in the mainland USA and having a higher educational level (p < 0.05) whereas the "snack-dessert" pattern was not significantly associated with any of the demographic variables. Conclusion: Our findings suggest that poor DP is common among second-generation immigrant Hispanic/Latino children who are obese/overweight. Future research needs to address how parental education and acculturation status are related to DP to inform future directions for preventing childhood obesity. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to assess the effectiveness of metformin for antipsychotic-induced weight gain (AIWG) and determine whether the timing of metformin initiation and premorbid obesity moderated metformin effectiveness in children and adolescents on treatment with second-generation antipsychotics (SGAs)., Methods: A cohort of individuals 6 to 17 years of age, from 2016 to 2021, initiating a new SGA treatment and receiving a subsequent metformin prescription during SGA treatment were identified from the IQVIA Ambulatory EMR-US database. The changes in body mass index (BMI) z score before and after metformin initiation were assessed using the piecewise linear mixed-effects regression model., Results: The results showed that the initiation of metformin was associated with a flattening out of the prior-metformin BMI z score trend. Relative to those who did not use metformin, metformin users had an additional monthly decrease in BMI z score of -0.053 ( P  = .0008) during the 6-month period after metformin initiation. Specifically, users who were non-obese before the intervention experienced a greater reduction in the BMI z score slope compared to those who were mildly-to-moderately obese and severely obese (non-obese - mildly-to-moderately obese: -0.07631, P  = .0001; non-obese - severely obese: -0.09613, P  < .0001). A different effect was not observed between patients who initiated metformin within versus beyond 90 days of SGA initiation. Extending the observation period to 12 months yielded comparable findings., Conclusions: Adjuvant metformin helps manage AIWG in children and adolescents by flattening the upward AIWG trend rather than reversing it. The effect was more prominent before the development of obesity, suggesting that the early introduction of metformin for AIWG management may be warranted., (© Copyright 2023 Physicians Postgraduate Press, Inc.)

Background: Preventing HIV infection remains a critically important tool in the continuing fight against HIV/AIDS. The primary aim is to evaluate the effect and interactions between a composite area-level social determinants of health measure and an area-level measure of residential segregation on the risk of HIV/AIDS in U.S. Veterans., Methods: Using the individual-level patient data from the U.S. Department of Veterans Affairs, we constructed a case-control study of veterans living with HIV/AIDS (VLWH) and age-, sex assigned at birth- and index date-matched controls. We geocoded patient's residential address to ascertain their neighborhood and linked their information to two measures of neighborhood-level disadvantage: area deprivation index (ADI) and isolation index (ISOL). We used logistic regression to estimate the odds ratio (OR) and 95% confidence interval (CI) for comparing VLWH with matched controls. We performed analyses for the entire U.S. and separately for each U.S. Census division., Findings: Overall, living in minority-segregated neighborhoods was associated with a higher risk of HIV (OR: 1.88 (95% CI: 1.79-1.97) while living in higher ADI neighborhoods was associated with a lower risk of HIV (OR: 0.88; 95% CI: 0.84-0.92). The association between living in a higher ADI neighborhood and HIV was inconsistent across divisions, while living in minority-segregated neighborhoods was consistently associated with increased risk across all divisions. In the interaction model, individuals from low ADI and high ISOL neighborhoods had a higher risk of HIV in three divisions: East South Central; West South Central, and Pacific., Interpretation: Our results suggest that residential segregation may prevent people in disadvantaged neighborhoods from protecting themselves from HIV independent from access to health care. There is the need to advance knowledge about the neighborhood-level social-structural factors that influence HIV vulnerability toward developing interventions needed to achieve the goal of ending the HIV epidemic., Funding: US National Cancer Institute., Competing Interests: None reported., (© 2023 The Author(s).)