Marginal Models Research Articles

Trends, risk factors and interventions for some mental health problems in the US children and adolescents: evidence from the National Survey of Children’s Health, 2016-2022

PurposeThe purpose of this study is threefold: Determine recent trends in several mental health problems in the USA, identify risk factors that may be responsible for the trends and evaluate intervention policies to reduce the consequences of these problems.Design/methodology/approachThis study used data from the National Survey of Children's Health (NSCH), a nationally representative survey of children under the age of 17 that was conducted between 2016 and 2022. Prevalence rates in the data take into account the probability of selection and nonresponse. Because of the possible correlation in the longitudinal responses in the data, an appropriate extension of the generalized linear models (the marginal models) was used. Marginal models, also known as population-average models, do not require distributional assumptions for the observations, only a regression model for the mean response. The avoidance of distributional assumptions leads to the use of the generalized estimating equations (GEE) method.FindingsThe author found that the odds of children and adolescents experiencing mental health problems in the USA changed over a seven-year period, from 2016 to 2022. Anxiety and depression, in particular, have both increased, with anxiety increasing faster than depression; however, behavioral issues and attention deficit disorder/attention deficit hyperactivity disoder (ADD/ADHD) remained stable until 2020 (the start of COVID-19), when they began to rise. This paper also found a link between increased social media use and increased mental health problems, and bullying has a negative impact on the mental health of children and adolescents.Originality/valueThe NSCH, an annual representative survey, was used in this study to assess mental health problems among children and adolescents in the USA. Marginal models, which enable the capture of potential correlations among observations of the same subject, were used in conjunction with the GEE method. This study differs from previous research, which used other surveys, pre-COVID-19 data points and logistic regressions that assumed independence in repeated observations.

GLP-1RA vs DPP-4i Use and Rates of Hyperkalemia and RAS Blockade Discontinuation in Type 2 Diabetes

Hyperkalemia is a common complication in people with type 2 diabetes (T2D) that may limit the use of guideline-recommended renin-angiotensin system inhibitors (RASis). Emerging evidence suggests that glucagon-like peptide-1 receptor agonists (GLP-1RAs) increase urinary potassium excretion, which may translate into reduced hyperkalemia risk. To compare rates of hyperkalemia and RASi persistence among new users of GLP-1RAs vs dipeptidyl peptidase-4 inhibitors (DPP-4is). This cohort study included all adults with T2D in the region of Stockholm, Sweden, who initiated GLP-1RA or DPP-4i treatment between January 1, 2008, and December 31, 2021. Analyses were conducted between October 1, 2023, and April 29, 2024. GLP-1RAs or DPP-4is. The primary study outcome was time to any hyperkalemia (potassium level >5.0 mEq/L) and moderate to severe (potassium level >5.5 mEq/L) hyperkalemia. Time to discontinuation of RASi use among individuals using RASis at baseline was assessed. Inverse probability of treatment weights served to balance more than 70 identified confounders. Marginal structure models were used to estimate per-protocol hazard ratios (HRs). A total of 33 280 individuals (13 633 using GLP-1RAs and 19 647 using DPP-4is; mean [SD] age, 63.7 [12.6] years; 19 853 [59.7%] male) were included. The median (IQR) time receiving treatment was 3.9 (1.0-10.9) months. Compared with DPP-4i use, GLP-1RA use was associated with a lower rate of any hyperkalemia (HR, 0.61; 95% CI, 0.50-0.76) and moderate to severe (HR, 0.52; 95% CI, 0.28-0.84) hyperkalemia. Of 21 751 participants who were using RASis, 1381 discontinued this therapy. The use of GLP-1RAs vs DPP-4is was associated with a lower rate of RASi discontinuation (HR, 0.89; 95% CI, 0.82-0.97). Results were consistent in intention-to-treat analyses and across strata of age, sex, cardiovascular comorbidity, and baseline kidney function. In this study of patients with T2D managed in routine clinical care, the use of GLP-1RAs was associated with lower rates of hyperkalemia and sustained RASi use compared with DPP-4i use. These findings suggest that GLP-1RA treatment may enable wider use of guideline-recommended medications and contribute to clinical outcomes in this population.

Anti-SARS-CoV-2 mRNA vaccination among patients living with SLE in Sweden: Coverage and clinical effectiveness.

To describe the uptake of anti-SARS-CoV2 vaccination in 2021 and investigate vaccine effectiveness in systemic lupus erythematosus (SLE) patients in Sweden. The cumulative incidence of first anti-SARS-CoV2 vaccination was estimated among SLE patients from the Swedish National Patient Register and matched comparators living in Sweden on January 1, 2021. To assess vaccine effectiveness, we included the individuals who received two doses of anti-SARS-CoV2 mRNA vaccines before year 2022, with no COVID-19 diagnosis code before the 2nd vaccine dose. Hospitalization rates with COVID-19 as main diagnosis during the year after second dose were compared between SLE patients and comparators in multivariable-adjusted marginal Cox models, overall and stratified by immunosuppressive treatment received during the year before second vaccine dose. Vaccination uptake was similar between SLE patients and comparators. By December 2021, 9% of both SLE and comparators had not received any vaccine doses. Among 5585 SLE patients and 37,102 comparators, 11 COVID-19 hospitalizations in the SLE group and 20 in the comparators occurred. SLE was associated with a higher risk of COVID-19 hospitalization (HR = 3.47, 95%CI 1.63-7.39). The HR was higher for immunosuppressive-treated SLE (7.03 95%CI 3.00-16.46) than for immunosuppressive-untreated (1.50 95%CI 0.34-6.60). Vaccination of immunosuppressive-untreated SLE patients had similar effectiveness as comparators. Anti-SARS-CoV2 vaccination coverage was similar between SLE patients and the general population in Sweden. Even though the incidence of post-vaccination COVID-19 hospitalization was very low, vaccine effectiveness was diminished in SLE patients compared to the general population and lowest in those treated with immunosuppressants.

Assessing genetic and environmental components for pterygium: a nationwide study in Taiwan

This study aims to estimate the familial risks of pterygium and assess its relative contributions to environmental and genetic factors using the 2000–2017 Taiwan National Health Insurance Research Database. The marginal Cox's model and the polygenic liability model were made. In Taiwan, the prevalence rate of pterygium in 2017 was 1.64% for individuals with affected first-degree relatives, higher than the general population (1.34%). The adjusted relative risk (RR) for pterygium was highest for twins of the same sex (15.54), followed by siblings of the same sex (4.69), offsprings (3.39), siblings of the different sex (2.88), spouse (2.12), parents (1.86), twins of the different sex (1.57), respectively. The phenotypic variance of pterygium was 21.6% from additive genetic variance, 24.3% from common environmental factors shared by family members, and 54.1% from non-shared environmental factors, respectively. Sensitivity analysis by restricting those with surgical pterygium reveals that aRRs and the three components were similar to those of the overall pterygium. In summary, the prevalence rate of pterygium was higher for individuals with affected first-degree relatives than for the general population. The non-shared environmental factors account for half of the phenotypic variance of pterygium; genetic and shared environmental factors explain the rest.

A Copula Discretization of Time Series-Type Model for Examining Climate Data

The study presents a comparative analysis of climate data under two scenarios: a Gaussian copula marginal regression model for count time series data and a copula-based bivariate count time series model. These models, built after comprehensive simulations, offer adaptable autocorrelation structures considering the daily average temperature and humidity data observed at a regional airport in Mobile, AL.

Assessment of Baseline Ultrawidefield Fluorescein Angiographic Quantitative Leakage Parameters with Ultrawidefield Fundus Features and Clinical Parameters in Diabetic Retinopathy in Protocol AA

PurposeEvaluate quantitative leakage parameters on ultra-widefield fluorescein angiography (UWF-FA) images and explore their association with Diabetic Retinopathy Severity Scale (DRSS), predominantly peripheral lesions (PPLs), visual acuity, and clinical characteristics. DesignA post-hoc analysis of baseline UWF-FA images in the DRCR Retina Network observational study Protocol AA. ParticipantsN = 575 eyes from 384 adults across 38 sites in the US and Canada with gradable UWF-FA. MethodsA machine learning-enhanced feature extraction platform provided initial leakage segmentation of UWF-FA images sequentially reviewed and corrected by two certified readers for segmentation accuracy. UWF-FA leakage was measured in five retinal zones: panretinal (whole retina), central macular (3-disc diameter fovea-centered circle), posterior pole (6-disc diameter fovea-centered circle), peripheral (outside 6-disc diameter circle) and widefield far peripheral (outside 9-disc diameter circle); associations with clinical factors were evaluated with marginal beta regression models. Main Outcome MeasuresUWF-FA leakage index, calculated as the area with leakage divided by the analyzable retinal area. ResultsThe mean quantitative leakage index was 3.5% for panretinal, 6.6% for macular, 4.8% for posterior pole, 3.3% for peripheral and 2.8% for wide-field far peripheral retinal zones. Panretinal leakage was associated with DRSS (mean 2.2% for no to mild NPDR, 3.4% for moderate NPDR, 4.2% for moderately severe NPDR, 4.8% for severe NPDR and 5.1% for PDR; P<.001), HbA1c (3.2% for HbA1c <8% vs. 3.8% for HbA1c ≥8%; P=.01 for continuous HbA1c), visual acuity (3.3% for 20/25 or better vs. 4.7% for 20/32 or worse; continuous P<.001), and UWF-FA-PPL types of IRMA (4.3% vs. 3.3%; P=.005) or NVE (5.7% vs. 3.4%; P=.003). DRSS was also statistically significant for leakage within all retinal zones (P<.001); eyes with non-central DME versus no DME had higher mean leakage in the central macular (11.2% vs. 5.9%; P=0.005) and posterior pole regions (9.2% vs. 4.2%; P=.002). ConclusionQuantitative UWF-FA leakage analysis identified associations between leakage and DRSS, visual acuity, and presence of DME. In the future, quantitative UWF-FA leakage parameters may be explored as potential biomarkers for disease progression risk.

Soil Marginal Effect and LSTM Model in Chinese Solar Greenhouse.

The food crisis has increased demand for agricultural resources due to various factors such as extreme weather, energy crises, and conflicts. A solar greenhouse enables counter-seasonal winter cultivation due to its thermal insulation, thus alleviating the food crisis. The root temperature is of critical importance, although the mechanism of soil thermal environment change remains uncertain. This paper presents a comprehensive study of the soil thermal environment of a solar greenhouse in Jinzhong City, Shanxi Province, employing a variety of analytical techniques, including theoretical, experimental, and numerical simulation, and deep learning modelling. The results of this study demonstrate the following: During the overwintering period, the thermal environment of the solar greenhouse floor was divided into a low-temperature zone, a constant-temperature zone, and a high-temperature zone; the distance between the low-temperature boundary and the southern foot was 2.6 m. The lowest temperature in the low-temperature zone was 11.06 °C and the highest was 19.05 °C. The floor in the low-temperature zone had to be heated; the lowest value of the constant-temperature zone was 18.29 °C, without heating. The minimum distance between the area of high temperature and the southern foot of the solar greenhouse was 8 m and the lowest temperature reading was 19.29 °C. The indoor soil temperature tended to stabilise at a depth of 45 cm, and the lowest temperature reading at a horizontal distance of 1400 mm from the south foot was 19.5 °C. The Fluent and LSTM models fitted well and the models can be used to help control soil temperature during overwintering in extreme climates. The research can provide theoretical and data support for the crop areas and the heating of pipelines in the solar greenhouse.

The Marginal Effect and LSTM Prediction Model under the Chinese Solar Greenhouse Film

The solar greenhouse is a significant agricultural facility in China. It enables the cultivation of crops during periods that do not coincide with the natural growing season, thus alleviating the pressure on the supply of fruits and vegetables during the winter months. The primary rationale behind the necessity of greenhouse cultivation lies in the fact that the temperature conditions conducive to optimal crop growth can be precisely replicated within this controlled environment. However, it is important to acknowledge that a distinct low-temperature area persists under the film during the overwintering period, with the precise delineation of its boundaries and distribution patterns remaining uncertain. In order to investigate the characteristics of the temperature distribution within the marginal region under the solar greenhouse film, experimental studies, CFD simulations, and LSTM prediction models were employed. The results of these studies indicate that, during the overwintering period, a low-temperature region was observed with approximately equal temperatures near the film membrane. The maximum horizontal distance from the south-side bottom corner was 6130 mm, while the minimum height from the ground was 600 mm. The lowest temperature in the low-temperature region was 4 °C, and the maximum observed temperature difference within the same period in different months was 1 °C. Additionally, a region of elevated temperatures was observed under the film. The lowest temperature in this region was 36.7 °C, and the highest temperature point was within the optimal range for crop growth. The CFD numerical simulation results were consistent with the actual observations, and the LSTM prediction model demonstrated high reliability. The findings of this study offer a theoretical foundation for the distribution of high and low temperatures in solar greenhouses. Furthermore, the developed prediction model provides the necessary buffer time for control, thus enhancing the efficiency of greenhouse cultivation.

Distributed Resources Allocation Method for Space-Ground Integrated Mobile Communication System.

This paper presents an innovative approach towards space-ground integrated communication systems by combining terrestrial cellular networks, UAV networks, and satellite networks, leveraging advanced slicing technology. The proposed architecture addresses the challenges posed by future user surges and aims to reduce network overhead effectively. Central to our approach is the introduction of a marginal mobile station (MS)-assisted network resource allocation decision architecture. Building upon this foundation, we introduce the DP-DQN model, an enhanced decision-making algorithm tailored for MSs in dynamic network environments. Furthermore, this study introduces a feedback mechanism to ensure the accuracy and adaptability of the marginalization model over time. Through extensive simulations and experimental validations, our DP-DQN-based edge decision method demonstrates substantial potential in alleviating core network overhead while improving success access ratios compared to conventional methods.

Comparative analysis of genetic risk scores for predicting biochemical recurrence in prostate cancer patients after radical prostatectomy

BackgroundIn recent years, Genome-Wide Association Studies (GWAS) has identified risk variants related to complex diseases, but most genetic variants have less impact on phenotypes. To solve the above problems, methods that can use variants with low genetic effects, such as genetic risk score (GRS), have been developed to predict disease risk.MethodsAs the GRS model with the most incredible prediction power for complex diseases has not been determined, our study used simulation data and prostate cancer data to explore the disease prediction power of three GRS models, including the simple count genetic risk score (SC-GRS), the direct logistic regression genetic risk score (DL-GRS), and the explained variance weighted GRS based on directed logistic regression (EVDL-GRS).Results and ConclusionsWe used 26 SNPs to establish GRS models to predict the risk of biochemical recurrence (BCR) after radical prostatectomy. Combining clinical variables such as age at diagnosis, body mass index, prostate-specific antigen, Gleason score, pathologic T stage, and surgical margin and GRS models has better predictive power for BCR. The results of simulation data (statistical power = 0.707) and prostate cancer data (area under curve = 0.8462) show that DL-GRS has the best prediction performance. The rs455192 was the most relevant locus for BCR (p = 2.496 × 10–6) in our study.

Simultaneous Inference of Multiple Binary Endpoints in Biomedical Research: Small Sample Properties of Multiple Marginal Models and a Resampling Approach.

In biomedical research, the simultaneous inference of multiple binary endpoints may be of interest. In such cases, an appropriate multiplicity adjustment is required that controls the family-wise error rate, which represents the probability of making incorrect test decisions. In this paper, we investigate two approaches that perform single-step -value adjustments that also take into account the possible correlation between endpoints. A rather novel and flexible approach known as multiple marginal models is considered, which is based on stacking of the parameter estimates of the marginal models and deriving their joint asymptotic distribution. We also investigate a nonparametric vector-based resampling approach, and we compare both approaches with the Bonferroni method by examining the family-wise error rate and power for different parameter settings, including low proportions and small sample sizes. The results show that the resampling-based approach consistently outperforms the other methods in terms of power, while still controlling the family-wise error rate. The multiple marginal models approach, on the other hand, shows a more conservative behavior. However, it offers more versatility in application, allowing for more complex models or straightforward computation of simultaneous confidence intervals. The practical application of the methods is demonstrated using a toxicological dataset from the National ToxicologyProgram.

Impact of Pirfenidone on Patient-Reported Outcomes in Patients With Idiopathic Pulmonary Fibrosis From the Pulmonary Fibrosis Foundation Patient Registry

BACKGROUNDPatients with idiopathic pulmonary fibrosis (IPF) experience debilitating symptoms. While antifibrotics may slow lung function decline, their impact on patients’ health-related quality of life (HRQoL) and disease symptoms in the real world remains unknown. RESEARCH QUESTIONWhat is the impact of pirfenidone vs no treatment on HRQoL and IPF-related symptoms of cough, dyspnea, and fatigue? STUDY DESIGN AND METHODSThis retrospective analysis included patients with IPF aged ≥ 55 years enrolled in the Pulmonary Fibrosis Foundation Patient Registry between March 2016 and December 2021. Change from baseline in patient-reported outcome measures (PROMs) including the Leicester Cough Questionnaire (LCQ), University of California, San Diego Shortness of Breath Questionnaire (UCSD SOBQ), Fatigue Severity Scale, and Short Form-6 Dimension questionnaire were assessed at Months 6, 12, and 18 in patients receiving pirfenidone vs no treatment. A marginal structure model (MSM) accounted for time-varying confounding caused by percent predicted forced vital capacity (%FVC) and percent predicted diffusing capacity of the lung for carbon monoxide. RESULTSIn the LCQ population (n = 237; pirfenidone, n = 155; no treatment, n = 82), treatment groups differed in age, insurance, and %FVC. In the unadjusted analyses, mean changes in PROMs differed numerically between treatment groups; however, based on the MSM, there were no significant differences in adjusted mean changes in PROMs. When analyzed by Gender, Age, and Physiology (GAP) score, a clinically meaningful reduction in worsening of pirfenidone vs no treatment was observed in the adjusted mean change of UCSD SOBQ at Month 12 in patients with GAP stage 2/3. INTERPRETATIONSimilar to previous findings, the difference in UCSD SOBQ scores observed in this real-world analysis suggests that patients with more advanced IPF may experience less dyspnea when receiving pirfenidone vs no treatment; further research is needed to confirm this finding.

Multimode Design and Analysis of an Integrated Leg-Arm Quadruped Robot with Deployable Characteristics

To improve locomotion and operation integration, this paper presents an integrated leg-arm quadruped robot (ILQR) that has a reconfigurable joint. First, the reconfigurable joint is designed and assembled at the end of the leg-arm chain. When the robot performs a task, reconfigurable configuration and mode switching can be achieved using this joint. In contrast from traditional quadruped robots, this robot can stack in a designated area to optimize the occupied volume in a nonworking state. Kinematics modeling and dynamics modeling are established to evaluate the mechanical properties for multiple modes. All working modes of the robot are classified, which can be defined as deployable mode, locomotion mode and operation mode. Based on the stability margin and mechanical modeling, switching analysis and evaluation between each mode is carried out. Finally, the prototype experimental results verify the function realization and switching stability of multimode and provide a design method to integrate and perform multimode for quadruped robots with deployable characteristics.

Evidence for Low‐Pressure Crustal Anatexis During the Northeast Atlantic Break‐Up

AbstractWhile basaltic volcanism is dominant during rifting and continental breakup, felsic magmatism may be a significant component of some rift margins. During International Ocean Discovery Program (IODP) Expedition 396 on the continental margin of Norway, a graphite‐garnet‐cordierite bearing dacitic unit (the Mimir dacite) was recovered in two holes within early Eocene sediments on Mimir High (Site U1570), a marginal high on the Vøring Transform Margin. Here, we present a comprehensive textural, petrological, and geochemical study of the Mimir dacite in order to assess its origin and discuss the geodynamic implications. The major mineral phases (garnet, cordierite, quartz, plagioclase, alkali feldspar) are hosted in a fresh rhyolitic, vesicular, glassy matrix that is locally mingled with sediments. The major element chemistry of garnet and cordierite, the presence of zircon inclusions with inherited cores, and thermobarometric calculations all support an upper crustal metapelitic origin. While most magma‐rich margin models favor crustal anatexis in the lower crust, thermobarometric calculations performed here show that the Mimir dacite was produced at upper‐crustal depths (&lt;5 kbar, 18 km depth) and high temperature (750–800°C) with up to 3 wt% water content. In situ U‐Pb analyses on zircon inclusions give a magmatic crystallization age of 54.6 ± 1.1 Ma, consistent with emplacement that post‐dates the Paleocene‐Eocene Thermal Maximum. Our results suggest that the opening of the Northeast Atlantic was associated with a phase of low‐pressure, high‐temperature crustal anatexis preceding the main phase of magmatism.

A bias-reduced generalized estimating equation approach for proportional odds models with small-sample longitudinal ordinal data

BackgroundLongitudinal ordinal data are commonly analyzed using a marginal proportional odds model for relating ordinal outcomes to covariates in the biomedical and health sciences. The generalized estimating equation (GEE) consistently estimates the regression parameters of marginal models even if the working covariance structure is misspecified. For small-sample longitudinal binary data, recent studies have shown that the bias of regression parameters may result from the GEE and have addressed the issue by applying Firth’s adjustment for the likelihood score equation to the GEE as if generalized estimating functions were likelihood score functions. In this manuscript, for the proportional odds model for longitudinal ordinal data, the small-sample properties of the GEE were investigated, and a bias-reduced GEE (BR-GEE) was derived.MethodsBy applying the adjusted function originally derived for the likelihood score function of the proportional odds model to the GEE, we produced the BR-GEE. We investigated the small-sample properties of both GEE and BR-GEE through simulation and applied them to a clinical study dataset.ResultsIn simulation studies, the BR-GEE had a bias closer to zero, smaller root mean square error than the GEE with coverage probability of confidence interval near or above the nominal level. The simulation also showed that BR-GEE maintained a type I error rate near or below the nominal level.ConclusionsFor the analysis of longitudinal ordinal data involving a small number of subjects, the BR-GEE is advantageous for obtaining estimates of the regression parameters of marginal proportional odds models.

Discrepancy between regulations and practice in initial margin calculation

Counterparty risk remains an issue in over-the-counter derivative transactions following the 2008 financial crisis. While the margin for a derivative transaction can only be transferred until just before the counterparty’s default, the exposure of the derivative transaction can vary stochastically during the margin period of risk, that is, the period from the counterparty’s default to the actual closing-out of the transaction. Thus, the anticipated positive exposure may not be recognized, resulting in counterparty risk. Considering it is difficult to calculate the initial margin (IM) according to the regulations, IM has been calculated in practice using a simplified method proposed by the International Swaps and Derivatives Association (ISDA), which is called the ISDA Standard Initial Margin Model (“ISDA SIMM”). In this study, we derive an approximate formula for some counterparty risk indicators for a stochastic volatility model and illustrate numerical analyses for a call option in the SABR model as an example to examine the effect of the discrepancy between regulations and practices in margin calculation. Our results imply that the IM calculated in practice may be insufficient for counterparty risk management, particularly when the market is volatile.

Achieving equitable space heating electrification: A case study of Los Angeles

A major step towards residential building decarbonization is the electrification of natural gas space heating. Current inequities such as limited access to cooling technologies and high energy burden can be addressed in transition if we take steps now to understand the economic impacts of different electric technologies. This study presents a novel high-resolution techno-economic model, the Marginal Net Present Value Upgrade Analysis model, which improves upon existing literature that examines the economics of electrifying space heating through a more detailed cost calculation and the use of a variable discount rate. Results show that 1) electrifying with heat pumps is only recommended for owners who are replacing a natural gas furnace and central AC system, 2) renters are highly vulnerable in this transition in that electric resistance technologies are the least capital intensive technology for landlords to install, with renters bearing the increased operational cost, 3) rebates from the Inflation Reduction Act of 2022 allow most qualifying landlords and owners to install even the highest efficiency heat pumps at a net savings when compared to the baseline heating and cooling system, and 4) reducing capital costs are more critical than altering utility rates to achieve high heat pump penetration. The model developed herein can support decision-making related to electrification and energy efficiency policy and rulemaking and will give insight into the impact residential building electrification can have on marginalized communities.

Generalized single index modeling of longitudinal data with multiple binary responses.

In health and clinical research, medical indices (eg, BMI) are commonly used for monitoring and/or predicting health outcomes of interest. While single-index modeling can be used to construct such indices, methods to use single-index models for analyzing longitudinal data with multiple correlated binary responses are underdeveloped, although there are abundant applications with such data (eg, prediction of multiple medical conditions based on longitudinally observed disease risk factors). This article aims to fill the gap by proposing a generalized single-index model that can incorporate multiple single indices and mixed effects for describing observed longitudinal data of multiple binary responses. Compared to the existing methods focusing on constructing marginal models for each response, the proposed method can make use of the correlation information in the observed data about different responses when estimating different single indices for predicting response variables. Estimation of the proposed model is achieved by using a local linear kernel smoothing procedure, together with methods designed specifically for estimating single-index models and traditional methods for estimating generalized linear mixed models. Numerical studies show that the proposed method is effective in various cases considered. It is also demonstrated using a dataset from the English Longitudinal Study of Aging project.

A joint normal-ordinal (probit) model for ordinal and continuous longitudinal data.

In biomedical studies, continuous and ordinal longitudinal variables are frequently encountered. In many of these studies it is of interest to estimate the effect of one of these longitudinal variables on the other. Time-dependent covariates have, however, several limitations; they can, for example, not be included when the data is not collected at fixed intervals. The issues can be circumvented by implementing joint models, where two or more longitudinal variables are treated as a response and modeled with a correlated random effect. Next, by conditioning on these response(s), we can study the effect of one or more longitudinal variables on another. We propose a normal-ordinal(probit) joint model. First, we derive closed-form formulas to estimate the model-based correlations between the responses on their original scale. In addition, we derive the marginal model, where the interpretation is no longer conditional on the random effects. As a consequence, we can make predictions for a subvector of one response conditional on the other response and potentially a subvector of the history of the response. Next, we extend the approach to a high-dimensional case with more than two ordinal and/or continuous longitudinal variables. The methodology is applied to a case study where, among others, a longitudinal ordinal response is predicted with a longitudinal continuous variable.

Risk of Recurrence in Acute Anterior Uveitis

PurposeTo examine the frequency of recurrence and identify risk factors for recurrence in patients with acute anterior uveitis (AAU). DesignRetrospective cohort study from a single tertiary ophthalmic clinical centre. ParticipantsAll subjects with AAU identified from a database of Inflammatory Eye Disease presenting to Te Whatu Ora (Auckland, New Zealand) between 2008 and 2021. MethodsData was collected retrospectively from chart review and electronic patient records for all patients during the study period. Rates of recurrence were reported using Kaplan Meier estimator. Multivariate analysis of risk factors for recurrence were calculated using a marginal Cox regression model. Main Outcome MeasuresThe primary outcome measure was disease recurrence. Secondary outcome measure was moderate vision loss (≤20/50). Results2763 eyes of 2092 subjects with AAU were studied, with a median follow up time of 8.9 years, and a total follow up of 19,794.9 eye-years. Recurrence occurred in the ipsilateral eye in 1258 eyes (45.5%) and in the contralateral eye in 522 eyes (27.3%). Rates of ipsilateral recurrence over ten years were 38.1% for idiopathic disease, 43.2% for HLAB27/inflammatory arthritis, and 44.9% for viral uveitis. On multivariate analysis the following were associated with increased risk of ipsilateral recurrence: older age (p<0.001); Māori ethnicity (p=0.006); Asian ethnicity (p<0.001); HLA-B27/inflammatory arthritis (p<0.001); viral uveitis (p=0.018). There was no association with gender, smoking, bilateral disease, or hypertensive uveitis. Rates of contralateral eye involvement were significantly lower than ipsilateral eye recurrence. Contralateral recurrence at ten years was 15.2% in idiopathic uveitis, 37.6% in HLAB27/inflammatory arthritis, and 2.0% in viral uveitis. Risk factors identified for contralateral eye involvement were Māori ethnicity (p=0.003), Pasifika (Pacific Islanders) ethnicity (p=0.021), HLAB27/inflammatory arthritis (p<0.001). Moderate vision loss (≤20/50) was present in 411 eyes (14.9%) at final follow up and was more common if time to first recurrence was shorter (p<0.001). ConclusionsApproximately half of patients with AAU will develop recurrence in the ipsilateral eye and a quarter will have recurrence in the contralateral eye. Patients with viral disease have the highest risk of ipsilateral recurrence and lowest risk of contralateral recurrence. Patients with risk factors for recurrence should be managed and counselled appropriately to minimise the risk of visual loss and complications of uveitis.