Semiparametric Proportional Hazards Model Research Articles

A quantile-regression approach to bivariate longitudinal joint modeling

Joint modeling of longitudinal outcomes and time-to-event data has become a major re- search interest in the last thirty years. A joint model is useful since it helps (i) to under- stand the evolution of the outcome(s) of interest over time, (ii) to understand the effects of the outcomes on the time of occurrence of some event(s) of interest (e.g. death/relapse), and (iii) to study the effects of the time-varying and time-invariant predictors on the longitudinal and time-to-event process. Traditional linear mixed models are routinely used for modeling the longitudinal process. However, for non-Gaussian/skewed outcomes it is more appealing to use quantile-regression models since such models do not assume any specific probability distribution for the outcomes. In this article, we present a bivariate quantile-regression approach for jointly modeling longitudinal process and time-to-event. In a Bayesian setting we consider an Asymmetric Laplace Distribution (ALD) for modeling different quantiles of the outcomes, and a semi-parametric Proportional Hazards (PH) model for time-to-event. Model parameters are estimated using Markov chain Monte Carlo (MCMC) algorithm, and we discuss the computational complexities through several simulation studies. Our numerical studies illustrate the usefulness of our model over the other traditional models. Journal of Statistical Research 2024, Vol. 58, No. 1, pp. 111-130.

Risk factors for COVID-19 and their association with mortality in Ecuadorian patients admitted to the ICU: A retrospective cohort multicentric study.

Several risk factors were associated with mortality in patients with coronavirus disease 2019 (COVID-19) infection in intensive care units (ICU). We assessed the effect of risk factors related to the characteristics and clinical history of the population, laboratory test results, drug management, and type of ventilation on the probability of survival/discharge from the ICU. A retrospective cohort multicentric study of adults with COVID-19 admitted to the ICU between March 2020 and December 2021. Data were collected from 6 hospitals in 5 cities in Ecuador. The primary outcome was ICU survival/discharge. Survival analysis was conducted using semi-parametric Cox proportional hazards models. Of those admitted to the ICU with COVID-19, (n = 991), mean age was 56.76 ± 13.14, and 65.9% were male. Regarding the primary outcome, 51.1% (n = 506) died and 48.9% (n = 485) survived. Of the group that died, their mean age was higher than the survivors (60.7 vs 52.60 years, respectively), and they had a higher prevalence of comorbidities such as arterial hypertension (37.2% vs 20.4%, respectively) and diabetes mellitus (26.9% vs 15.7%, respectively), with P < .001. In ventilatory management, 32.7% of patients used noninvasive ventilation and high-flow nasal cannula, and 67.3% required invasive ventilatory support. After adjusting for confounders, Cox regression analysis showed that patients were less likely to be discharged alive from the ICU if they met the following conditions: arterial hypertension (hazard ratio [HR] = 0.83 95% CI 0.723-0.964), diabetes mellitus (HR = 0.80 95% CI 0.696-0.938), older than 62 years (HR = 0.86 95% CI 0.790-0.956), obese (body mass index ≥ 30) (HR = 0.78 95% CI 0.697-0.887), 1 unit increase in SOFA score (HR = 0.94 95% CI 0.937-0.961), PaO2/FiO2 ratio <100 mm Hg (HR = 0.84 95% CI 0.786-0.914), and the use of invasive mechanical ventilation (HR = 0.68 95% CI 0.614-0.769). Risk factors associated with increased mortality were older age, obesity, arterial hypertension, and diabetes. Factors such as male gender, chronic obstructive pulmonary disease, acute kidney injury, and cancer reported in other investigations did not have the same effect on mortality in our study.

Outcome risk model development for heterogeneity of treatment effect analyses: a comparison of non-parametric machine learning methods and semi-parametric statistical methods

BackgroundIn randomized clinical trials, treatment effects may vary, and this possibility is referred to as heterogeneity of treatment effect (HTE). One way to quantify HTE is to partition participants into subgroups based on individual’s risk of experiencing an outcome, then measuring treatment effect by subgroup. Given the limited availability of externally validated outcome risk prediction models, internal models (created using the same dataset in which heterogeneity of treatment analyses also will be performed) are commonly developed for subgroup identification. We aim to compare different methods for generating internally developed outcome risk prediction models for subject partitioning in HTE analysis.MethodsThree approaches were selected for generating subgroups for the 2,441 participants from the United States enrolled in the ASPirin in Reducing Events in the Elderly (ASPREE) randomized controlled trial. An extant proportional hazards-based outcomes predictive risk model developed on the overall ASPREE cohort of 19,114 participants was identified and was used to partition United States’ participants by risk of experiencing a composite outcome of death, dementia, or persistent physical disability. Next, two supervised non-parametric machine learning outcome classifiers, decision trees and random forests, were used to develop multivariable risk prediction models and partition participants into subgroups with varied risks of experiencing the composite outcome. Then, we assessed how the partitioning from the proportional hazard model compared to those generated by the machine learning models in an HTE analysis of the 5-year absolute risk reduction (ARR) and hazard ratio for aspirin vs. placebo in each subgroup. Cochran’s Q test was used to detect if ARR varied significantly by subgroup.ResultsThe proportional hazard model was used to generate 5 subgroups using the quintiles of the estimated risk scores; the decision tree model was used to generate 6 subgroups (6 automatically determined tree leaves); and the random forest model was used to generate 5 subgroups using the quintiles of the prediction probability as risk scores. Using the semi-parametric proportional hazards model, the ARR at 5 years was 15.1% (95% CI 4.0–26.3%) for participants with the highest 20% of predicted risk. Using the random forest model, the ARR at 5 years was 13.7% (95% CI 3.1–24.4%) for participants with the highest 20% of predicted risk. The highest outcome risk group in the decision tree model also exhibited a risk reduction, but the confidence interval was wider (5-year ARR = 17.0%, 95% CI= -5.4–39.4%). Cochran’s Q test indicated ARR varied significantly only by subgroups created using the proportional hazards model. The hazard ratio for aspirin vs. placebo therapy did not significantly vary by subgroup in any of the models. The highest risk groups for the proportional hazards model and random forest model contained 230 participants each, while the highest risk group in the decision tree model contained 41 participants.ConclusionsThe choice of technique for internally developed models for outcome risk subgroups influences HTE analyses. The rationale for the use of a particular subgroup determination model in HTE analyses needs to be explicitly defined based on desired levels of explainability (with features importance), uncertainty of prediction, chances of overfitting, and assumptions regarding the underlying data structure. Replication of these analyses using data from other mid-size clinical trials may help to establish guidance for selecting an outcomes risk prediction modelling technique for HTE analyses.

Self-reported Visual Difficulty, Age-related Eye Disease, and Neuropsychiatric Outcomes in Older Adults

ABSTRACT Purpose Self-reported visual difficulty is consistently associated with dementia and other neuropsychiatric outcomes, but studies of specific age-related eye diseases have yielded conflicting results. Methods We conducted a retrospective cohort study using data from The National Health and Aging Trends Study, an ongoing nationally representative survey of older U.S. adults (n = 10,089). All subjects are screened for self-reported visual difficulty annually. Using linked Medicare claims data, we identified subjects with age-related macular degeneration (AMD), primary open-angle glaucoma (POAG), diabetic retinopathy, and cataract. For each condition, controls with complete Medicare eligibility and at least one eye care encounter were selected. We used semiparametric discrete time proportional hazards models to measure associations with incident dementia, and generalized estimating equations to examine longitudinal associations with depression, anxiety, and hallucinations, adjusting for baseline demographics and time-varying comorbidities. Results Self-reported visual difficulty was associated with dementia (HR 1.16, 95% CI: 1.00–1.34), depression (OR 1.14, 95% CI: 1.04–1.26), anxiety (OR 1.17, 95% CI: 1.06–1.29), and hallucinations (OR 1.54, 95% CI: 1.29–1.84). Diabetic retinopathy was associated with depression (OR 1.31, 95% CI: 1.05–1.64), and cataracts were associated with a lower risk of depression (OR 0.84, 95% CI: 0.74–0.95) and anxiety (OR 0.86, 95% CI: 0.75–0.99). There were no other associations between age-related eye disease and neuropsychiatric outcomes. Conclusion Self-reported visual difficulty is associated with dementia and other neuropsychiatric outcomes to a greater degree than age-related eye disease. These findings highlight the distinction between self-reported vision and clinically diagnosed eye disease with regard to health outcomes in older adults.

318 Discovering Subgroups with Supervised Machine Learning Models for Heterogeneity of Treatment Effect Analysis

OBJECTIVES/GOALS: The goal of the study is to provide insights into the use of machine learning methods as a means to predict heterogeneity of treatment effect (HTE) in participants of randomized clinical trials. METHODS/STUDY POPULATION: Using data from 2,441 participants enrolled in the ASPirin in Reducing Events in the Elderly (ASPREE) randomized controlled trial of daily low-dose aspirin vs placebo in the United States, we developed multivariable risk prediction models for the composite outcome of dementia, disability, or death. We used two machine learning techniques, decision trees and random forests, to develop novel non-parametric outcomes classifiers and generate risk-based subgroups. The comparator method was an extant semi-parametric proportional hazards predictive risk model. We then assessed HTE by examining the 5-year absolute risk reduction (ARR) of aspirin vs placebo in each risk subgroup. RESULTS/ANTICIPATED RESULTS: In the random forest classifier, the ARR at 5 years in the highest risk quintile was 13.7% (95% CI 3.1% to 24.4%). For the semi-parametric proportional hazards model, the ARR in the highest risk quintile was 15.1% (95% CI 4.0% to 26.3%). These results were comparable and provide evidence of the viability of internally developed parsimonious non-parametric machine learning models for HTE analysis. The decision tree model results (5-year ARR = 17.0%, 95% CI= -5.4% to 39.4% in the highest risk subgroup) exhibited more uncertainty in the results. DISCUSSION/SIGNIFICANCE: None of the models detected significant HTE on the relative scale; there was substantial HTE on the absolute scale in three of the models. Treatment benefit on the absolute scale may be regarded as bearing greater clinical importance and may be present even in the absence of benefit on the relative scale.

A semiparametric model for the cause-specific hazard under risk proportionality

Semiparametric Cox proportional hazards models enjoy great popularity in empirical survival analysis. A semiparametric model for cause-specific hazards under a proportionality restriction across risks is considered, which has desired practical properties such as estimation by partial likelihood and an analytical solution for the copula-graphic estimator. The cause-specific and marginal hazards are shown to share functional form restrictions in this case. The model for the cause-specific hazard can be used for inference about parametric restrictions on the marginal hazard without the risk of misspecifying the latter and without knowing the risk dependence. After the class of parametric marginal hazards has been determined, it can be estimated in conjunction with the degree of risk dependence. Finite sample properties are investigated with simulations. An application to employment duration demonstrates the practicality of the approach.

A Bayesian joint model for multivariate longitudinal and time-to-event data with application to ALL maintenance studies

ABSTRACT Retraction: A Bayesian joint model for multivariate longitudinal and time-to-event data with application to ALL maintenance studies (DOI: 10.1080/10543406.2023.2171430) We, the Publisher of the Journal of Biopharmaceutical Statistics, have retracted the following article: Damitri Kundu, Partha Sarkar & Kiranmoy Das. A Bayesian joint model for multivariate longitudinal and time-to-event data with application to ALL maintenance studies. Journal of Biopharmaceutical Statistics, Latest Articles. 2023. 10.1080/10543406.2023.2171430. This is an outdated version of a duplicate article published in March 2023 (DOI: 10.1080/10543406.2023.2187413). Although published online, this article was never compiled into an issue. We are now correcting the scholarly record. We have been informed in our decision-making by our policy on publishing ethics and integrity and the COPE guidelines on retractions. The retracted article will remain online to maintain the scholarly record, but it will be digitally watermarked on each page as “Retracted.”

Factors affecting the survival of patients with glioblastoma treated with standard and hypofractionated radiation regimens

Background. Glioblastoma has the worst prognosis and is the most common primary tumor of the central nervous system (CNS) among adults. Since it is multimodal treatment that increases survival chances of patients with glioblastoma, the analysis of factors that affect survival is a necessary precondition for developing more effective therapeutic approaches for this cohort. Such analysis makes it possible to determine the subgroups of patients which demonstrate the biggest therapeutic benefit from certain types of multimodal treatment, thus leading to implementation of personalized neuro-oncological treatment. Purpose. To analyze factors affecting cancer-specific survival (CSS) of patients with glioblastoma in stratification of the cohort according to the regimen of adjuvant radiation therapy into groups of standard and hypofractionated treatment regimens. Materials and methods. The single-center non-randomized study is based on the analysis of the results of the cohort of 159 patients with primarily diagnosed glioblastoma that were treated over the period from 2014 to 2020 at the State Institution «Romodanov Neurosurgery Institute of the National Academy of Medical Sciences of Ukraine». According to the regimen of radiation therapy, the patients of the cohort (n=159) were stratified into two groups: standard regimen group – 49 (30.8%) patients (30 fractions, total radiation dose of 60.0 Gy) and hypofractionated regimen group – 110 (69.2%) patients (15 fractions, total radiation dose of 52.5 Gy). The survival of the patients was analyzed by the Kaplan–Meier method. The log-rank test was used for comparing Kaplan–Meier survival curves for different studied groups. For the purpose of studying impact of independent variables on the survival, we used regression analysis according to semiparametric proportional hazards model. Hazard ratio was calculated with 95% confidence intervals (CI). Results and discussion. The median CSS in the total cohort was 16.6 (95% CI 14.1–17.8 months) months in median follow-up time of 23.8 (95% CI 21.9–27.3) months. In standard regimen group, the median CSS was 15.7 (95% CI 14.1–17.8) months in median follow-up time of 24.4 (95% CI 23.1–25.3) months. In hypofractionated regimen group, the median CSS was 17.5 (95% CI 14.6–19.7) months in median follow-up time of 22.3 (95% CI 21.3 – 27.2) months. According to the logrank test (taking into consideration cautions about its use), no statistically significant difference in CSS of patients of both groups was determined р=0.07&gt;0.05. For analysis of the impact of clinical factors (age, sex, radicality of the surgical treatment, chemotherapeutic treatment, functional status according to the Karnofsky scale) on the CSS of both groups, they were considered as the ones that may have different base hazard. Statistically significant impact of all studied covariates on the CSS was registered (p70 points, ceteris paribus. For male patients, the hazard of death is 1.7 times higher (р=0.016267; HR 1.7; 95% CI 1.1–2.5) than for female patients, ceteris paribus. Absence of chemotherapy in adjuvant treatment increases hazard of death by 2.37 times (HR 2.37; 95% CI 1.6–3.2), ceteris paribus. The hazard of death decreases, ceteris paribus, by 82% in chemotherapy with temozolomide and by 47% when the patient is younger than 60 years old (HR 0.53; 95% CI 0.4–0.8). Conclusions. This analysis is a stage of the study of differentiated treatment effect in groups of standard and hypofractionated regimens of radiation therapy in patients with glioblastoma. These data can be used for an in-depth subgroup analysis and serve as the basis for development of personalized approaches in treatment of neuro-oncological patients.

Expectation-Maximization Algorithm for the Weibull Proportional Hazard Model under Current Status Data

Due to the flexibility of the Weibull distribution and the proportional hazard (PH) model, Weibull PH is widely used in survival analysis under right censored data and interval censored data but it is seldom investigated under current status data, partially because there is less information in current status data than in right censored data and interval censored data. This paper considers the Weibull PH model under the current status data and introduces the Poisson latent variables to augment the data, then uses the expectation-maximization (EM) algorithm to obtain the maximum likelihood estimators of the model parameters. The EM algorithm is compared with the Newton–Raphson (NR) algorithm from several perspectives in the simulation studies, and the results show that the proposed method has several highlights, such as computational simplicity, improved convergence stability, and overall estimator results that are either comparable or slightly better in terms of bias. Furthermore, the performance of the Weibull PH model and the semi-parametric PH model is compared under two simulation scenarios, and two standard model selection criteria are used for model selection. The results indicate that the Weibull PH model has significant advantages when failure time follows a Weibull distribution. Lastly, the Weibull PH model along with EM algorithm is applied to lung tumor data and intraocular lens (IOL) calcification data with the aim of assessing the impact of covariates, including environmental factors and gender, on event timing and risk.

A single risk approach to the semiparametric competing risks model with parametric Archimedean risk dependence

This paper considers a dependent competing risks model with the distribution of one risk being a semiparametric proportional hazards model, whereas the model for the other risks and the degree of risk dependence of an Archimedean copula are unknown. Identifiability is shown when there is at least one covariate with at least two values. Estimation is done by means of a n-consistent semiparametric two-step procedure. Applicability and attractive finite sample performance are demonstrated with the help of simulations. An application to unemployment duration confirms the importance of estimating rather than assuming risk dependence.

CausalCmprsk: An R package for nonparametric and Cox-based estimation of average treatment effects in competing risks data

Background and ObjectiveCompeting risks data arise in both observational and experimental clinical studies with time-to-event outcomes, when each patient might follow one of the multiple mutually exclusive competing paths. Ignoring competing risks in the analysis can result in biased conclusions. In addition, possible confounding bias of the treatment-outcome relationship has to be addressed, when estimating treatment effects from observational data. In order to provide tools for estimation of average treatment effects on time-to-event outcomes in the presence of competing risks, we developed the R package causalCmprsk. We illustrate the package functionality in the estimation of effects of a right heart catheterization procedure on discharge and in-hospital death from observational data. MethodsThe causalCmprsk package implements an inverse probability weighting estimation approach, aiming to emulate baseline randomization and alleviate possible treatment selection bias. The package allows for different types of weights, representing different target populations. causalCmprsk builds on existing methods from survival analysis and adapts them to the causal analysis in non-parametric and semi-parametric frameworks. ResultsThe causalCmprsk package has two main functions: fit.cox assumes a semiparametric structural Cox proportional hazards model for the counterfactual cause-specific hazards, while fit.nonpar does not impose any structural assumptions. In both frameworks, causalCmprsk implements estimators of (i) absolute risks for each treatment arm, e.g., cumulative hazards or cumulative incidence functions, and (ii) relative treatment effects, e.g., hazard ratios, or restricted mean time differences. The latter treatment effect measure translates the treatment effect from probability into more intuitive time domain and allows the user to quantify, for example, by how many days or months the treatment accelerates the recovery or postpones illness or death. ConclusionsThe causalCmprsk package provides a convenient and useful tool for causal analysis of competing risks data. It allows the user to distinguish between different causes of the end of follow-up and provides several time-varying measures of treatment effects. The package is accompanied by a vignette that contains more details, examples and code, making the package accessible even for non-expert users.

Bayesian semiparametric mixed effects proportional hazards model for clustered partly interval-censored data

Clustered partly interval-censored survival data naturally arise from many medical and epidemiological studies. We propose a Bayesian semiparametric approach for fitting a mixed effects proportional hazards (PH) model to clustered partly interval-censored data. The proposed method allows for not only a random intercept as most frailty models do for clustered survival data, but also random effects of covariates. We assume a normal prior for each random intercept/random effect, seeing the instability of a gamma prior for a frailty in this situation. Simulation studies with data generated from both mixed effects PH model and mixed effects accelerated failure times model are conducted, to evaluate the performance of the proposed method and compare it with the three methods currently available in the literature. The application of the proposed approach is illustrated through analyzing the progression-free survival data derived from a phase III metastatic colorectal cancer clinical trial.

0449 Unbiased Examination of Metabolomic Signatures in Sleep Disordered Breathing and Group 1 PAH in the (PVDOMICS) Cohort

Abstract Introduction Metabolic alterations have been identified as a novel driver of pulmonary arterial hypertension (PAH) pathogenesis. Sleep disordered breathing (SDB), characterized by intermittent hypoxemic episodes, has also been implicated in PAH, particularly when associated with more profound degrees of hypoxia, and metabolic dysfunction. We hypothesize to observe in SDB and PAH in humans a similar pattern of metabolic alterations as previously described in animal models of PAH. Methods Pulmonary Vascular Disease Phenomics (PVDOMICS,NCT02980887), a multicenter study, was designed in part to elucidate molecular signatures in PH. We analyzed data from Group 1 PAH participants who underwent home sleep apnea testing with circulating plasma metabolomic measures (Metabolon). We conducted an unbiased analysis of SDB measures: apnea-hypopnea index (AHI, 3% oxygen desaturation hypopnea definition) and % recording time&amp;lt; 90% SpO2 (TRT&amp;lt; 90%), with metabolites (954 after qc filtering) using a flexible and robust semi-parametric proportional hazards model adjusted for age, sex, body mass index (BMI), diabetes mellitus (DM), race and study site. Metabolites with False discovery rate (FDR) adjusted p-values &amp;lt; 0.1 were called significant. Closed-set testing with the Simes method and Metabolon provided annotations (90 sets) was used to test metabolite sets. Results The cohort (n=175) was 72% female, 81% White and 16% DM with (1st Quartile/Median/3rd Quartile) Age: 42/54/63 years, BMI: 24.6/29.1/34.1 kg/m2, AHI: 0.9/4.3/12.6 and TRT&amp;lt; 90%: 2.3/37/87.4. 21 metabolites showed significant association with TRT&amp;lt; 90% (8 with positive direction/13 negative) and 0 with AHI. Among metabolite sets, Pregnenolone steroids had the strongest association with TRT&amp;lt; 90% (6 members; adjusted p=0.038; True Discovery Proportion (TDP)=0.33) followed by Fatty Acid Metabolism (Acyl Choline) (7 members; adjusted p-value=0.046; TDP=0.71) and Polyamine Metabolism (7 members; adjusted p-value p=0.054; TDP=0.14). Conclusion Three primary metabolite pathways were associated with sleep-related hypoxia in Group 1 PAH. Polyamine metabolism and fatty acid metabolism changes have previously been observed in a rat PAH model, consistent with our findings. Findings specific to metabolic biomarkers in SDB and PAH are novel and may lead to insights that broaden our understanding of PAH pathobiology and potential therapeutic targets. Support (if any)

Improving marginal hazard ratio estimation using quadratic inference functions.

Clustered and multivariate failure time data are commonly encountered in biomedical studies and a marginal regression approach is often employed to identify the potential risk factors of a failure. We consider a semiparametric marginal Cox proportional hazards model for right-censored survival data with potential correlation. We propose to use a quadratic inference function method based on the generalized method of moments to obtain the optimal hazard ratio estimators. The inverse of the working correlation matrix is represented by the linear combination of basis matrices in the context of the estimating equation. We investigate the asymptotic properties of the regression estimators from the proposed method. The optimality of the hazard ratio estimators is discussed. Our simulation study shows that the estimator from the quadratic inference approach is more efficient than those from existing estimating equation methods whether the working correlation structure is correctly specified or not. Finally, we apply the model and the proposed estimation method to analyze a study of tooth loss and have uncovered new insights that were previously inaccessible using existing methods.

Semiparametric model averaging method for survival probability predictions of patients

In biomedical and clinical research, predicting the survival probabilities for patients is a core task. Accurate survival probability predictions can help physicians make better treatments or prevention plans for patients. A novel semiparametric proportional hazards model averaging prediction technique is introduced to address this problem. Under the potential partly linear additive structures, the conditional survival probabilities of individuals can be predicted by the weighted averages of submodels which are estimated by maximizing the partial likelihood functions. The selection of weights is a crucial part of model averaging since the weights can affect the accuracy of survival probability prediction. A Brier score type criterion is employed to choose the optimal model averaging weights and the rate of convergence of the selected weights is studied. In addition, the finite sample performance of the proposed method is evaluated via abundant simulation studies. To further illustrate the effectiveness of the proposed approach, the model averaging is applied to heart failure data.

A Bayesian joint model for multivariate longitudinal and time-to-event data with application to ALL maintenance studies

ABSTRACT The most common type of cancer diagnosed among children is the Acute Lymphocytic Leukemia (ALL). A study was conducted by Tata Translational Cancer Research Center (TTCRC) Kolkata, in which 236 children (diagnosed as ALL patients) were treated for the first two years (approximately) with two standard drugs (6MP and MTx) and were then followed nearly for the next 3 years. The goal is to identify the longitudinal biomarkers that are associated with time-to-relapse, and also to assess the effectiveness of the drugs. We develop a Bayesian joint model in which a linear mixed model is used to jointly model three biomarkers (i.e. white blood cell count, neutrophil count, and platelet count) and a semi-parametric proportional hazards model is used to model the time-to-relapse. Our proposed joint model can assess the effects of different covariates on the progression of the biomarkers, and the effects of the biomarkers (and the covariates) on time-to-relapse. In addition, the proposed joint model can impute the missing longitudinal biomarkers efficiently. Our analysis shows that the white blood cell (WBC) count is not associated with time-to-relapse, but the neutrophil count and the platelet count are significantly associated with it. We also infer that a lower dose of 6MP and a higher dose of MTx jointly result in a lower relapse probability in the follow-up period. Interestingly, we find that relapse probability is the lowest for the patients classified into the “high-risk” group at presentation. The effectiveness of the proposed joint model is assessed through the extensive simulation studies.

Risk of CKD Following Detection of Microscopic Hematuria: A Retrospective Cohort Study

Microscopic hematuria is an uncertain risk factor for chronic kidney disease (CKD). We investigated the association between persistent or single episodes of microscopic hematuria and the development of incident CKD, overall and separately among men and women. Retrospective cohort study. A total of 232,220 Korean adults without CKD at baseline who underwent repeated regular health examinations at Kangbuk Samsung Health Study formed the study cohort. Microscopic hematuria was defined by≥5 red blood cells per high-power field. Participants were categorized into 1 of 4 groups according to the presence of hematuria at 2 consecutive examinations: (1) no hematuria at both examinations (reference group); (2) hematuria followed by no hematuria (regressed hematuria group); (3) no hematuria followed by hematuria (developed hematuria group); and (4) hematuria at both examinations (persistent hematuria group). CKD was defined as an estimated glomerular filtration rate<60mL/min/1.73m2 or proteinuria (1+or more on dipstick examination). Semiparametric proportional hazards models were used to estimate hazard ratios. During a 4.8-year median follow-up period, 2,392 participants developed CKD. Multivariable-adjusted hazard ratios for incident CKD, comparing the regressed, developed, and persistent hematuria groups to the no-hematuria group were 1.85 (95% CI, 1.35-2.53), 3.18 (95% CI, 2.54-3.98), and 5.23 (95% CI, 4.15-6.59), respectively. The association between persistent hematuria and incident CKD was stronger in men than women (P for interaction<0.001), although a statistically significant association was observed in both sexes. Lack of albuminuria and inability to consider specific glomerular diseases. Men and women with microscopic hematuria, especially persistent hematuria, may be at increased risk of CKD.

Semiparametric single-index models for optimal treatment regimens with censored outcomes.

There is a growing interest in precision medicine, where a potentially censored survival time is often the most important outcome of interest. To discover optimal treatment regimens for such an outcome, we propose a semiparametric proportional hazards model by incorporating the interaction between treatment and a single index of covariates through an unknown monotone link function. This model is flexible enough to allow non-linear treatment-covariate interactions and yet provides a clinically interpretable linear rule for treatment decision. We propose a sieve maximum likelihood estimation approach, under which the baseline hazard function is estimated nonparametrically and the unknown link function is estimated via monotone quadratic B-splines. We show that the resulting estimators are consistent and asymptotically normal with a covariance matrix that attains the semiparametric efficiency bound. The optimal treatment rule follows naturally as a linear combination of the maximum likelihood estimators of the model parameters. Through extensive simulation studies and an application to an AIDS clinical trial, we demonstrate that the treatment rule derived from the single-index model outperforms the treatment rule under the standard Cox proportional hazards model.

Board of Directors versus the CEO: Social Networks and CEO Dismissal

This study draws on social capital theory and social network analysis literature to examine the research question of when CEOs are dismissed. It views CEO dismissal as a contest between the board and the CEO powered by their position within the upper echelons social network. We test hypotheses on firms listed in Standard and Poor’s ExecuComp for the period 2000-2016 using a Cox (1972) semiparametric proportional hazard model. Findings show that the higher the network centrality of directors in the upper echelons social network, the more likely they are to dismiss the CEO. In addition, this relationship is negatively moderated by the centrality of the CEO’s position within the social network, and the overlap of the CEO’s and the directors’ social networks. The study extends the literature on the socio-political perspective as it finds that the directors’ social networks affect CEO dismissal. Findings have implications for the criteria used to select board directors.

Effect of High Altitude on the Survival of COVID-19 Patients in Intensive Care Unit: A Cohort Study.

Purpose: The effect of high altitude ( ≥ 1500 m) and its potential association with mortality by COVID-19 remains controversial. We assessed the effect of high altitude on the survival/discharge of COVID-19 patients requiring intensive care unit (ICU) admission for mechanical ventilation compared to individuals treated at sea level. Methods: A retrospective cohort multi-center study of consecutive adults patients with a positive RT-PCR test for COVID-19 who were mechanically ventilated between March and November 2020. Data were collected from two sea-level hospitals and four high-altitude hospitals in Ecuador. The primary outcome was ICU and hospital survival/discharge. Survival analysis was conducted using semi-parametric Cox proportional hazards models. Results: Of the study population (n = 670), 35.2% were female with a mean age of 58.3 ± 12.6 years. On admission, high-altitude patients were more likely to be younger (57.2 vs. 60.5 years old), presented with less comorbidities such as hypertension (25.9% vs. 54.9% with p-value <.001) and diabetes mellitus (20.5% vs. 37.2% with p-value <.001), less probability of having a capillary refill time > 3 sec (13.7% vs. 30.1%, p-value <.001), and less severity-of-illness condition (APACHE II score, 17.5 ± 8.1 vs. 20 ± 8.2, p < .01). After adjusting for key confounders high altitude is associated with significant higher probabilities of ICU survival/discharge (HR: 1.74 [95% CI: 1.46-2.08]) and hospital survival/discharge (HR: 1.35 [95% CI: 1.18-1.55]) than patients treated at sea level. Conclusions: Patients treated at high altitude at any time point during the study period were 74% more likely to experience ICU survival/discharge and 35% more likely to experience hospital survival/discharge than to the sea-level group. Possible reasons for these findings are genetic and physiological adaptations due to exposure to chronic hypoxia.