RESUMEN
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.
Asunto(s)
Algoritmos , COVID-19 , Análisis de Clases Latentes , Cadenas de Markov , Humanos , COVID-19/epidemiología , Estudios Longitudinales , Simulación por Computador , Modelos Estadísticos , Texas/epidemiología , SARS-CoV-2 , FemeninoRESUMEN
This study investigates the two-mode core-periphery structures of venue affiliation networks of younger Black men who have sex with men (YBMSM). We examined the association between these structures and HIV phylogenetic clusters, defined as members who share highly similar HIV strains that are regarded as a proxy for sexual affiliation networks. Using data from 114 YBMSM who are living with HIV in two large U.S. cities, we found that HIV phylogenetic clustering patterns were associated with social clustering patterns whose members share affiliation with core venues that overlap with those of YBMSM. Distinct HIV transmission patterns were found in each city, a finding that can help to inform tailored venue-based and network intervention strategies.
RESUMEN
PURPOSE: To determine risk factors that affect nonproliferative diabetic retinopathy (NPDR) progression and establish a predictive model to estimate the probability of and time to progression in NPDR. Patients and Methods. Charts of diabetic patients who received an initial eye exam between 2010 and 2017 at our county hospital were included. Patients with proliferative diabetic retinopathy (PDR), fewer than 2 years of follow-up, or fewer than 3 clinic visits were excluded. Demographics and baseline systemic and ocular characteristics were recorded. Follow-up mean annual HbA1c and blood pressure, best-corrected visual acuity, and the number of antivascular endothelial growth factor treatments were recorded. Stage and date of progression were recorded. A 5-state nonhomogeneous continuous-time Markov chain with a backward elimination model was used to identify risk factors and estimate their effects on progression. RESULTS: Two hundred thirty patients were included. Initially, 65 eyes (28.3%) had no retinopathy; 73 (31.7%) mild NPDR; 60 (26.1%) moderate NPDR; and 32 (13.9%) severe NPDR. Patients were followed for a mean of 5.8 years (±2.0 years; range 2.1-9.4 years). 164 (71.3%) eyes progressed during the follow-up. Time-independent risk factors affecting progression rate were age (hazard ratio (HR) = 0.99, P=0.047), duration of diabetes (HR = 1.02, P=0.018), and Hispanic ethnicity (HR = 1.31, P=0.068). Mean sojourn times at mean age, duration of diabetes, and annual HbA1c for a non-Hispanic patient were estimated to be 3.03 (±0.97), 4.63 (±1.21), 6.18 (±1.45), and 4.85 (±1.25) years for no retinopathy, mild NPDR, moderate NPDR, and severe NPDR, respectively. Each 1% increase in HbA1c annually diminished sojourn times by 15%, 10%, 7%, and 10% for no retinopathy, mild NPDR, moderate NPDR, and severe NPDR, respectively. CONCLUSION: HbA1c level is a significant modifiable risk factor in controlling the progression of DR. The proposed model could be used to predict the time and rate of progression based on an individual's risk factors. A prospective multicenter study should be conducted to further validate our model.