A lag functional linear model for prediction of magnetization transfer ratio in multiple sclerosis lesions

Pomann, Gina‐Maria; Staicu, Ana‐Maria; Lobatón, Edgar; Mejia, Amanda F.; Reich, Daniel S.; Sweeney, Elizabeth; Shinohara, Russell T.

doi:10.1214/16-aoas981

Cited by 14 publications

(33 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, newer research sequences with putative higher sensitivity to changes in myelin, such as MTR, could also be used in this study design and their added value could be evaluated. 23–25…”

Section: Discussionmentioning

confidence: 99%

Experimental design and sample size considerations in longitudinal magnetic resonance imaging-based biomarker detection for multiple sclerosis

Schindler

Reich

et al. 2020

Stat Methods Med Res

View full text Add to dashboard Cite

Several modeling approaches have been developed to quantify differences in multiple sclerosis lesion evolution on magnetic resonance imaging to identify the effect of treatment on disease progression. These studies have limited clinical applicability due to onerous scan frequency and lengthy study duration. Efficient methods are needed to reduce the required sample size, study duration, and sampling frequency in longitudinal magnetic resonance imaging studies. We develop a data-driven approach to identify parameters of study design for evaluation of longitudinal magnetic resonance imaging biomarkers of multiple sclerosis lesion evolution. Our design strategies are considerably shorter than those described in previous studies, thus having the potential to lower costs of clinical trials. From a dataset of 36 multiple sclerosis patients with at least six monthly magnetic resonance imagings, we extracted new lesions and performed principal component analysis to estimate a biomarker that recapitulated lesion recovery. We tested the effect of multiple sclerosis disease modifying therapy on the lesion evolution index in three experimental designs and calculated sample sizes needed to appropriately power studies. Our proposed methods can be used to calculate required sample size and scan frequency in observational studies of multiple sclerosis disease progression as well as in designing clinical trials to find effects of treatment on multiple sclerosis lesion evolution.

show abstract

Section: Discussionmentioning

confidence: 99%

Experimental design and sample size considerations in longitudinal magnetic resonance imaging-based biomarker detection for multiple sclerosis

Schindler

Reich

et al. 2020

Stat Methods Med Res

View full text Add to dashboard Cite

show abstract

“…This has included work in variable selection , interactions , and nonlinear effects . The functional model can also be adapted for dynamic risk assessment using a historical functional linear model . Empirical work has shown that different formulations of the functional model perform better in different settings .…”

Section: Methodsmentioning

confidence: 99%

A comparison of risk prediction methods using repeated observations: an application to electronic health records for hemodialysis

Goldstein

Pomann

Winkelmayer

et al. 2017

Statistics in Medicine

View full text Add to dashboard Cite

An increasingly important data source for the development of clinical risk prediction models are Electronic health records (EHRs). One of their key advantages is that they contain data on many individuals collected over time. This allows one to incorporate more clinical information into a risk model. However, traditional methods for developing risk models are not well suited to these irregularly collected clinical covariates. In this paper, we compare a range of approaches for using longitudinal predictors in a clinical risk model. Using data from an EHR for patients undergoing hemodialysis, we incorporate five different clinical predictors to a risk model for patient mortality. We consider different approaches for treating the repeated measurements including use of summary statistics, machine learning methods, functional data analysis and joint models. We follow-up our empirical findings with a simulation study. Overall, our results suggest that simple approaches perform just as well, if not better, than more complex analytic approaches. These results have important implication for development of risk prediction models with EHRs.

show abstract

“…One possible approach to account for the past functional covariates is to consider a regression model like the historical functional linear model (see Malfait and Ramsay (), Pomann et al . (), Scheipl et al . () and Kim et al .…”

Section: Discussionmentioning

confidence: 96%

“…E[Y ij |X i1 .·/, : : : , X in i .·/] = E[Y ij |X ij .·/]: This assumption makes sense for our application, but it may not be reasonable for other situations. One possible approach to account for the past functional covariates is to consider a regression model like the historical functional linear model (see Malfait and Ramsay (2003), Pomann et al (2016), Scheipl et al (2015) and Kim et al (2011)).…”

Section: Discussionmentioning

confidence: 99%

Longitudinal Dynamic Functional Regression

Staicu

Islam

Dumitru

et al. 2019

Journal of the Royal Statistical Society Series C: Applied Statistics

View full text Add to dashboard Cite

Summary The paper develops a parsimonious modelling framework to study the time‐varying association between scalar outcomes and functional predictors observed at many instances, in longitudinal studies. The methods enable us to reconstruct the full trajectory of the response and are applicable to Gaussian and non‐Gaussian responses. The idea is to model the time‐varying functional predictors by using orthogonal basis functions and to expand the time‐varying regression coefficient by using the same basis. Numerical investigation through simulation studies and data analysis show excellent performance in terms of accurate prediction and efficient computations, when compared with existing alternatives. The methods are inspired and applied to an animal science application, where of interest is to study the association between the feed intake of lactating sows and the minute‐by‐minute temperature throughout the 21 days of their lactation period. R code and an R illustration are provided.

show abstract

A lag functional linear model for prediction of magnetization transfer ratio in multiple sclerosis lesions

Cited by 14 publications

References 54 publications

Experimental design and sample size considerations in longitudinal magnetic resonance imaging-based biomarker detection for multiple sclerosis

Experimental design and sample size considerations in longitudinal magnetic resonance imaging-based biomarker detection for multiple sclerosis

A comparison of risk prediction methods using repeated observations: an application to electronic health records for hemodialysis

Longitudinal Dynamic Functional Regression

Contact Info

Product

Resources

About