scholarly journals Integrating latent classes in the Bayesian shared parameter joint model of longitudinal and survival outcomes

2020 ◽  
Vol 29 (11) ◽  
pp. 3294-3307
Author(s):  
Eleni-Rosalina Andrinopoulou ◽  
Kazem Nasserinejad ◽  
Rhonda Szczesniak ◽  
Dimitris Rizopoulos
Keyword(s):  
Cystic Fibrosis ◽  
Lung Function ◽  
Latent Class ◽  
Joint Model ◽  
Forced Expiratory Volume ◽  
Optimal Number ◽  
Latent Classes ◽  
Joint Models ◽  
Number Of Classes ◽  
Strength Of Association

Cystic fibrosis is a chronic lung disease requiring frequent lung-function monitoring to track acute respiratory events (pulmonary exacerbations). The association between lung-function trajectory and time-to-first exacerbation can be characterized using joint longitudinal-survival modeling. Joint models specified through the shared parameter framework quantify the strength of association between such outcomes but do not incorporate latent sub-populations reflective of heterogeneous disease progression. Conversely, latent class joint models explicitly postulate the existence of sub-populations but do not directly quantify the strength of association. Furthermore, choosing the optimal number of classes using established metrics like deviance information criterion is computationally intensive in complex models. To overcome these limitations, we integrate latent classes in the shared parameter joint model through a fully Bayesian approach. To choose the optimal number of classes, we construct a mixture model assuming more latent classes than present in the data, thereby asymptotically “emptying” superfluous latent classes, provided the Dirichlet prior on class proportions is sufficiently uninformative. Model properties are evaluated in simulation studies. Application to data from the US Cystic Fibrosis Registry supports the existence of three sub-populations corresponding to lung-function trajectories with high initial forced expiratory volume in 1 s ( FEV1), rapid FEV1 decline, and low but steady FEV1 progression. The association between FEV1 and hazard of exacerbation was negative in each class, but magnitude varied.

scholarly journals Multivariate joint modeling to identify markers of growth and lung function decline that predict cystic fibrosis pulmonary exacerbation onset

2019 ◽  
Author(s):  
Eleni-Rosalina Andrinopoulou ◽  
John Paul Clancy ◽  
Rhonda Szczesniak
Keyword(s):  
Cystic Fibrosis ◽  
Lung Function ◽  
Predictive Accuracy ◽  
Characteristic Curve ◽  
Joint Modeling ◽  
Joint Model ◽  
Receiver Operator Characteristic Curve ◽  
Joint Models ◽  
Lung Function Decline ◽  
Growth And Nutrition

Abstract Background: Attenuated decreases in lung function can signal the onset of acute respiratory events known as pulmonary exacerbation (PEs) in children and adolescents with cystic fibrosis (CF). Univariate joint modeling facilitates dynamic risk prediction of PE onset and accounts for measurement error of the lung function marker. However, CF is a multi-system disease and the extent to which simultaneously modeling growth and nutrition markers improves PE predictive accuracy is unknown. Furthermore, it is unclear which routinely collected clinical indicators of growth and nutrition in early life predict PE onset in CF. Methods: Using a longitudinal cohort of 17,100 patients aged 6-20 years (US Cystic Fibrosis Foundation Patient Registry; 2003-2015), we fit a univariate joint model of lung-function decline and PE onset and contrasted its predictive performance with a class of multivariate joint models that included combinations of growth markers as additional submodels. Outcomes were longitudinal lung function (forced expiratory volume in 1 s of % predicted), percentile measures of body mass index, weight-for-age and height-for-age and PE onset. Relevant demographic/clinical covariates were included in each submodel. We implemented a univariate joint model of lung function and time-to-PE and four multivariate joint models including growth outcomes. Results: All five joint models showed that declining lung function corresponded to slightly increased risk of PE onset (hazard ratio from univariate joint model: 0.97, P < 0.0001), and all had reasonable predictive accuracy (cross-validated area under the receiver-operator characteristic curve > 0.70). None of the growth markers alongside lung function as outcomes in multivariate joint modeling appeared to have an association with hazard of PE. Jointly modeling only lung function and PE onset yielded the most accurate (area under the receiver-operator characteristic curve = 0.75) and precise (narrowest interquartile range) predictions. Dynamic predictions were accurate across forecast horizons (0.5, 1 and 2 years) and precision improved with age. Conclusions: Including growth markers via multivariate joint models did not yield gains in prediction performance, compared to a univariate joint model with lung function. However, the joint-modeling approach itself may be useful for monitoring CF disease progression by providing a means of dynamic risk prediction.

scholarly journals Multivariate joint modeling to identify markers of growth and lung function decline that predict cystic fibrosis pulmonary exacerbation onset

2020 ◽  
Author(s):  
Eleni-Rosalina Andrinopoulou ◽  
John Paul Clancy ◽  
Rhonda Szczesniak
Keyword(s):  
Cystic Fibrosis ◽  
Lung Function ◽  
Predictive Accuracy ◽  
Characteristic Curve ◽  
Joint Modeling ◽  
Joint Model ◽  
Receiver Operator Characteristic Curve ◽  
Joint Models ◽  
Lung Function Decline ◽  
Growth And Nutrition

Abstract Background: Attenuated decreases in lung function can signal the onset of acute respiratory events known as pulmonary exacerbations (PEs) in children and adolescents with cystic fibrosis (CF). Univariate joint modeling facilitates dynamic risk prediction of PE onset and accounts for measurement error of the lung function marker. However, CF is a multi-system disease and the extent to which simultaneously modeling growth and nutrition markers improves PE predictive accuracy is unknown. Furthermore, it is unclear which routinely collected clinical indicators of growth and nutrition in early life predict PE onset in CF. Methods: Using a longitudinal cohort of 17,100 patients aged 6-20 years (US Cystic Fibrosis Foundation Patient Registry; 2003-2015), we fit a univariate joint model of lung-function decline and PE onset and contrasted its predictive performance with a class of multivariate joint models that included combinations of growth markers as additional submodels. Outcomes were longitudinal lung function (forced expiratory volume in 1 s of % predicted), percentiles of body mass index, weight-for-age and height-for-age and PE onset. Relevant demographic/clinical covariates were included in submodels. We implemented a univariate joint model of lung function and time-to-PE and four multivariate joint models including growth outcomes. Results: All five joint models showed that declining lung function corresponded to slightly increased risk of PE onset (hazard ratio from univariate joint model: 0.97, P < 0.0001), and all had reasonable predictive accuracy (cross-validated area under the receiver-operator characteristic curve > 0.70). None of the growth markers alongside lung function as outcomes in multivariate joint modeling appeared to have an association with hazard of PE. Jointly modeling only lung function and PE onset yielded the most accurate (area under the receiver-operator characteristic curve = 0.75) and precise (narrowest interquartile range) predictions. Dynamic predictions were accurate across forecast horizons (0.5, 1 and 2 years) and precision improved with age. Conclusions: Including growth markers via multivariate joint models did not yield gains in prediction performance, compared to a univariate joint model with lung function. Individualized dynamic predictions from joint modeling could enhance physician monitoring of CF disease progression by providing PE risk assessment over a patient’s clinical course.

scholarly journals Risk factor identification in cystic fibrosis by flexible hierarchical joint models

2020 ◽  
pp. 096228022095036
Author(s):  
Weiji Su ◽  
Xia Wang ◽  
Rhonda D Szczesniak
Keyword(s):  
Risk Factors ◽  
Cystic Fibrosis ◽  
Lung Function ◽  
Gaussian Process ◽  
Joint Model ◽  
Model Assessment ◽  
Link Function ◽  
Pulmonary Exacerbation ◽  
Flexible Link ◽  
Joint Models

Cystic fibrosis (CF) is a lethal autosomal disease hallmarked by respiratory failure. Maintaining lung function and minimizing frequency of acute respiratory events known as pulmonary exacerbations are essential to survival. Jointly modeling longitudinal lung function and exacerbation occurrences may provide better inference. We propose a shared-parameter joint hierarchical Gaussian process model with flexible link function to investigate the impacts of both demographic and time-varying clinical risk factors on lung function decline and to examine the associations between lung function and occurrence of pulmonary exacerbation. A two-level Gaussian process is used to capture the nonlinear longitudinal trajectory, and a flexible link function is introduced to the joint model in order to analyze binary process. Bayesian model assessment criteria are provided in examining the overall performance in joint models and marginal fitting in each submodel. We conduct simulation studies and apply the proposed model in a local CF center cohort. In the CF application, a nonlinear structure is supported in modeling both the longitudinal continuous and binary processes. A negative association is detected between lung function and pulmonary exacerbation by the joint model. The importance of risk factors, including gender, diagnostic status, insurance status, and BMI, is examined in joint models.

scholarly journals Multivariate joint modeling to identify markers of growth and lung function decline that predict cystic fibrosis pulmonary exacerbation onset

2020 ◽  
Author(s):  
Eleni-Rosalina Andrinopoulou ◽  
John Paul Clancy ◽  
Rhonda Szczesniak
Keyword(s):  
Cystic Fibrosis ◽  
Lung Function ◽  
Predictive Accuracy ◽  
Characteristic Curve ◽  
Joint Modeling ◽  
Joint Model ◽  
Receiver Operator Characteristic Curve ◽  
Joint Models ◽  
Lung Function Decline ◽  
Growth And Nutrition

Abstract Background: Attenuated decreases in lung function can signal the onset of acute respiratory events known as pulmonary exacerbations (PEs) in children and adolescents with cystic fibrosis (CF). Univariate joint modeling facilitates dynamic risk prediction of PE onset and accounts for measurement error of the lung function marker. However, CF is a multi-system disease and the extent to which simultaneously modeling growth and nutrition markers improves PE predictive accuracy is unknown. Furthermore, it is unclear which routinely collected clinical indicators of growth and nutrition in early life predict PE onset in CF. Methods: Using a longitudinal cohort of 17,100 patients aged 6-20 years (US Cystic Fibrosis Foundation Patient Registry; 2003-2015), we fit a univariate joint model of lung-function decline and PE onset and contrasted its predictive performance with a class of multivariate joint models that included combinations of growth markers as additional submodels. Outcomes were longitudinal lung function (forced expiratory volume in 1 s of % predicted), percentiles of body mass index, weight-for-age and height-for-age and PE onset. Relevant demographic/clinical covariates were included in submodels. We implemented a univariate joint model of lung function and time-to-PE and four multivariate joint models including growth outcomes. Results: All five joint models showed that declining lung function corresponded to slightly increased risk of PE onset (hazard ratio from univariate joint model: 0.97, P < 0.0001), and all had reasonable predictive accuracy (cross-validated area under the receiver-operator characteristic curve > 0.70). None of the growth markers alongside lung function as outcomes in multivariate joint modeling appeared to have an association with hazard of PE. Jointly modeling only lung function and PE onset yielded the most accurate (area under the receiver-operator characteristic curve = 0.75) and precise (narrowest interquartile range) predictions. Dynamic predictions were accurate across forecast horizons (0.5, 1 and 2 years) and precision improved with age. Conclusions: Including growth markers via multivariate joint models did not yield gains in prediction performance, compared to a univariate joint model with lung function. Individualized dynamic predictions from joint modeling could enhance physician monitoring of CF disease progression by providing PE risk assessment over a patient’s clinical course.

scholarly journals Multivariate joint modeling to identify markers of growth and lung function decline that predict cystic fibrosis pulmonary exacerbation onset

2020 ◽  
Author(s):  
Eleni-Rosalina Andrinopoulou ◽  
John Paul Clancy ◽  
Rhonda Szczesniak
Keyword(s):  
Cystic Fibrosis ◽  
Lung Function ◽  
Predictive Accuracy ◽  
Characteristic Curve ◽  
Joint Modeling ◽  
Joint Model ◽  
Receiver Operator Characteristic Curve ◽  
Joint Models ◽  
Lung Function Decline ◽  
Growth And Nutrition

Abstract Background: Attenuated decreases in lung function can signal the onset of acute respiratory events known as pulmonary exacerbations (PEs) in children and adolescents with cystic fibrosis (CF). Univariate joint modeling facilitates dynamic risk prediction of PE onset and accounts for measurement error of the lung function marker. However, CF is a multi-system disease and the extent to which simultaneously modeling growth and nutrition markers improves PE predictive accuracy is unknown. Furthermore, it is unclear which routinely collected clinical indicators of growth and nutrition in early life predict PE onset in CF. Methods: Using a longitudinal cohort of 17,100 patients aged 6-20 years (US Cystic Fibrosis Foundation Patient Registry; 2003-2015), we fit a univariate joint model of lung-function decline and PE onset and contrasted its predictive performance with a class of multivariate joint models that included combinations of growth markers as additional submodels. Outcomes were longitudinal lung function (forced expiratory volume in 1 s of % predicted), percentiles of body mass index, weight-for-age and height-for-age and PE onset. Relevant demographic/clinical covariates were included in submodels. We implemented a univariate joint model of lung function and time-to-PE and four multivariate joint models including growth outcomes. Results: All five joint models showed that declining lung function corresponded to slightly increased risk of PE onset (hazard ratio from univariate joint model: 0.97, P < 0.0001), and all had reasonable predictive accuracy (cross-validated area under the receiver-operator characteristic curve > 0.70). None of the growth markers alongside lung function as outcomes in multivariate joint modeling appeared to have an association with hazard of PE. Jointly modeling only lung function and PE onset yielded the most accurate (area under the receiver-operator characteristic curve = 0.75) and precise (narrowest interquartile range) predictions. Dynamic predictions were accurate across forecast horizons (0.5, 1 and 2 years) and precision improved with age. Conclusions: Including growth markers via multivariate joint models did not yield gains in prediction performance, compared to a univariate joint model with lung function. Individualized dynamic predictions from joint modeling could enhance physician monitoring of CF disease progression by providing PE risk assessment over a patient’s clinical course.

scholarly journals A MULTIDIMENSIONAL MODEL FOR POLYPHARMACY MEASUREMENT IN OLDER ADULTS: EVIDENCE FROM THE HEALTH RETIREMENT STUDY

2019 ◽  
Vol 3 (Supplement_1) ◽  
pp. S707-S707
Author(s):  
Rebecca Bendayan ◽  
Ewan Carr ◽  
Alex D Federman ◽  
Richard J Dobson
Keyword(s):  
Older Adults ◽  
Latent Class ◽  
Optimal Number ◽  
Model Fit ◽  
Latent Classes ◽  
Chi Square ◽  
Chronic Health ◽  
Adverse Health Outcomes ◽  
Traditional Research ◽  
Retirement Study

Abstract Polypharmacy is associated with increased health care costs and adverse health outcomes. Traditional research on polypharmacy uses dichotomous measures which overlook its multidimensional nature. We propose a new approach to grouping older adults based on the number and type of medications taken as well as other indicators of polypharmacy. Data was extracted from 1328 respondents of the 2007 Prescription Drug Survey (a sub-study of the Health Retirement Study) who were between 50 and 70 years old and taking ≥1 medication each month. Latent class analysis was carried out with the optimal number of classes assessed based on relative model fit (AIC, adjusted BIC) and interpretability. Latent classes were formed based on the number of medications, drug types, duration of medication intake, side effects, and presence of chronic health conditions. A four-class model was selected based on model fit and interpretability of the solutions. Although there was some overlap when we compared our model with standard cut-offs for polypharmacy (i.e., ‘high polypharmacy’ classes were more likely to take 5+ and 9+ medications), chi-square tests showed significant differences between our latent classes and cut-offs based on 5+ [X2 = 894; p&lt;0.001] and 9+ medications [X2 = 398; p&lt;0.001]. Among individuals taking &lt;5 medications, our model differentiated two distinct types of ‘low polypharmacy’ based on the types of drugs reported. Our proposal to incorporate a multidimensional assessment of polypharmacy considers the wider context of medication use and chronic health in older age, moving beyond crude medication counts.

scholarly journals 1014 Relationship Between Lung Function and Obstructive Sleep Apnea in Cystic Fibrosis

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A385-A385
Author(s):  
A Shakkottai ◽  
S Z Nasr ◽  
F Hassan ◽  
L M O’Brien ◽  
R D Chervin
Keyword(s):  
Cystic Fibrosis ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Lung Function ◽  
Forced Expiratory Volume ◽  
Apnea Hypopnea Index ◽  
Lung Function Decline ◽  
Obstructive Sleep ◽  
Larger Sample ◽  
Training Grant

Abstract Introduction The frequency of obstructive sleep apnea (OSA) may be high among patients with cystic fibrosis (CF), a life-shortening, genetic respiratory disease that affects approximately 30,000 Americans. Yet, the potential relationship between OSA and lung function has not been thoroughly explored. Methods Single-center retrospective review of polysomnography (PSG) results from 2009-2017 in referred patients with CF and available pulmonary function data (PFTs) obtained at time of PSG and at 3, 6, 9, and 12-months prior. Results Mean ages were 11.1±3.9 (sd) and 37.1±14.1 years, among 18 children and 16 adults, respectively. Mean body mass index (BMI) was normal in both groups (62.5±26.6% in children; 25.1±6.4 kg/m2 in adults). Twenty-six subjects (76%) had OSA (apnea-hypopnea index &gt;1 in children, ≥5 in adults). Mean forced expiratory volume in 1 second percent predicted (FEV1 PPD) was higher among subjects with vs. without OSA at PSG and at each time-point in the year prior, independent of age and BMI at PSG (longitudinal mixed effects model, β=19.0, SE=8.1, p=0.028). While FEV1 PPD remained unchanged in the non-OSA group, FEV1 PPD at PSG was lower, in comparison to the year prior in subjects with OSA, with the greatest difference observed at 9-months prior to PSG (2-sample t-test, difference of -6.6% vs 0.6% in OSA vs. non-OSA groups respectively, p=0.078). Conclusion The PFTs, as daytime markers of CF lung disease severity, do not seem to reliably predict risk for OSA. In our sample, CF patients with vs. without OSA had better PFTs at baseline but they also showed a greater tendency for decline in PFTs over the year prior to OSA diagnosis. Larger sample size and longer duration of assessment may help, going forward, to assess any potential adverse impact of OSA on lung function decline. Support NIH Training Grant (T32NS007222, F32HL145915)

scholarly journals Lung function over the life course of paediatric and adult patients with cystic fibrosis from a large multi-centre registry

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Arul Earnest ◽  
Farhad Salimi ◽  
Claire E. Wainwright ◽  
Scott C. Bell ◽  
Rasa Ruseckaite ◽  
...  
Keyword(s):  
Cystic Fibrosis ◽  
Lung Function ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Pancreatic Insufficiency ◽  
Forced Expiratory Volume ◽  
Rate Of Change ◽  
Data Registry ◽  
Mortality Outcome ◽  
The Impact

Abstract A key measure of lung function in people with Cystic Fibrosis (CF) is Forced Expiratory Volume in the first second FEV1 percent predicted (FEV1pp). This study aimed to address challenges in identifying predictors of FEV1pp, specifically dealing with non-linearity and the censoring effect of death. Data was obtained from a large multi-centre Australian Cystic Fibrosis Data Registry (ACFDR). A linear mixed model was used to study FEV1pp as the endpoint. There were 3655 patients (52.4% male) included in our study. Restricted cubic splines were used to fit the non-linear relationship between age of visit and FEV1pp. The following predictors were found to be significant in the multivariate model: age of patient at visit, BMI z-score, age interaction with lung transplantation, insulin dependent diabetes, cirrhosis/portal hypertension, pancreatic insufficiency, Pseudomonas aeruginosa infection and baseline variability in FEV1pp. Those with P. aeruginosa infection had a lower mean difference in FEV1pp of 4.7 units, p < 0.001 compared to those who did not have the infection. Joint modelling with mortality outcome did not materially affect our findings. These models will prove useful for to study the impact of CFTR modulator therapies on rate of change of lung function among patients with CF.

scholarly journals Burkholderia dolosa phenotypic variation during the decline in lung function of a cystic fibrosis patient during 5.5 years of chronic colonization

2014 ◽  
Vol 63 (4) ◽  
pp. 594-601 ◽  
Author(s):  
Ana Sílvia Moreira ◽  
Carla P. Coutinho ◽  
Pilar Azevedo ◽  
Luís Lito ◽  
José Melo-Cristino ◽  
...  
Keyword(s):  
Cystic Fibrosis ◽  
Lung Function ◽  
Fungal Pathogens ◽  
Forced Expiratory Volume ◽  
Burkholderia Cenocepacia ◽  
Epidemiological Surveillance ◽  
Lung Function Decline ◽  
Swarming Motility ◽  
Systematic Assessment ◽  
Chronic Colonization

Although rarely isolated from cystic fibrosis (CF) patients, Burkholderia dolosa is associated with accelerated lung function decline. During 18 years of epidemiological surveillance in the major Portuguese CF centre in Lisbon, only one patient was infected with B. dolosa. Pulmonary deterioration, associated with the evolution of forced expiratory volume in 1 s, occurred during 5.5 years of colonization with this B. dolosa clone (with the new sequence type ST-668). Transient co-colonization with Burkholderia cenocepacia and other bacterial and fungal pathogens occurred, but B. dolosa prevailed until the patient’s death. The systematic assessment of relevant phenotypes for the sequential clonal isolates examined in this retrospective study (14 of B. dolosa and four of B. cenocepacia) showed that they were variants, although in general no isolation time-dependent pattern of alteration was identified. However, the first B. dolosa isolate retrieved was more susceptible to gentamicin, imipenem and tobramycin, and exhibited a higher swarming motility compared with most of the isolates obtained during the later stages of disease progression and antimicrobial therapy.

scholarly journals Pulmonary function deficits in newborn screened infants with cystic fibrosis managed with standard UK care are mild and transient

2017 ◽  
Vol 50 (5) ◽  
pp. 1700326 ◽  
Author(s):  
Gwyneth Davies ◽  
Janet Stocks ◽  
Lena P. Thia ◽  
Ah-Fong Hoo ◽  
Andrew Bush ◽  
...  
Keyword(s):  
Cystic Fibrosis ◽  
Lung Function ◽  
Early Life ◽  
Treatment Protocol ◽  
Forced Expiratory Volume ◽  
Z Score ◽  
Average Group ◽  
Significant Difference ◽  
Residual Capacity ◽  
High Risk Infants

With the advent of novel designer molecules for cystic fibrosis (CF) treatment, there is huge need for early-life clinical trial outcomes, such as infant lung function (ILF). We investigated the degree and tracking of ILF abnormality during the first 2 years of life in CF newborn screened infants.Forced expiratory volume in 0.5 s (FEV0.5), lung clearance index (LCI) and plethysmographic functional residual capacity were measured at ∼3 months, 1 year and 2 years in 62 infants with CF and 34 controls.By 2 years there was no significant difference in FEV0.5 z-score between CF and controls, whereas mean LCI z-score was 0.81 (95% CI 0.45–1.17) higher in CF. However, there was no significant association between LCI z-score at 2 years with either 3-month or 1-year results. Despite minimal average group changes in any ILF outcome during the second year of life, marked within-subject changes occurred. No child had abnormal LCI or FEV0.5 on all test occasions, precluding the ability to identify “high-risk” infants in early life.In conclusion, changes in lung function are mild and transient during the first 2 years of life in newborn screened infants with CF when managed according to a standardised UK treatment protocol. Their potential role in tracking disease to later childhood will be ascertained by ongoing follow-up.

Sign in / Sign up

Export Citation Format

Share Document