Cumulative Logit Research Articles

Applying survey weights to ordinal regression models for improved inference in outcome-dependent samples with ordinal outcomes.

Researchers often use outcome-dependent sampling to study the exposure-outcome association. The case-control study is a widely used example of outcome-dependent sampling when the outcome is binary. When the outcome is ordinal, standard ordinal regression models generally produce biased coefficients when the sampling fractions depend on the values of the outcome variable. To address this problem, we studied the performance of survey-weighted ordinal regression models with weights inversely proportional to the sampling fractions. Through an extensive simulation study, we compared the performance of four ordinal regression models (SM: stereotype model; AC: adjacent-category logit model; CR: continuation-ratio logit model; and CM: cumulative logit model), with and without sampling weights under outcome-dependent sampling. We observed that when using weights, all four models produced estimates with negligible bias of all regression coefficients. Without weights, only stereotype model and adjacent-category logit model produced estimates with negligible to low bias for all coefficients except for the intercepts in all scenarios. In one scenario, the unweighted continuation-ratio logit model also produced estimates with low bias. The weighted stereotype model and adjacent-category logit model also produced estimates with lower relative root mean square errors compared to the unweighted models in most scenarios. In some of the scenarios with unevenly distributed categories, the weighted continuation-ratio logit model and cumulative logit model produced estimates with lower relative root mean square errors compared to the respective unweighted models. We used a study of knee osteoarthritis as an example.

Associations of Plasma Erythritol with Dietary Factors, Cardiometabolic, Inflammatory, and Gut Health Markers in People with and without HIV: A Cross-Sectional Study.

Recently, elevated levels of plasma erythritol have been associated with major adverse cardiovascular events (MACE). It is known that people with HIV (PWH) have a higher cardiovascular disease burden. Whether PWH have higher levels of plasma erythritol has not been evaluated. This study aimed to assess if blood erythritol levels are elevated in PWH and to examine relationships between erythritol and dietary, cardiometabolic, inflammatory, and gut health markers. Plasma erythritol levels were measured using frozen samples from 162 participants, including 109 PWH and 53 people without HIV (PWoH) in a parent study. General linear models were used to assess the linear relationship between characteristics, cardiovascular measures, markers of body composition, inflammation, and gut integrity with plasma erythritol. Logistic regression was used to assess risk factors associated with PWH, and cumulative logit models were used to investigate which factors were associated with having the highest plasma erythritol levels among PWH. Compared to PWoH, PWH had higher plasma erythritol levels (p = 0.03). Every 10% increase in VLDL (p = 0.01), visceral adipose tissue (p < 0.0001), or TNFrI (p = 0.01) was associated with an approximately 1% increase in plasma erythritol. Among PWH, HgbA1c (p = 0.003), TNFrI (p = 0.002), and IFAB-P (p = 0.004) were associated with having the highest tertile of plasma erythritol (≥3.6 μM). Compared to PWoH, PWH were more than two times as likely (p = 0.03) to have plasma erythritol ≥ 3.6 μM. We identified positive associations between plasma erythritol levels and several factors, including HIV status, BMI, adipose tissue, TNFr1, HbA1c, and VLDL. These results underscore the importance of further investigating the role of elevated plasma erythritol levels in people with HIV, particularly in light of their increased vulnerability to cardiovascular and metabolic diseases.

Emotional Fertility Intention and its correlates in Ethiopia among married contraceptive user women: using linked community and health facility data from performance monitoring for action; a generalized ordered logistics regression modeling

BackgroundEmotional fertility intention and couples communication are key during pregnancy and childbirth with simultaneous minimization of reproductive coercion. Intention to conceive is an integral part of the reproductive health (RH) right and can be considered as decision making on fertility, family wellbeing and the country’s population demographic dividend and composition. However, in low and middle income countries including Ethiopia where males dominance is culturally constructed and socially accepted, males took the lead in every decision making process. In the aforementioned context, women are less likely for their voices to be heard, hence, this study aimed at determining the level of womens´ emotional fertility readiness and its correlates. The finding provided actionable evidence for the ministry and developmental partners working on reproductive and womens´ health so as to be used as an action point to empower women in terms of their reproductive health right to have control over their fertility.MethodsLinked community and facility data with nationally representation from Performance Monitoring for Action (PMA Ethiopia) 2020 Survey Ethiopia except Tigray Region were used for this study. A total of 2,069 current and/or recent contraceptive user women of child bearing age who are currently married/living together as a partner were included in this analysis. Frequency was computed to describe the study participant’s characteristics. Generalized Ordered logistics regression modeling was employed to identify correlates of the hierarchical variation in women fertility intention if they became pregnant. Results were presented in the form of percentages and odds ratio with 95% Confidence Intervals. Candidate variables were selected using p-value of 0.25. Statistical significance was declared at p-value of 0.05.ResultsThe proportion of womens´ emotional fertility intention of feeling unhappiness was 48.73% (95%CI: 46.21%, 51.23%). On the contrary, 22.88%, 11.36% and 17.03% of them reported that they felt sort of happy, very happy and mixed feeling. An increase in age,10 and above years marriage duration, the type of decision maker for contraceptive use were found to increase the odds of women emotional fertility intention across the higher level categories by (AOR: 95% CI: 6.75 (3.11, 14.62) times higher among elder women aged 35 to 49 years, (AOR: 95% CI: 3.79 (1.72, 8.31) times higher for women with a 10 or more years of marriage duration; and 1.83 (1.03,3.24) times higher for women whose contraceptive use was decided by the health care provide alone. A higher birth order lowered the cumulative odds of womens´ emotional fertility intention symmetrically across the higher level categories by 86% (AOR: 95% CI: 0.14 (0.07, 0.29). Women who wanted to have additional child and whose nearest facility provided 5 or more methods had an increased odds of being in the higher level categories of women emotional fertility intention with disproportional association across the cumulative logit. Accordingly, women whose nearest health facility provided 5 or more methods had an 49% (AOR: 95%CI:1.49 (1.01, 2.19) increased likelihood of being in the mixed or happy category than being very/sort of unhappy category of the emotional fertility intention while the number of methods had no significant association with emotional fertility intention at higher cumulative logit: 1.34 (0.87,2.10). Those who wanted to have an additional child had a 3.16 (2.28, 4.36) higher odds to be in the mixed or happy category than being in unhappy category. Further, this tendency was even stronger at higher categories of emotional fertility intention: 4.83 (3.23, 7.23).ConclusionNearly one in two women reported being unhappy while 17.03% felt mixed emotion calling up on intended and spaced pregnancies by ensuring women reproductive and economic empowerment to empower women to have control over their fertility. Activities and efforts that promote intended and spaced pregnancies; and diversifying access to contraceptive methods in the nearest health facilities are likely to improve women emotional fertility intention; and activities that enable women to decide their contraceptive as well. The finding that health care provider decides on women current/recent contraceptive use calls for activities to improve quality of contraceptive use counseling to enable women to decide their contraceptive use by the themselves while the access of diversified methods in the nearby health facility create an opportunity for women to obtain the method they preferred to use and make them emotionally well. These activities are hoped to enable women to plan their fertility thereby increasing their emotional well-being. These activities and interventions need to be tailored across regions and need to be age sensitive.

A Day-to-Day Dynamical Approach to the Most Likely User Equilibrium Problem

The lack of a unique user equilibrium (UE) route flow in traffic assignment has posed a significant challenge to many transportation applications. The maximum-entropy principle, which advocates for the consistent selection of the most likely solution, is often used to address the challenge. Built on a recently proposed day-to-day discrete-time dynamical model called cumulative logit (CumLog), this study provides a new behavioral underpinning for the maximum-entropy user equilibrium (MEUE) route flow. It has been proven that CumLog can reach a UE state without presuming that travelers are perfectly rational. Here, we further establish that CumLog always converges to the MEUE route flow if (i) travelers have no prior information about routes and thus, are forced to give all routes an equal initial choice probability or if (ii) all travelers gather information from the same source such that the general proportionality condition is satisfied. Thus, CumLog may be used as a practical solution algorithm for the MEUE problem. To put this idea into practice, we propose to eliminate the route enumeration requirement of the original CumLog model through an iterative route discovery scheme. We also examine the discrete-time versions of four popular continuous-time dynamical models and compare them with CumLog. The analysis shows that the replicator dynamic is the only one that has the potential to reach the MEUE solution with some regularity. The analytical results are confirmed through numerical experiments. History: This paper has been accepted for the Transportation Science Special Issue on ISTTT25 Conference. Funding: This research was funded by the United States National Science Foundation’s Division of Civil, Mechanical and Manufacturing Innovation [Grant 2225087]. The work of J. Xie was funded by the National Natural Science Foundation of China [Grant 72371205]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2024.0525 .

The randomized controlled trial (NAVKIDS2) of a patient navigator program created for children with chronic kidney disease

Patient navigators enable adult patients to circumnavigate complex health systems, improving access to health care and outcomes. Here, we aimed to evaluate the effects of a patient navigation program in children with chronic kidney disease (CKD). In this multi-center, randomized controlled trial, we randomly assigned children (aged 0-16 years) with CKD stages 1-5 (including children on dialysis or with kidney transplants), from low socioeconomic status backgrounds, and/or residing in remote areas, to receive patient navigation at randomization (immediate) or at six months (waitlist). The primary outcome was self-rated health (SRH) of participating children at six months, using intention to treat analysis. Secondary outcomes included caregivers’ SRH and satisfaction with health care, children’s quality of life, hospitalizations, and missed school days. Repeated measures of the primary outcome from baseline to six months were analyzed using cumulative logit mixed effects models. Semi-structured interviews were thematically evaluated. Of 398 screened children, 162 were randomized (80 immediate and 82 waitlist); mean age (standard deviation) of 8.8 (4.8) years with 64.8% male. SRH was not significantly different between the immediate and wait-listed groups at six months. There were also no differences across all secondary outcomes between the two groups. Caregivers’ perspectives were reflected in seven themes: easing mental strain, facilitating care coordination, strengthening capacity to provide care, reinforcing care collaborations, alleviating family tensions, inability to build rapport and unnecessary support. Thus, in children with CKD, self-rated health may not improve in response to a navigator program, but caregivers gained skills related to providing and accessing care.

Condom use increased after a peer group intervention implemented by community volunteers in Malawi

BackgroundHIV prevention remains a global priority, especially in sub-Saharan Africa. Our research team previously developed an evidence-based peer group program for HIV prevention called Mzake ndi Mzake (Friend to Friend). A community-engaged collaboration adapted the program for community ownership and implementation. Here we report whether this HIV prevention program, implemented by community volunteers, increased condom use among sexually active individuals in rural Malawi.MethodsThree communities sequentially rolled out the program. Effectiveness was evaluated using a stepped wedge design. Repeated surveys 11–13 months apart were conducted between 2016 and 2019. At Time 1, no community had offered the intervention. At Time 2, the first community had offered the intervention and two had not (control group). At Time 3, two communities had offered the intervention and one had not (control group). We used two condom use indicators; condom use frequency in the last 2 months (N = 771) and condom use at last sex (N = 880). The analytical sample included all sexually active persons answering that question at one or more time points. Mixed-effects cumulative logit and Generalized Estimating Equation (GEE) models were used to model the two condom indicators over time, controlling for demographic factors, UNAIDS HIV knowledge, safer sex self-efficacy and partner communication.ResultsThis peer group intervention implemented by trained community volunteers increased both condom use indicators at Times 2 and 3. In the final adjusted models with non-significant factors removed, condom use in the last two months increased for the intervention group vs. control group [Time 2: Adjusted Odds Ratio (AOR) = 1.59 (1.15, 2.21); Time 3: AOR 2.01 (1.23, 3.30)]. Similarly, condom use at last sex increased for the intervention group vs. control group [Time 2: AOR = 1.48 (1.08, 2.03); Time 3: AOR 1.81 (1.13, 2.90)]. Other significant predictors of greater condom use were also described. Although the intervention increased UNAIDS HIV knowledge, knowledge did not predict condom use.ConclusionsIn this community-engaged implementation study, an evidence-based peer group program for HIV prevention increased condom use when delivered by trained community volunteers. Community ownership and program delivery by trained volunteers offer an innovative and cost-effective strategy to address ongoing HIV prevention needs without overburdening healthcare systems in sub-Saharan Africa.Trial registrationClinical Trials.gov NCT02765659 Registered May 6, 2016.

Modeling Financial Risk Attitude: The Role of Education And Financial Literacy

Abstract This paper studies the relationship between risk propensity, education and financial literacy. The results of the empirical investigation confirm the importance of the key explanatory variables of education and financial competence. Since they are both included in the model, the different roles of each are singled out. In particular, while education turns out to be a factor contributing to raising risk tolerance, financial literacy tends to reduce risk propensity. Risk attitude is evaluated by self-reported assessment and modeled through cumulative logit models. In order to handle anomalous data, M estimators with a bounded influence function are considered.

Occupational tasks associated with shoulder pain and upper extremity disability: a cross-sectional study in the Johnston County Osteoarthritis Project

BackgroundShoulder pain is a leading cause of disability. Occupations requiring high upper extremity demands may put workers at greater risk of shoulder injury and resulting pain. We examined associations of occupation with shoulder pain and upper extremity disability in the Johnston County Osteoarthritis Project.MethodsWork industry and occupational tasks for the longest job held were collected from participants. At follow-up ranging from 4–10 years later, participants were asked about shoulder symptoms (pain, aching, or stiffness occurring most days of 1 month in the last year) and given a 9-item, modified Disabilities Arm Shoulder and Hand (DASH) questionnaire to categorize disability from 0–4 (none-worst). Logistic regression and cumulative logit regression models were used to estimate associations with prevalent shoulder symptoms and with worse disability category, respectively. Models were adjusted for cohort, age, sex, race, education and time to follow-up. Sex- and race-stratified associations were evaluated.ResultsAmong 1560 included participants, mean age was 62 years (standard deviation ± 9 years); 32% were men, and 31% were Black. Compared to the managerial/professional industry, higher odds of both shoulder symptoms and worse upper extremity disability were seen for most industrial groups with physically demanding jobs, particularly the service industry. Work that often or always required lifting/moving > 10 lbs. was associated with higher odds of shoulder symptoms. Work that sometimes or always required heavy work while standing was associated with higher odds of shoulder symptoms, and this association was stronger among men and White workers.ConclusionPhysically demanding occupations were associated with increased occurrence of shoulder pain and disability. Mitigating specific physical work demands may reduce shoulder-related disability.

Population under Stress: The Coping Mechanisms of Lebanese Adults in Times of Intermingling Crises and Their Relationship with Stress.

The Lebanese population has faced numerous stressors due to multiple crises in the past four years. This study aims to measure the perceived stress of the Lebanese population, identify the coping mechanisms being used, and determine whether they are associated with their stress levels. A cross-sectional study of 205 individuals randomly selected from Beirut was conducted. Frequency distribution, descriptive analysis, and multivariable cumulative logit models were used to determine the associations between coping mechanisms and perceived stress. Our results indicated that 95.4% of our population had moderate to high perceived stress levels. Problem-focused coping was the most adopted mechanism and was associated with a statistically significant lower stress level, whereas avoidant coping was associated with a statistically significant higher stress level. Our study can pave the way for raising awareness on the importance of managing stress with adaptive coping mechanisms.

ANALISIS MODEL LOGIT KUMULATIF UNTUK MENENTUKAN DETERMINAN USIA KAWIN PERTAMA WANITA DI KABUPATEN BALANGAN

The Province of South Kalimantan is one of the five provinces in Indonesia with the highest teenage marriage rate from 2017 to 2020. Based on 13 South Kalimantan regencies/cities, it is known that Balangan Regency has the greatest percentage of women's age at first marriage under 19 years compared to other regencies/cities, which is 55.58%. The purpose of this study is to identify the factors that influence women's age at first marriage in Balangan Regency in 2020. In this investigation, ordinal logistic regression with the cumulative logit model was used. The findings revealed that the highest education ever/currently obtained by a woman (X1), parents' age at first marriage (X2), the highest diploma of the head of the household (X3), employment status of the head of the family (X4), location of place of residence (X5), poverty status (X6), and migration (X7) had no significant effect. Furthermore, using the Spearman rank correlation coefficient, it was discovered that the highest education ever/currently obtained by a woman (X1) has a substantial correlation/closeness of link with women's age at first marriage by 28%. Women with a higher degree of education are less likely to marry at a young age, whereas women with a lower level of education are more likely.

THE ROLE OF HEALTH LITERACY IN HEALTH CARE UTILIZATION AMONG TAIWANESE OLDER ADULTS

Abstract Health literacy is one of important capabilities links to health-related behaviours. The extant study provides limited information about the healthcare access of older adults. This study investigated factors determining the healthcare utilisation of 2423 community-dwelling older adults from the Taiwan Longitudinal Study on Ageing between 2011 and 2015. We used linear mixed-effects regression models and cumulative logit models to examine whether personal characteristics are associated with healthcare utilisation. A significant association was found between the level of difficulties in health literacy and healthcare utilisation after controlling for age, comorbidity, depression, mobility and accessibilities. The higher the older adults scored in the difficulty of health literacy, the lower frequencies of clinics (p = .03), inpatient (p = .02) and dentist visits (p = .02). Individuals who access health-related information more easily have a better chance to receive inpatient services when they feel unwell (p = .0004). Better perceived health is less likely to use clinics (p &amp;lt; .0001), emergency (p &amp;lt; .0001) and inpatient services (p = .0007) but not include visits to pharmacy and traditional medicine. People engaging in workouts are less likely to purchase in a pharmacy (p = .02) but visit traditional medicine (p = .02) more often. It echoes that health literacy is an intermediate attribute to self-efficacy in managing personal health matters and suggests a perspective that older adults consider taking traditional medicine as a self-care instead of healthcare treatment. Future intervention programmes can address health literacy promotion as an initiating step to facilitate participants’ engagement.

Physical and Psychological Burden among Caregivers of Latinx Older Adults with Stroke and Multimorbidity.

To investigate the association between Latinx older adults' stroke, multimorbidity, and caregiver burden. For this retrospective cohort study, we used the Hispanic Established Populations for the Epidemiologic Study of the Elderly (H-EPESE) Wave-7 data set. The caregiver's physical burden was defined by using the Level of Burden Index. The caregiver's psychological burden was measured by using the Perceived Stress Scale (PSS-4). Multimorbidity was defined as the presence of 3 or more chronic conditions. The average age of the Latinx adults was 86 years, and the caregivers were 56 years. Latinx older adults and caregivers were more likely to be females (66% and 75%). Most caregivers were children (71%). Twelve percent of Latinx older adults presented with stroke, and 50% presented with multimorbidity. Caregiver physical burden was stratified into 3 levels: low (43%), medium (17%), and high (40%) burden. The cumulative logit model revealed that caregivers caring for those with stroke or multimorbidity had a high physical burden. Family caregivers and caregivers with a higher household income had a low physical burden. Caregivers with multimorbidity had a higher psychological burden. Caregivers who were interviewed in Spanish and those with higher household incomes had decreased psychological burden. This study revealed that caregivers had a higher physical burden among caregivers of Latinx adults with stroke or multimorbidity. Future studies must investigate the relationship between Latinx adults' stroke and caregiver psychological health, and build culturally tailored policies and community interventions to support caregivers susceptible to high stress and burden.

Abstract 16926: Associations of Preeclampsia and Preterm Delivery With Lifetime Posttraumatic Stress

Introduction: Adverse pregnancy outcomes (APOs) are female-specific CVD risk factors while posttraumatic stress disorder (PTSD) is a female-predominant CVD risk factor. Preeclampsia and preterm delivery are acute APOs with negative maternal and fetal consequences that, for some, results in trauma. Hypothesis: We hypothesized that individuals with a history of preeclampsia or preterm delivery would be more likely to screen positive for lifetime PTSD. Methods: Parous Nurses’ Health Study II participants who responded to a 2008 questionnaire ascertaining trauma (Brief Trauma Questionnaire, with targeted query of 16 event types) and PTSD (Short Screening Scale for DSM-IV PTSD) comprised the analytic sample (n=40,256). Trauma and PTSD were categorized using four categories: no trauma, trauma with no PTSD symptoms, 1-3 symptoms, or ≥4 symptoms (probable PTSD). Ordered logistic regression, using a cumulative logit link and multinomial distribution, estimated odds ratios (OR) and 95% confidence intervals (CI), adjusting for age at enrollment, race/ethnicity, and parental education. Results: Seven percent of participants had a history of preeclampsia (n=3,012) while 13.5% (n=5,418) ever delivered preterm. Twenty-one percent of participants screened positive for PTSD (n=8,336), endorsing ≥4 symptoms from their worst trauma. Among participants with PTSD, 66% of those with preterm preeclampsia in their first pregnancy endorsed having a traumatic pregnancy complication or labor/birth, compared to 23% among those who delivered normotensive first pregnancies at term. Odds of PTSD were higher with history of ever preeclampsia (OR=1.36, CI: 1.27-1.45) or preterm delivery (OR=1.41, CI: 1.34-1.48), compared to only normotensive pregnancies and term deliveries, respectively. Further adjustment for physical or sexual abuse in childhood/adolescence did not change conclusions but did attenuate the odds ratio for preeclampsia (OR=1.26, CI: 1.18-1.35). Conclusions: History of preeclampsia or preterm delivery identifies a population at higher risk for lifetime posttraumatic stress. Further studies are needed to disentangle temporality and examine to what extent subsequent mental health conditions may mediate the relationship between APOs and CVD.

Comparative Analysis of Frequentist and Bayesian Approaches in Fitting Stereotype Models for Ordinal Outcomes

Introduction: Stereotype regression models provide a parsimonious solution for analyzing ordinal response variables. When the proportional odds assumption is violated, these models offer a viable alternative to more commonly used cumulative logit models. However, their adoption in research remains limited due to a lack of standardization. Our study compares frequentist and Bayesian approaches for fitting stereotype models for ordinal outcomes, elucidating the benefits of each method to encourage broader utilization. Methods: We simulated ordinal data to contrast a Bayesian approach for an ordered stereotype model with two frequentist methods in R: Reduced-Rank Vector Generalized Linear Models (RRVGLM) for unordered scores and Ordered Stereotype Model (OSM) for ordered scores. Metrics included mean squared error (MSE) and bias across multiple simulation scenarios with various sample sizes and the introduction of multicollinear predictors. Lastly, a real dataset was utilized to demonstrate the application of these approaches. Results: Both frequentist methods exhibited errors in simulations and real data when the sample size was small and when multicollinearity was present. In simulation scenarios with small sample size (N=50, 70), frequentist methods often failed to converge or produced large standard errors, while the Bayesian approach always converged and yielded lower MSEs. In scenarios with large sample sizes (N=300, 500), all methods produced comparable MSEs. However, frequentist methods produced slightly less biased estimates. Conclusion: RRVGLM offers fast, accurate results but may encounter errors or produce unordered scores complicating interpretation. In these cases, OSM may provide better results. Bayesian models excel with small sample sizes and complex data with issues such as multicollinearity but require more computation time.

Ordinal data and residual analysis: Review and application

Experiments in which the response is ordinal polytomous are often performed in the agricultural sciences and, often, the cumulative logit models are used to analyze this variable. A particular characteristic is that the polytomous variables are objects of multivariate statistics and the ordinary residual, associated with the classical models available, is a vector for each subject. Consequently, these residuals are not easily interpreted, and their distribution is unknown. Residual analysis is an essential step in validating any statistical model, and not performing it can allow a model to incorrectly fit the data, resulting in erroneous conclusions and inferences. In this context, the work aims to review the residuals for ordinal data available in the literature, emphasizing the so-called surrogate residuals with continuous distribution. As a practicalapplication, it is present an experiment carried out with Tambaqui fish of different types of genotype. The response variable in this study is the severity of the lesions found in the livers of Tambaquis. The estimation of the parameters was performed using the maximum likelihood. The selected model by the likelihood ratio test included the proportional odds and fish genotype effect. According to this model, it was possible to verify in this study that fish with genotype 122 presented a higher probability of liver lesion classified as irreversible (71, 26%), while Tambaquis with genotype 130 had a higher probability of moderate lesion, 46, 75%. For the model diagnostics, the half-normal plot and the Kolmogorov-Smirnov test were used to examine the performance of the surrogate residual. The results obtained provided evidence of the adequacy of the selected model since the residuals did not reveal patterns or influential points in diagnostic tools.

Row mixture-based clustering with covariates for ordinal responses

Existing methods can perform likelihood-based clustering on a multivariate data matrix of ordinal data, using finite mixtures to cluster the rows (observations) of the matrix. These models can incorporate the main effects of individual rows and columns, as well as cluster effects, to model the matrix of responses. However, many real-world applications also include available covariates, which provide insights into the main characteristics of the clusters and determine clustering structures based on both the individuals’ similar patterns of responses and the effects of the covariates on the individuals' responses. In our research we have extended the mixture-based models to include covariates and test what effect this has on the resulting clustering structures. We focus on clustering the rows of the data matrix, using the proportional odds cumulative logit model for ordinal data. We fit the models using the Expectation-Maximization algorithm and assess performance using a simulation study. We also illustrate an application of the models to the well-known arthritis clinical trial data set.

Breastfeeding initiation and duration among people with mild chronic hypertension: a secondary analysis of the Chronic Hypertension and Pregnancy trial

Increased duration of breastfeeding improves maternal cardiovascular health and may be especially beneficial in high-risk populations, such as those with chronic hypertension. Others have shown that individuals with hypertension are less likely to breastfeed, and there has been limited research aimed at supporting breastfeeding goals in this population. The impact of perinatal blood pressure control on breastfeeding outcomes among people with chronic hypertension is unknown. This study aimed to evaluate whether breastfeeding initiation and short-term duration assessed at the postpartum clinic visit differed according to perinatal blood pressure treatment strategy (targeting blood pressure <140/90 mm Hg vs reserving antihypertensive treatment for blood pressure ≥160/105 mm Hg). We performed a secondary analysis of the Chronic Hypertension and Pregnancy trial. This was an open-label, multicenter, randomized trial where pregnant participants with mild chronic hypertension were randomized to receive antihypertensive medications with goal blood pressure <140/90 mm Hg (active treatment) or deferredtreatment until blood pressure ≥160/105 mm Hg (control). The primary outcome was initiation and duration of breastfeeding, assessed at the postpartum clinic visit. We performed bivariate analyses and log-binomial and cumulative logit regression models, adjusting models for variables that were unbalanced in bivariate analyses. We performed additional analyses to explore the relationship between breastfeeding duration and blood pressure measurements at the postpartum visit. Of the 2408 participants from the Chronic Hypertension and Pregnancy trial, 1444 (60%) attended the postpartum study visit and provided breastfeeding information. Participants in the active treatment group had different body mass index class distribution and earlier gestational age at enrollment, and (by design) were more often discharged on antihypertensives. Breastfeeding outcomes did not differ significantly by treatment group. In the active and control treatment groups, 563 (77.5%) and 561 (78.1%) initiated breastfeeding, and mean durations of breastfeeding were 6.5±2.3and 6.3±2.1weeks, respectively. The probability of ever breastfeeding (adjusted relative risk, 0.99; 95% confidence interval, 0.93-1.05), current breastfeeding at postpartum visit (adjusted relative risk, 1.01; 95% confidence interval, 0.94-1.10), and weeks of breastfeeding (adjusted odds ratio, 0.87; 95% confidence interval, 0.68-1.12) did not differ by treatment group. Increased duration (≥2 vs <2 weeks) of breastfeeding was associated with slightly lower blood pressure measurements at the postpartum visit, but these differences were not significant in adjusted models. In a secondary analysis of the cohort of Chronic Hypertension and Pregnancy trial participants who attended the postpartum study visit and provided breastfeeding information (60% of original trial participants), breastfeeding outcomes did not differ significantly by treatment group. This suggests that maintaining goal blood pressure <140/90 mm Hg throughout the perinatal period is associated with neither harm nor benefit for short-term breastfeeding goals. Further study is needed to understand long-term breastfeeding outcomes among individuals with chronic hypertension and how to support this population in achieving their breastfeeding goals.

Gene-level association analysis of bivariate ordinal traits with functional regressions.

In genetic studies, many phenotypes have multiple naturally ordered discrete values. The phenotypes can be correlated with each other. If multiple correlated ordinal traits are analyzed simultaneously, the power of analysis may increase significantly while the false positives can be controlled well. In this study, we propose bivariate functional ordinal linear regression (BFOLR) models using latent regressions with cumulative logit link or probit link to perform a gene-based analysis for bivariate ordinal traits and sequencing data. In the proposed BFOLR models, genetic variant data are viewed as stochastic functions of physical positions, and the genetic effects are treated as a function of physical positions. The BFOLR models take the correlation of the two ordinal traits into account via latent variables. The BFOLR models are built upon functional data analysis which can be revised to analyze the bivariate ordinal traits and high-dimension genetic data. The methods are flexible and can analyze three types of genetic data: (1) rare variants only, (2) common variants only, and (3) a combination of rare and common variants. Extensive simulation studies show that the likelihood ratio tests of the BFOLR models control type I errors well and have good power performance. The BFOLR models are applied to analyze Age-Related Eye Disease Studydata, in which two genes, CFH and ARMS2, are found to strongly associate with eye drusen size, drusen area, age-related macular degeneration (AMD) categories, and AMD severity scale.

Achievement of Improved Post-Intervention Status in Patients with Generalized Myasthenia Gravis Treated with Ravulizumab during the CHAMPION MG Study (S5.008)

Achievement of Improved Post-Intervention Status in Patients with Generalized Myasthenia Gravis Treated with Ravulizumab during the CHAMPION MG Study (S5.008)

Assessing the incidence and severity of drug adverse events: a Bayesian hierarchical cumulative logit model

ABSTRACT Detection of safety signals based on multiple comparisons of adverse events (AEs) between two treatments in a clinical trial involves evaluations requiring multiplicity adjustment. A Bayesian hierarchical mixture model is a good solution to this problem as it borrows information across AEs within the same System Organ Class (SOC) and modulates extremes due merely to chance. However, the hierarchical model compares only the incidence rates of AEs, regardless of severity. In this article, we propose a three-level Bayesian hierarchical non-proportional odds cumulative logit model. Our model allows for testing the equality of incidence rate and severity for AEs between the control arm and the treatment arm while addressing multiplicities. We conduct simulation study to investigate the operating characteristics of the proposed hierarchical model. The simulation study demonstrates that the proposed method could be implemented as an extension of the Bayesian hierarchical mixture model in detecting AEs with elevated incidence rate and/or elevated severity. To illustrate, we apply our proposed method using the safety data from a phase III, two-arm randomized trial.