Making sense of breast cancer risk estimates.

Individual probabilistic assessments on the risk of cancer, primary or secondary, will not be understood by most patients. That is the essence of our arguments in this paper. Greater understanding can be achieved by extensive, intensive, and detailed counseling. But since probability itself is a concept that easily escapes our everyday intuition-consider the famous Monte Hall paradox-then it would also be wise to advise patients and potential patients, to not put undue weight on any probabilistic assessment. Such assessments can be of value to the epidemiologist in the investigation of different potential etiologies describing cancer evolution or to the clinical trialist as a way to maximize design efficiency. But to an ordinary individual we cannot anticipate that these assessments will be correctly interpreted.

Fast and flexible inference for joint models of multivariate longitudinal and survival data using integrated nested Laplace approximations.

Modeling longitudinal and survival data jointly offers many advantages such as addressing measurement error and missing data in the longitudinal processes, understanding and quantifying the association between the longitudinal markers and the survival events, and predicting the risk of events based on the longitudinal markers. A joint model involves multiple submodels (one for each longitudinal/survival outcome) usually linked together through correlated or shared random effects. Their estimation is computationally expensive (particularly due to a multidimensional integration of the likelihood over the random effects distribution) so that inference methods become rapidly intractable, and restricts applications of joint models to a small number of longitudinal markers and/or random effects. We introduce a Bayesian approximation based on the integrated nested Laplace approximation algorithm implemented in the R package R-INLA to alleviate the computational burden and allow the estimation of multivariate joint models with fewer restrictions. Our simulation studies show that R-INLA substantially reduces the computation time and the variability of the parameter estimates compared with alternative estimation strategies. We further apply the methodology to analyze five longitudinal markers (3 continuous, 1 count, 1 binary, and 16 random effects) and competing risks of death and transplantation in a clinical trial on primary biliary cholangitis. R-INLA provides a fast and reliable inference technique for applying joint models to the complex multivariate data encountered in health research.

Pooling controls from nested case-control studies with the proportional risks model.

The standard approach to regression modeling for cause-specific hazards with prospective competing risks data specifies separate models for each failure type. An alternative proposed by Lunn and McNeil (1995) assumes the cause-specific hazards are proportional across causes. This may be more efficient than the standard approach, and allows the comparison of covariate effects across causes. In this paper, we extend Lunn and McNeil (1995) to nested case-control studies, accommodating scenarios with additional matching and non-proportionality. We also consider the case where data for different causes are obtained from different studies conducted in the same cohort. It is demonstrated that while only modest gains in efficiency are possible in full cohort analyses, substantial gains may be attained in nested case-control analyses for failure types that are relatively rare. Extensive simulation studies are conducted and real data analyses are provided using the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial (PLCO) study.

A transformer model for cause-specific hazard prediction.

BACKGROUD: Modelling discrete-time cause-specific hazards in the presence of competing events and non-proportional hazards is a challenging task in many domains. Survival analysis in longitudinal cohorts often requires such models; notably when the data is gathered at discrete points in time and the predicted events display complex dynamics. Current models often rely on strong assumptions of proportional hazards, that is rarely verified in practice; or do not handle sequential data in a meaningful way. This study proposes a Transformer architecture for the prediction of cause-specific hazards in discrete-time competing risks. Contrary to Multilayer perceptrons that were already used for this task (DeepHit), the Transformer architecture is especially suited for handling complex relationships in sequential data, having displayed state-of-the-art performance in numerous tasks with few underlying assumptions on the task at hand. RESULTS: Using synthetic datasets of 2000-50,000 patients, we showed that our Transformer model surpassed the CoxPH, PyDTS, and DeepHit models for the prediction of cause-specific hazard, especially when the proportional assumption did not hold. The error along simulated time outlined the ability of our model to anticipate the evolution of cause-specific hazards at later time steps where few events are observed. It was also superior to current models for prediction of dementia and other psychiatric conditions in the English longitudinal study of ageing cohort using the integrated brier score and the time-dependent concordance index. We also displayed the explainability of our model's prediction using the integrated gradients method. CONCLUSIONS: Our model provided state-of-the-art prediction of cause-specific hazards, without adopting prior parametric assumptions on the hazard rates. It outperformed other models in non-proportional hazards settings for both the synthetic dataset and the longitudinal cohort study. We also observed that basic models such as CoxPH were more suited to extremely simple settings than deep learning models. Our model is therefore especially suited for survival analysis on longitudinal cohorts with complex dynamics of the covariate-to-outcome relationship, which are common in clinical practice. The integrated gradients provided the importance scores of input variables, which indicated variables guiding the model in its prediction. This model is ready to be utilized for time-to-event prediction in longitudinal cohorts.

Death ORACL: An Algorithm to Predict Death Using Insurance Claims Data.

The inability to identify dates of death in insurance claims data is the United States is a major limitation to retrospective claims-based research. While deaths result in disenrollment, disenrollment can also occur due to changes in insurance providers. We created an algorithm to differentiate between disenrollment from health plans due to death and disenrollment for other reasons. We identified 5,259,735 adults who disenrolled from private insurance between 2007 and 2018. Using death dates ascertained from the Social Security Death Index, inpatient discharge status, and death indicators in the administrative data, 7.6% of all disenrollments were classified as resulting from death. We used elastic net regression to build an algorithm using claims data in the year prior to disenrollment; candidate predictors included medical conditions, individual demographic characteristics, treatment utilization, and structural factors related to health insurance eligibility and coding. Using a predicted probability threshold of 0.9 (selected to reflect the corresponding known prevalence of mortality), internal validation found that the algorithm classified death at disenrollment with a positive predictive value of 0.815, sensitivity of 0.721 and specificity of 0.986 (AUC=0.97). Independent data sources were used for external validation and for an applied example. Code for implementation is publicly available.

Causal Effects of Competing Obstetrical Interventions: Mediators of Placental Abruption and Perinatal Mortality.

Placental abruption, the premature placental separation, confers increased perinatal mortality risk with preterm delivery as an important pathway through which the risk appears mediated. While pregnancies complicated by abruption are often delivered through an obstetrical intervention, many deliver spontaneously. We examined the contributions of clinician-initiated (PTDIND) and spontaneous (PTDSPT) preterm delivery at <37 weeks as competing causal mediators of the abruption-perinatal mortality association. Using the Consortium for Safe Labor (2002-2008) data (n = 203,990; 1.6% with abruption), we applied a potential outcomes-based mediation analysis to decompose the total effect into direct and mediator-specific indirect effects through PTDIND and PTDSPT. Each mediated effect describes the reduction in the counterfactual mortality risk if that preterm delivery subtype was shifted from its distribution under abruption to without abruption. The total effect risk ratio (RR) of abruption on perinatal mortality was 5.4 (95% confidence interval [CI] 4.6, 6.3). The indirect effect RRs for PTDIND and PTDSPT were 1.5 (95% CI: 1.4, 1.6) and 1.5 (95% CI: 1.5, 1.6), respectively; these corresponded to mediated proportions of 25% each. These findings underscore that spontaneous and clinician-initiated preterm deliveries each play essential roles in shaping perinatal mortality risks associated with placental abruption.

Can metformin prevent cancer relative to sulfonylureas? A target trial emulation accounting for competing risks and poor overlap via double/debiased machine learning estimators.

There is mounting interest in the possibility that metformin, indicated for glycemic control in type 2 diabetes, has a range of additional beneficial effects. Randomized trials have shown that metformin prevents adverse cardiovascular events, and metformin use has also been associated with reduced cognitive decline and cancer incidence. In this paper, we dig more deeply into whether metformin prevents cancer by emulating target randomized trials comparing metformin to sulfonylureas as first line diabetes therapy using data from Clinical Practice Research Datalink, a U.K. primary care database (1987-2018). We included individuals with diabetes, no prior cancer diagnosis, no chronic kidney disease, and no prior diabetes therapy who initiated metformin (N=93353) or a sulfonylurea (N=13864). In our cohort, the estimated overlap weighted additive separable direct effect of metformin compared to sulfonylureas on cancer risk at 6 years was -1% (.95 CI=-2.2%, 0.1%), which is consistent with metformin providing no direct protection against cancer incidence or substantial protection. The analysis faced two methodological challenges-poor overlap, and pre-cancer death as a competing risk. To address these issues while minimizing nuisance model misspecification, we develop and apply double/debiased machine learning estimators of overlap weighted separable effects in addition to more traditional effect estimates.

Does breast cancer modify the long-term relationship between lifestyle behaviors and mortality? A prospective analysis of breast cancer survivors and population-based controls.

BACKGROUND: Modifiable lifestyle factors are known to impact survival. It is less clear whether this differs between postmenopausal women ever diagnosed with breast cancer and unaffected women. METHODS: Women diagnosed with breast cancer and unaffected women of comparable age were recruited from 2002 to 2005 and followed up until 2020. Using baseline information, a lifestyle adherence score (range 0-8; categorized as low [0-3.74], moderate [3.75-4.74], and high [≥4.75]) was created based on the 2018 World Cancer Research Fund/American Institute for Cancer Research (WCRF/AICR) cancer prevention recommendations. Cox regression and competing risks analysis were used to analyze the association of adherence to WCRF/AICR lifestyle recommendations with overall mortality and with death due to cardiovascular diseases and cancer, respectively. RESULTS: A total of 8584 women were included (2785 with breast cancer and 5799 without). With a median follow-up of 16.1 years there were 2006 total deaths. Among the deaths of known causes (98.6%), 445 were cardiovascular-related and 1004 were cancer-related. The average lifestyle score was 4.2. There was no differential effect of lifestyle score by case-control status on mortality. After adjusting for covariates, moderate (hazard ratio [HR], 0.66; 95% confidence interval [CI], 0.57-0.76) and high (HR, 0.54; 95% CI, 0.47-0.63) adherence to WCRF/AICR lifestyle recommendations were significantly associated with a decrease in overall mortality. Similarly, in competing risks analysis, moderate and high adherence were associated with decreased mortality from cardiovascular diseases and from cancer. CONCLUSIONS: A healthy lifestyle can substantially reduce mortality risk in women. With low adherence to all WCRF/AICR guidelines in about a third of study participants, health interventions are warranted.

A competing risks model to estimate the risk of graft failure and patient death after kidney transplantation using continuous donor-recipient age combinations.

Graft failure and recipient death with functioning graft are important competing outcomes after kidney transplantation. Risk prediction models typically censor for the competing outcome thereby overestimating the cumulative incidence. The magnitude of this overestimation is not well described in real-world transplant data. This retrospective cohort study analyzed data from the European Collaborative Transplant Study (n = 125 250) and from the American Scientific Registry of Transplant Recipients (n = 190 258). Separate cause-specific hazard models using donor and recipient age as continuous predictors were developed for graft failure and recipient death. The hazard of graft failure increased quadratically with increasing donor age and decreased decaying with increasing recipient age. The hazard of recipient death increased linearly with increasing donor and recipient age. The cumulative incidence overestimation due to competing risk-censoring was largest in high-risk populations for both outcomes (old donors/recipients), sometimes amounting to 8.4 and 18.8 percentage points for graft failure and recipient death, respectively. In our illustrative model for posttransplant risk prediction, the absolute risk of graft failure and death is overestimated when censoring for the competing event, mainly in older donors and recipients. Prediction models for absolute risks should treat graft failure and death as competing events.

Semiparametric marginal regression for clustered competing risks data with missing cause of failure.

Clustered competing risks data are commonly encountered in multicenter studies. The analysis of such data is often complicated due to informative cluster size (ICS), a situation where the outcomes under study are associated with the size of the cluster. In addition, the cause of failure is frequently incompletely observed in real-world settings. To the best of our knowledge, there is no methodology for population-averaged analysis with clustered competing risks data with an ICS and missing causes of failure. To address this problem, we consider the semiparametric marginal proportional cause-specific hazards model and propose a maximum partial pseudolikelihood estimator under a missing at random assumption. To make the latter assumption more plausible in practice, we allow for auxiliary variables that may be related to the probability of missingness. The proposed method does not impose assumptions regarding the within-cluster dependence and allows for ICS. The asymptotic properties of the proposed estimators for both regression coefficients and infinite-dimensional parameters, such as the marginal cumulative incidence functions, are rigorously established. Simulation studies show that the proposed method performs well and that methods that ignore the within-cluster dependence and the ICS lead to invalid inferences. The proposed method is applied to competing risks data from a large multicenter HIV study in sub-Saharan Africa where a significant portion of causes of failure is missing.

Rheumatoid arthritis and the risk of ischemic stroke after diagnosis of atrial fibrillation: a Norwegian nationwide register study.

OBJECTIVES: Rheumatoid arthritis (RA) patients have an increased risk for cardiovascular diseases, including atrial fibrillation (AF), but the impact of RA on ischemic stroke risk in the context of AF remains unknown. We explored whether the risk of ischemic stroke after diagnosis of AF is further increased among patients with RA compared with non-RA patients. METHODS: In the nationwide Norwegian Cardio-Rheuma Register, we evaluated cumulative incidence and hazard rate of ischemic stroke after the first AF diagnosis (2,750 individuals with RA and 158 879 without RA between 2010 and 2017) by using a competing risk model with a 3-month delayed entry. RESULTS: The 5-year unadjusted cumulative incidence of ischemic stroke was 7.3% (95% CI: 5.9%-8.7%) for patients with RA and 5.0% (95% CI 4.9%-5.2%) for patients without RA. Unadjusted univariate analyses indicated that AF patients with RA had a HR of 1.36 (95% CI: 1.13, 1.62) for ischemic stroke compared with those without RA. Sex- and age-adjusted HR for ischemic stroke in RA patients with AF was 1.25 (95% CI: 1.05, 1.50), and the effect size remained unchanged after adjustment for diabetes, hypertension, atherosclerotic cardiovascular disease, and oral anticoagulant (OAC) treatment. RA patients were less likely to receive OAC treatment than non-RA patients (adjusted odds ratio 0.88, 95% CI 0.80, 0.97). CONCLUSION: RA patients diagnosed with AF are at a further increased risk for stroke compared with non-RA patients with AF, and less likely to receive OAC treatment, emphasizing the need to improve stroke prevention in AF patients with RA.

First trimester risk of preeclampsia and rate of spontaneous birth in patients without preeclampsia.

BACKGROUND: First-trimester screening for preeclampsia using a combination of maternal risk factors and mean arterial pressure, uterine artery pulsatility index, and placental growth factor, as proposed by the Fetal Medicine Foundation, provides effective prediction of preterm preeclampsia. Placental dysfunction is a potential precursor of spontaneous birth. OBJECTIVE: The objective of this study was to examine if the estimated risk of preeclampsia is associated with the gestational age at onset of spontaneous delivery in the absence of preeclampsia. STUDY DESIGN: This was a secondary analysis of the data from the Screening programme for pre-eclampsia trial in which there was a comparison of the performance of first-trimester screening for preterm preeclampsia using the Fetal Medicine Foundation model vs a traditional history-based risk scoring system. A subgroup of women from the trial with spontaneous onset of delivery (labor with intact membranes or preterm prelabor rupture of membranes) was included in this study and was arbitrarily divided into 3 groups according to the risk for preterm preeclampsia as determined by the Fetal Medicine Foundation model at 11 to 13 weeks' gestation as follows: group 1 low risk (˂1/100); group 2 intermediate risk (1/50 to 1/100); and group 3 high risk (˃1/50). A survival analysis was carried out using a Kaplan-Meier estimator and a Cox regression analysis with stratification by the 3 preeclampsia risk groups. Occurrence of spontaneous birth in the study groups was compared using log-rank tests and hazard ratios. RESULTS: The study population comprised 10,820 cases with delivery after spontaneous onset of labor among the 16,451 cases who participated in the Screening programme for pre-eclampsia trial. There were 9795 cases in group 1, 583 in group 2, and 442 in group 3. The gestational age at delivery was <28, <32, <35, <37, and <40 weeks in 0.29%, 0.64%, 1.68%, 4.52%, and 44.97% of cases, respectively, in group 1; 0.69%, 1.71%, 3.26%, 7.72%, and 55.23% of cases, respectively, in group 2; and 0.45%, 1.81%, 5.66%, 13.80%, and 63.12% of cases, respectively, in group 3. The curve profile of gestational age at spontaneous birth in the 3 study groups was significantly different overall and in pairwise comparisons (P values <.001). The Cox regression analysis showed that risks increased for spontaneous birth by 18% when the intermediate-risk group was compared with the low-risk group (P˂.001) and by 41% when the high-risk group was compared with the low-risk group (P˂.001). CONCLUSION: In this study that investigated birth after spontaneous onset of labor in women without preeclampsia, there were 2 major findings. First, the duration of pregnancy decreased with increasing first-trimester risk for preeclampsia. Second, in the high-risk group, when compared with the low-risk group, the risk for spontaneous birth was 4 times higher at a gestational age of 24 to 26 weeks, 3 times higher at 28 to 32 weeks, and 2 times higher at 34 to 39 weeks. These differences present major clinical implications for antepartum counselling, monitoring, and interventions in these pregnancies.

Maternal vascular indices at 36 weeks' gestation in the prediction of preeclampsia.

BACKGROUND: Epidemiological studies have shown that women with preeclampsia (PE) are at increased long term cardiovascular risk. This risk might be associated with accelerated vascular ageing process but data on vascular abnormalities in women with PE are scarce. OBJECTIVE: This study aimed to identify the most discriminatory maternal vascular index in the prediction of PE at 35 to 37 weeks' gestation and to examine the performance of screening for PE by combinations of maternal risk factors and biophysical and biochemical markers at 35 to 37 weeks' gestation. STUDY DESIGN: This was a prospective observational nonintervention study in women attending a routine hospital visit at 35 0/7 to 36 6/7 weeks' gestation. The visit included recording of maternal demographic characteristics and medical history, vascular indices, and hemodynamic parameters obtained by a noninvasive operator-independent device (pulse wave velocity, augmentation index, cardiac output, stroke volume, central systolic and diastolic blood pressures, total peripheral resistance, and fetal heart rate), mean arterial pressure, uterine artery pulsatility index, and serum concentration of placental growth factor and soluble fms-like tyrosine kinase-1. The performance of screening for delivery with PE at any time and at <3 weeks from assessment using a combination of maternal risk factors and various combinations of biomarkers was determined. RESULTS: The study population consisted of 6746 women with singleton pregnancies, including 176 women (2.6%) who subsequently developed PE. There were 3 main findings. First, in women who developed PE, compared with those who did not, there were higher central systolic and diastolic blood pressures, pulse wave velocity, peripheral vascular resistance, and augmentation index. Second, the most discriminatory indices were systolic and diastolic blood pressures and pulse wave velocity, with poor prediction from the other indices. However, the performance of screening by a combination of maternal risk factors plus mean arterial pressure was at least as high as that of a combination of maternal risk factors plus central systolic and diastolic blood pressures; consequently, in screening for PE, pulse wave velocity, mean arterial pressure, uterine artery pulsatility index, placental growth factor, and soluble fms-like tyrosine kinase-1 were used. Third, in screening for both PE within 3 weeks and PE at any time from assessment, the detection rate at a false-positive rate of 10% of a biophysical test consisting of maternal risk factors plus mean arterial pressure, uterine artery pulsatility index, and pulse wave velocity (PE within 3 weeks: 85.2%; 95% confidence interval, 75.6%-92.1%; PE at any time: 69.9%; 95% confidence interval, 62.5%-76.6%) was not significantly different from a biochemical test using the competing risks model to combine maternal risk factors with placental growth factor and soluble fms-like tyrosine kinase-1 (PE within 3 weeks: 80.2%; 95% confidence interval, 69.9%-88.3%; PE at any time: 64.2%; 95% confidence interval, 56.6%-71.3%), and they were both superior to screening by low placental growth factor concentration (PE within 3 weeks: 53.1%; 95% confidence interval, 41.7%-64.3%; PE at any time: 44.3; 95% confidence interval, 36.8%-52.0%) or high soluble fms-like tyrosine kinase-1-to-placental growth factor concentration ratio (PE within 3 weeks: 65.4%; 95% confidence interval, 54.0%-75.7%; PE at any time: 53.4%; 95% confidence interval, 45.8%-60.9%). CONCLUSION: First, increased maternal arterial stiffness preceded the clinical onset of PE. Second, maternal pulse wave velocity at 35 to 37 weeks' gestation in combination with mean arterial pressure and uterine artery pulsatility index provided effective prediction of subsequent development of preeclampsia.

Competitive Risk Analysis of Prognosis in Older Adults with Sigmoid Colon Adenocarcinoma: A Population-Based Study.

BACKGROUND: The purpose of this study is to employ a competing risk model based on the Surveillance, Epidemiology, and End Results (SEER) database to identify prognostic factors for elderly individuals with sigmoid colon adenocarcinoma (SCA) and compare them with the classic Cox proportional hazards model. METHODS: We extracted data from elderly patients diagnosed with SCA registered in the SEER database between 2010 and 2015. Univariate analysis was conducted using cumulative incidence functions and Gray's test, while multivariate analysis was performed using both the Fine-Gray and Cox proportional hazards models. RESULTS: Among the 10,712 eligible elderly patients diagnosed with SCA, 5595 individuals passed away: 2987 due to sigmoid colon adenocarcinoma and 2608 from other causes. The results of one-way Gray's test showed that age, race, marital status, AJCC stage, differentiation grade, tumor size, surgical status, liver metastasis status, lung metastasis status, brain metastasis status, radiotherapy status, and chemotherapy status all affected the prognosis of SCA (P < .05). Multivariate analysis showed that sex, age, race, marital status, and surgical status affected the prognosis of SCA (P < .05). Multifactorial Fine-Gray analysis revealed that key factors influencing the prognosis of SCA patients include age, race, marital status, AJCC stage, grade classification, surgical status, tumor size, liver metastasis, lung metastasis, and chemotherapy status (P < .05). CONCLUSION: Data from the SEER database were used to more accurately estimate CIFs for sigmoid colon adenocarcinoma-specific mortality and prognostic factors using competing risk models.

Efficient estimation for left-truncated competing risks regression for case-cohort studies.

The case-cohort study design provides a cost-effective study design for a large cohort study with competing risk outcomes. The proportional subdistribution hazards model is widely used to estimate direct covariate effects on the cumulative incidence function for competing risk data. In biomedical studies, left truncation often occurs and brings extra challenges to the analysis. Existing inverse probability weighting methods for case-cohort studies with competing risk data not only have not addressed left truncation, but also are inefficient in regression parameter estimation for fully observed covariates. We propose an augmented inverse probability-weighted estimating equation for left-truncated competing risk data to address these limitations of the current literature. We further propose a more efficient estimator when extra information from the other causes is available. The proposed estimators are consistent and asymptotically normally distributed. Simulation studies show that the proposed estimator is unbiased and leads to estimation efficiency gain in the regression parameter estimation. We analyze the Atherosclerosis Risk in Communities study data using the proposed methods.

Absolute risk from double nested case-control designs: cause-specific proportional hazards models with and without augmented estimating equations.

We estimate relative hazards and absolute risks (or cumulative incidence or crude risk) under cause-specific proportional hazards models for competing risks from double nested case-control (DNCC) data. In the DNCC design, controls are time-matched not only to cases from the cause of primary interest, but also to cases from competing risks (the phase-two sample). Complete covariate data are available in the phase-two sample, but other cohort members only have information on survival outcomes and some covariates. Design-weighted estimators use inverse sampling probabilities computed from Samuelsen-type calculations for DNCC. To take advantage of additional information available on all cohort members, we augment the estimating equations with a term that is unbiased for zero but improves the efficiency of estimates from the cause-specific proportional hazards model. We establish the asymptotic properties of the proposed estimators, including the estimator of absolute risk, and derive consistent variance estimators. We show that augmented design-weighted estimators are more efficient than design-weighted estimators. Through simulations, we show that the proposed asymptotic methods yield nominal operating characteristics in practical sample sizes. We illustrate the methods using prostate cancer mortality data from the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial Study of the National Cancer Institute.

The multivariate Bernoulli detector: change point estimation in discrete survival analysis.

Time-to-event data are often recorded on a discrete scale with multiple, competing risks as potential causes for the event. In this context, application of continuous survival analysis methods with a single risk suffers from biased estimation. Therefore, we propose the multivariate Bernoulli detector for competing risks with discrete times involving a multivariate change point model on the cause-specific baseline hazards. Through the prior on the number of change points and their location, we impose dependence between change points across risks, as well as allowing for data-driven learning of their number. Then, conditionally on these change points, a multivariate Bernoulli prior is used to infer which risks are involved. Focus of posterior inference is cause-specific hazard rates and dependence across risks. Such dependence is often present due to subject-specific changes across time that affect all risks. Full posterior inference is performed through a tailored local-global Markov chain Monte Carlo (MCMC) algorithm, which exploits a data augmentation trick and MCMC updates from nonconjugate Bayesian nonparametric methods. We illustrate our model in simulations and on ICU data, comparing its performance with existing approaches.

Testing Similarity of Parametric Competing Risks Models for Identifying Potentially Similar Pathways in Healthcare.

The identification of similar patient pathways is a crucial task in healthcare analytics. A flexible tool to address this issue are parametric competing risks models, where transition intensities may be specified by a variety of parametric distributions, thus in particular being possibly time-dependent. We assess the similarity between two such models by examining the transitions between different health states. This research introduces a method to measure the maximum differences in transition intensities over time, leading to the development of a test procedure for assessing similarity. We propose a parametric bootstrap approach for this purpose and provide a proof to confirm the validity of this procedure. The performance of our proposed method is evaluated through a simulation study, considering a range of sample sizes, differing amounts of censoring, and various thresholds for similarity. Finally, we demonstrate the practical application of our approach with a case study from urological clinical routine practice, which inspired this research.

Weighting estimation in the cause-specific Cox regression with partially missing causes of failure.

Complex diseases are often analyzed using disease subtypes classified by multiple biomarkers to study pathogenic heterogeneity. In such molecular pathological epidemiology research, we consider a weighted Cox proportional hazard model to evaluate the effect of exposures on various disease subtypes under competing-risk settings in the presence of partially or completely missing biomarkers. The asymptotic properties of the inverse and augmented inverse probability-weighted estimating equation methods are studied with a general pattern of missing data. Simulation studies have been conducted to demonstrate the double robustness of the estimators. For illustration, we applied this method to examine the association between pack-years of smoking before the age of 30 and the incidence of colorectal cancer subtypes defined by a combination of four tumor molecular biomarkers (statuses of microsatellite instability, CpG island methylator phenotype, BRAF mutation, and KRAS mutation) in the Nurses' Health Study cohort.

An augmented illness-death model for semi-competing risks with clinically immediate terminal events.

Preeclampsia is a pregnancy-associated condition posing risks of both fetal and maternal mortality and morbidity that can only resolve following delivery and removal of the placenta. Because in its typical form preeclampsia can arise before delivery, but not after, these two events exemplify the time-to-event setting of "semi-competing risks" in which a non-terminal event of interest is subject to the occurrence of a terminal event of interest. The semi-competing risks framework presents a valuable opportunity to simultaneously address two clinically meaningful risk modeling tasks: (i) characterizing risk of developing preeclampsia, and (ii) characterizing time to delivery after onset of preeclampsia. However, some people with preeclampsia deliver immediately upon diagnosis, while others are admitted and monitored for an extended period before giving birth, resulting in two distinct trajectories following the non-terminal event, which we call "clinically immediate" and "non-immediate" terminal events. Though such phenomena arise in many clinical contexts, to-date there have not been methods developed to acknowledge the complex dependencies between such outcomes, nor leverage these phenomena to gain new insight into individualized risk. We address this gap by proposing a novel augmented frailty-based illness-death model with a binary submodel to distinguish risk of immediate terminal event following the non-terminal event. The model admits direct dependence of the terminal event on the non-terminal event through flexible regression specification, as well as indirect dependence via a shared frailty term linking each submodel. We develop an efficient Bayesian sampler for estimation and corresponding model fit metrics, and derive formulae for dynamic risk prediction. In an extended example using pregnancy outcome data from an electronic health record, we demonstrate the proposed model's direct applicability to address a broad range of clinical questions.