Discussion of “A risk-based measure of time-varying prognostic discrimination for survival models,” by C. Jason Liang and Patrick J. Heagerty

Biometrics ◽  
2016 ◽  
Vol 73 (3) ◽  
pp. 739-741
Author(s):  
Thomas Alexander Gerds ◽  
Martin Schumacher
Keyword(s):  
Survival Models ◽  
Time Varying

scholarly journals A Tutorial on Evaluating the Time-Varying Discrimination Accuracy of Survival Models Used in Dynamic Decision Making

2018 ◽  
Vol 38 (8) ◽  
pp. 904-916 ◽  
Author(s):  
Aasthaa Bansal ◽  
Patrick J. Heagerty
Keyword(s):  
Decision Making ◽  
Statistical Methods ◽  
Sensitivity And Specificity ◽  
Prognostic Model ◽  
Dynamic Decision Making ◽  
Time Dependent ◽  
Survival Models ◽  
Biliary Cirrhosis ◽  
Time Varying ◽  
Over Time

Many medical decisions involve the use of dynamic information collected on individual patients toward predicting likely transitions in their future health status. If accurate predictions are developed, then a prognostic model can identify patients at greatest risk for future adverse events and may be used clinically to define populations appropriate for targeted intervention. In practice, a prognostic model is often used to guide decisions at multiple time points over the course of disease, and classification performance (i.e., sensitivity and specificity) for distinguishing high-risk v. low-risk individuals may vary over time as an individual’s disease status and prognostic information change. In this tutorial, we detail contemporary statistical methods that can characterize the time-varying accuracy of prognostic survival models when used for dynamic decision making. Although statistical methods for evaluating prognostic models with simple binary outcomes are well established, methods appropriate for survival outcomes are less well known and require time-dependent extensions of sensitivity and specificity to fully characterize longitudinal biomarkers or models. The methods we review are particularly important in that they allow for appropriate handling of censored outcomes commonly encountered with event time data. We highlight the importance of determining whether clinical interest is in predicting cumulative (or prevalent) cases over a fixed future time interval v. predicting incident cases over a range of follow-up times and whether patient information is static or updated over time. We discuss implementation of time-dependent receiver operating characteristic approaches using relevant R statistical software packages. The statistical summaries are illustrated using a liver prognostic model to guide transplantation in primary biliary cirrhosis.

Rejoinder to discussions on: A risk-based measure of time-varying prognostic discrimination for survival models

Biometrics ◽  
2016 ◽  
Vol 73 (3) ◽  
pp. 745-748
Author(s):  
C. Jason Liang ◽  
Patrick J. Heagerty
Keyword(s):  
Survival Models ◽  
Time Varying

scholarly journals Further Results on the Proportional Vitalities Model

Entropy ◽  
2021 ◽  
Vol 23 (9) ◽  
pp. 1201
Author(s):  
Mohamed Kayid
Keyword(s):  
Growth Parameter ◽  
Stochastic Ordering ◽  
Survival Models ◽  
Hazard Rates ◽  
Time Varying ◽  
Proportional Hazard ◽  
Model Potentials ◽  
Dynamic Version

In contrast to many survival models such as proportional hazard rates and proportional mean residual lives, the proportional vitalities model has also been introduced in the literature. In this paper, further stochastic ordering properties of a dynamic version of the model with a random vitality growth parameter are investigated. Examples are presented to illustrate different established properties of the model. Potentials for inference about the parameters in proportional vitalities model with possibly time-varying effects are also argued and discussed.

scholarly journals 1506Flexible parametric survival models investigating factors associated with diabetes-related foot ulcer time-to-healing

2021 ◽  
Vol 50 (Supplement_1) ◽  
Author(s):  
Yuqi Zhang ◽  
Susanna Cramb ◽  
Steven McPhail ◽  
Rosana Pacella ◽  
Jaap van Netten ◽  
...  
Keyword(s):  
Foot Ulcer ◽  
Negative Influence ◽  
Healing Time ◽  
Survival Models ◽  
Foot Ulcers ◽  
Time Varying ◽  
Factors Associated ◽  
Varying Coefficients ◽  
Time Varying Coefficients ◽  
Parametric Survival

Abstract Background Diabetes-related foot ulcers (DFU) take months to heal, reduce patient’s quality-of-life, and induce large healthcare expenditure. Various factors have been identified to influence DFU healing at fixed periods, however, data on factors associated with time-to-healing is scarce. Methods Patients presenting with DFU to Diabetic Foot Services across Queensland, Australia between July 2011 and December 2017 were included and had their demographics, disease history and treatments examined at baseline. Outcome of interest was healing of all ulcers within two-year follow-up time. Time-to-healing and associated factors were examined using flexible parametric survival models, which easily enabled including time-varying coefficients and predicting proportions healed. Results Of 4,709 included patients (median age 63 years, 69.5% male, 10.5% Indigenous), median time-to-healing was 112 days, and 68% healed within two years. Younger age (<60 years), geographical remoteness, smoking, neuropathy, deep ulcers, infection, not receiving offloading, and no recent podiatry treatment were independently associated with longer time-to-healing. Time-varying effects of peripheral artery disease and ulcer size were identified for the first time: both had a negative influence on healing with effects diminishing after six months. The predicted proportions healed, for example, within six months is 65.0% (63.3-66.7) for people residing in a major city, 54.6% (52.6-56.8) in regional area, and 40.3% (34.6-47.1) in remote area. Conclusions This study identified novel and confirmatory factors influencing time-to-healing over 24 months in a large real-world cohort of people with diabetes-related foot ulcers. Visualizing the adjusted predicted proportion healed revealed the influence each factor had on healing rates over time. Key messages Flexible parametric survival model provided flexibility in investigating time-varying effects and outcome prediction in those with diabetes-related foot ulcer healing.

scholarly journals A risk-based measure of time-varying prognostic discrimination for survival models

Biometrics ◽  
2016 ◽  
Vol 73 (3) ◽  
pp. 725-734 ◽  
Author(s):  
C. Jason Liang ◽  
Patrick J. Heagerty
Keyword(s):  
Survival Models ◽  
Time Varying

scholarly journals Subjective Environmental Experiences and Women’s Breastfeeding Journeys: A Survival Analysis Using an Online Survey of UK Mothers

2020 ◽  
Vol 17 (21) ◽  
pp. 7903
Author(s):  
Laura J. Brown ◽  
Sarah Myers ◽  
Abigail E. Page ◽  
Emily H. Emmott
Keyword(s):  
Survival Analysis ◽  
Exclusive Breastfeeding ◽  
Online Survey ◽  
Survival Models ◽  
Retrospective Data ◽  
Time Varying ◽  
Environmental Measures ◽  
Social Environmental ◽  
Social Environmental Factors ◽  
Over Time

Local physical and social environmental factors are important drivers of human health and behaviour. Environmental perception has been linked with both reproduction and parenting, but links between subjective environmental experiences and breastfeeding remain unclear. Using retrospective data from an online survey of UK mothers of children aged 0–24 months, Cox-Aalen survival models test whether negative subjective environmental experiences negatively correlated with any and exclusive breastfeeding (max n = 473). Matching predictions, hazards of stopping any breastfeeding were increased, albeit non-significantly, across the five environmental measures (HR: 1.05–1.26) Hazards for stopping exclusive breastfeeding were however (non-significantly) reduced (HR: 0.65–0.87). Score processes found no significant time-varying effects. However, estimated cumulative coefficient graphs showed that the first few weeks postpartum were most susceptible to environmental influences and that contrary to our predictions, mothers with worse subjective environmental experiences were less likely to stop breastfeeding at this time. In addition, the hazard of stopping exclusive breastfeeding declined over time for mothers who thought that littering was a problem. The predicted increased hazards of stopping breastfeeding were only evident in the later stages of any breastfeeding and only for mothers who reported littering as a problem or that people tended not to know each other. Perceived harsher physical and social environmental conditions are assumed to deter women from breastfeeding, but this may not always be the case. Women’s hazards of stopping breastfeeding change over time and there may be particular timepoints in their breastfeeding journeys where subjective environmental experiences play a role.

Sign in / Sign up

Export Citation Format

Share Document