Dynamic prediction of cumulative incidence functions by direct binomial regression

Grand, Mia Klinten; Witte, T.J.M. de; Putter, Hein

doi:10.1002/bimj.201700194

Cited by 7 publications

(9 citation statements)

References 22 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Ignores underlying covariate trajectory, often correlations a ignored, requires complete follow-up, and LOCF approach induces bias. dynpred and coxph functions in R. Competing risks [ 34 , 41 ], recurrent events [ 36 ], combined with TSM [ 34 , 38 , 40 ], pseudo-observations [ 35 , 41 ], cure fraction models [ 42 ]. Employed to predict relapse/death for those in leukaemia remission after transplant [ 34 ].…”

Section: Resultsmentioning

confidence: 99%

“…Competing risks [34,41], recurrent events [36], combined with TSM [34,38,40], pseudo-observations [35,41], cure fraction models [42].…”

Section: Generalised Estimating Equationsmentioning

confidence: 99%

“…data required to develop a CPM at each landmark time) into a stacked dataset and fit just one model to the available data, including landmark time as an independent variable. This is often referred to as the`super landmark model' [34,35]. Correlations between the within-subject observations can be accounted for using GEEs [35], and non-parametric time-varying coefficients can be modelled over landmark time points [36,37].…”

Section: Landmark Analysismentioning

confidence: 99%

“…However, it appears that there is no general guidance on the choice of landmark times as they vary with each application. Examples include using quantiles of event times to capture the changes in the at-risk population [35] or using different follow-up appointment times in clinical practice [34]. Implementation can also be challenging for left-censored information, and routinely collected data with no defined baseline time-point [37].…”

Section: Landmark Analysismentioning

confidence: 99%

See 3 more Smart Citations

Harnessing repeated measurements of predictor variables for clinical risk prediction: a review of existing methods

et al. 2020

View full text Add to dashboard Cite

Background: Clinical prediction models (CPMs) predict the risk of health outcomes for individual patients. The majority of existing CPMs only harness cross-sectional patient information. Incorporating repeated measurements, such as those stored in electronic health records, into CPMs may provide an opportunity to enhance their performance. However, the number and complexity of methodological approaches available could make it difficult for researchers to explore this opportunity. Our objective was to review the literature and summarise existing approaches for harnessing repeated measurements of predictor variables in CPMs, primarily to make this field more accessible for applied researchers. Methods: MEDLINE, Embase and Web of Science were searched for articles reporting the development of a multivariable CPM for individual-level prediction of future binary or time-to-event outcomes and modelling repeated measurements of at least one predictor. Information was extracted on the following: the methodology used, its specific aim, reported advantages and limitations, and software available to apply the method. Results: The search revealed 217 relevant articles. Seven methodological frameworks were identified: time-dependent covariate modelling, generalised estimating equations, landmark analysis, two-stage modelling, joint-modelling, trajectory classification and machine learning. Each of these frameworks satisfies at least one of three aims: to better represent the predictor-outcome relationship over time, to infer a covariate value at a pre-specified time and to account for the effect of covariate change. Conclusions: The applicability of identified methods depends on the motivation for including longitudinal information and the method's compatibility with the clinical context and available patient data, for both model development and risk estimation in practice.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Competing risks [34,41], recurrent events [36], combined with TSM [34,38,40], pseudo-observations [35,41], cure fraction models [42].…”

Section: Generalised Estimating Equationsmentioning

confidence: 99%

Section: Landmark Analysismentioning

confidence: 99%

Section: Landmark Analysismentioning

confidence: 99%

See 2 more Smart Citations

Harnessing repeated measurements of predictor variables for clinical risk prediction: a review of existing methods

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Thereby, the hazard function provides a general dynamic concept on which all these approaches can be based. Of course, to build landmark regression models alternative modeling approaches like joint models for longitudinal and time‐to‐event data (Rizopoulos, ; Rizopoulos et al., ) and direct binomial regression (Grand, de Witte, & Putter, ) may also be used. For competing risk outcomes, Cox regression models for the cause‐specific hazards or, alternatively, the Fine & Gray model for the subdistribution hazard may be used (Cortese & Andersen, ; Cortese, Gerds, & Andersen, ).…”

Section: Discussionmentioning

confidence: 99%

Dynamic prediction: A challenge for biostatisticians, but greatly needed by patients, physicians and the public

et al. 2019

View full text Add to dashboard Cite

Prognosis is usually expressed in terms of the probability that a patient will or will not have experienced an event of interest t years after diagnosis of a disease. This quantity, however, is of little informative value for a patient who is still event-free after a number of years. Such a patient would be much more interested in the conditional probability of being event-free in the upcoming years, given that he/she did not experience the event in the s years after diagnosis, called "conditional survival." It is the simplest form of a dynamic prediction and can be dealt with using straightforward extensions of standard time-to-event analyses in clinical cohort studies. For a healthy individual, a related problem with further complications is the so-called "ageconditional probability of developing cancer" in the next t years. Here, the competing risk of dying from other diseases has to be taken into account. For both situations, the hazard function provides the central dynamic concept, which can be further extended in a natural way to build dynamic prediction models that incorporate both baseline and time-dependent characteristics. Such models are able to exploit the most current information accumulating over time in order to accurately predict the further course or development of a disease. In this article, the biostatistical challenges as well as the relevance and importance of dynamic prediction are illustrated using studies of multiple myeloma, a hematologic malignancy with a formerly rather poor prognosis which has improved over the last few years. K E Y W O R D Sage-conditional probability of developing cancer, conditional survival, dynamic prognosis, landmark regression models, time-dependent bias 822In doing so, we consider only absolute CS since this is the quantity of major interest in a clinical context. From a public health or epidemiologic perspective, however, relative CS, defined as the ratio of survival probabilities with the denominator derived from an age-adjusted normal population, may also be a highly relevant quantity (Shack, Braynt, Lockwood, & Ellison, 2013), which is sometimes also used for a statistical definition of cure (Baade, Youlden, & Chambers, 2011).On the other hand, for a healthy individual it might be of interest to know the probability of developing a certain disease, for example, a specific type of cancer. Quantities that are regularly published are age-specific incidence rates. These, however, cannot be directly translated into probabilities since death from other causes, for example, cardiovascular death, constitutes a competing event. Thus, the framework of multistate competing risks models has to be used to account for this fact. In a similar way as argued for CS, the resulting probabilities are of little value for an individual who is still alive and healthy at some age . Here, age-conditional probabilities of developing or dying from cancer are of interest for healthy individuals and today these are frequently reported by tumor registers and/or national statistical offi...

show abstract

Multiple imputation strategies for a bounded outcome variable in a competing risks analysis

Curnow

Hughes

Birnie

et al. 2021

Statistics in Medicine

View full text Add to dashboard Cite

In patient follow‐up studies, events of interest may take place between periodic clinical assessments and so the exact time of onset is not observed. Such events are known as “bounded” or “interval‐censored.” Methods for handling such events can be categorized as either (i) applying multiple imputation (MI) strategies or (ii) taking a full likelihood‐based (LB) approach. We focused on MI strategies, rather than LB methods, because of their flexibility. We evaluated MI strategies for bounded event times in a competing risks analysis, examining the extent to which interval boundaries, features of the data distribution and substantive analysis model are accounted for in the imputation model. Candidate imputation models were predictive mean matching (PMM); log‐normal regression with postimputation back‐transformation; normal regression with and without restrictions on the imputed values and Delord and Genin's method based on sampling from the cumulative incidence function. We used a simulation study to compare MI methods and one LB method when data were missing at random and missing not at random, also varying the proportion of missing data, and then applied the methods to a hematopoietic stem cell transplantation dataset. We found that cumulative incidence and median event time estimation were sensitive to model misspecification. In a competing risks analysis, we found that it is more important to account for features of the data distribution than to restrict imputed values based on interval boundaries or to ensure compatibility with the substantive analysis by sampling from the cumulative incidence function. We recommend MI by type 1 PMM.

show abstract

Dynamic prediction of cumulative incidence functions by direct binomial regression

Cited by 7 publications

References 22 publications

Harnessing repeated measurements of predictor variables for clinical risk prediction: a review of existing methods

Harnessing repeated measurements of predictor variables for clinical risk prediction: a review of existing methods

Dynamic prediction: A challenge for biostatisticians, but greatly needed by patients, physicians and the public

Multiple imputation strategies for a bounded outcome variable in a competing risks analysis

Contact Info

Product

Resources

About